2024/04/12 18:14:25 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1709703021 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 9.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.5 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.5, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.7.0 MMEngine: 0.8.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl', 'port': 29320} seed: 1709703021 Distributed launcher: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2024/04/12 18:14:27 - mmengine - INFO - Config: default_scope = 'embodiedscan' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=4), sampler_seed=dict(type='DistSamplerSeedHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl', port=29320)) log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False n_points = 100000 backend_args = None model = dict( type='Embodied3DDetector', data_preprocessor=dict( type='Det3DDataPreprocessor', mean=[ 123.675, 116.28, 103.53, ], std=[ 58.395, 57.12, 57.375, ], bgr_to_rgb=True, pad_size_divisor=32, batchwise_inputs=True), backbone=dict( type='mmdet.ResNet', depth=50, base_channels=16, num_stages=4, out_indices=( 0, 1, 2, 3, ), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'), style='pytorch'), backbone_3d=dict(type='MinkResNet', in_channels=3, depth=34), use_xyz_feat=True, bbox_head=dict( type='FCAF3DHeadRotMat', in_channels=( 128, 256, 512, 1024, ), out_channels=128, voxel_size=0.01, pts_prune_threshold=20000, pts_assign_threshold=27, pts_center_threshold=18, num_classes=284, num_reg_outs=12, center_loss=dict(type='mmdet.CrossEntropyLoss', use_sigmoid=True), bbox_loss=dict( type='BBoxCDLoss', mode='l1', loss_weight=1.0, group='g8'), cls_loss=dict(type='mmdet.FocalLoss'), decouple_bbox_loss=True, decouple_groups=4, decouple_weights=[ 0.2, 0.2, 0.2, 0.4, ]), coord_type='DEPTH', train_cfg=dict(), test_cfg=dict(nms_pre=1000, iou_thr=0.5, score_thr=0.01)) dataset_type = 'EmbodiedScanDataset' data_root = 'data' class_names = ( 'adhesive tape', 'air conditioner', 'alarm', 'album', 'arch', 'backpack', 'bag', 'balcony', 'ball', 'banister', 'bar', 'barricade', 'baseboard', 'basin', 'basket', 'bathtub', 'beam', 'beanbag', 'bed', 'bench', 'bicycle', 'bidet', 'bin', 'blackboard', 'blanket', 'blinds', 'board', 'body loofah', 'book', 'boots', 'bottle', 'bowl', 'box', 'bread', 'broom', 'brush', 'bucket', 'cabinet', 'calendar', 'camera', 'can', 'candle', 'candlestick', 'cap', 'car', 'carpet', 'cart', 'case', 'chair', 'chandelier', 'cleanser', 'clock', 'clothes', 'clothes dryer', 'coat hanger', 'coffee maker', 'coil', 'column', 'commode', 'computer', 'conducting wire', 'container', 'control', 'copier', 'cosmetics', 'couch', 'counter', 'countertop', 'crate', 'crib', 'cube', 'cup', 'curtain', 'cushion', 'decoration', 'desk', 'detergent', 'device', 'dish rack', 'dishwasher', 'dispenser', 'divider', 'door', 'door knob', 'doorframe', 'doorway', 'drawer', 'dress', 'dresser', 'drum', 'duct', 'dumbbell', 'dustpan', 'dvd', 'eraser', 'excercise equipment', 'fan', 'faucet', 'fence', 'file', 'fire extinguisher', 'fireplace', 'flowerpot', 'flush', 'folder', 'food', 'footstool', 'frame', 'fruit', 'furniture', 'garage door', 'garbage', 'glass', 'globe', 'glove', 'grab bar', 'grass', 'guitar', 'hair dryer', 'hamper', 'handle', 'hanger', 'hat', 'headboard', 'headphones', 'heater', 'helmets', 'holder', 'hook', 'humidifier', 'ironware', 'jacket', 'jalousie', 'jar', 'kettle', 'keyboard', 'kitchen island', 'kitchenware', 'knife', 'label', 'ladder', 'lamp', 'laptop', 'ledge', 'letter', 'light', 'luggage', 'machine', 'magazine', 'mailbox', 'map', 'mask', 'mat', 'mattress', 'menu', 'microwave', 'mirror', 'molding', 'monitor', 'mop', 'mouse', 'napkins', 'notebook', 'ottoman', 'oven', 'pack', 'package', 'pad', 'pan', 'panel', 'paper', 'paper cutter', 'partition', 'pedestal', 'pen', 'person', 'piano', 'picture', 'pillar', 'pillow', 'pipe', 'pitcher', 'plant', 'plate', 'player', 'plug', 'plunger', 'pool', 'pool table', 'poster', 'pot', 'price tag', 'printer', 'projector', 'purse', 'rack', 'radiator', 'radio', 'rail', 'range hood', 'refrigerator', 'remote control', 'ridge', 'rod', 'roll', 'roof', 'rope', 'sack', 'salt', 'scale', 'scissors', 'screen', 'seasoning', 'shampoo', 'sheet', 'shelf', 'shirt', 'shoe', 'shovel', 'shower', 'sign', 'sink', 'soap', 'soap dish', 'soap dispenser', 'socket', 'speaker', 'sponge', 'spoon', 'stairs', 'stall', 'stand', 'stapler', 'statue', 'steps', 'stick', 'stool', 'stopcock', 'stove', 'structure', 'sunglasses', 'support', 'switch', 'table', 'tablet', 'teapot', 'telephone', 'thermostat', 'tissue', 'tissue box', 'toaster', 'toilet', 'toilet paper', 'toiletry', 'tool', 'toothbrush', 'toothpaste', 'towel', 'toy', 'tray', 'treadmill', 'trophy', 'tube', 'tv', 'umbrella', 'urn', 'utensil', 'vacuum cleaner', 'vanity', 'vase', 'vent', 'ventilation', 'wardrobe', 'washbasin', 'washing machine', 'water cooler', 'water heater', 'window', 'window frame', 'windowsill', 'wine', 'wire', 'wood', 'wrap', ) head_labels = [ 48, 177, 82, 179, 37, 243, 28, 277, 32, 84, 215, 145, 182, 170, 22, 72, 30, 141, 65, 257, 221, 225, 52, 75, 231, 158, 236, 156, 47, 74, 6, 18, 71, 242, 217, 251, 66, 263, 5, 45, 14, 73, 278, 198, 24, 23, 196, 252, 19, 135, 26, 229, 183, 200, 107, 272, 246, 269, 125, 59, 279, 15, 163, 258, 57, 195, 51, 88, 97, 58, 102, 36, 137, 31, 80, 160, 155, 61, 238, 96, 190, 25, 219, 152, 142, 201, 274, 249, 178, 192, ] common_labels = [ 189, 164, 101, 205, 273, 233, 131, 180, 86, 220, 67, 268, 224, 270, 53, 203, 237, 226, 10, 133, 248, 41, 55, 16, 199, 134, 99, 185, 2, 20, 234, 194, 253, 35, 174, 8, 223, 13, 91, 262, 230, 121, 49, 63, 119, 162, 79, 168, 245, 267, 122, 104, 100, 1, 176, 280, 140, 209, 259, 143, 165, 147, 117, 85, 105, 95, 109, 207, 68, 175, 106, 60, 4, 46, 171, 204, 111, 211, 108, 120, 157, 222, 17, 264, 151, 98, 38, 261, 123, 78, 118, 127, 240, 124, ] tail_labels = [ 76, 149, 173, 250, 275, 255, 34, 77, 266, 283, 112, 115, 186, 136, 256, 40, 254, 172, 9, 212, 213, 181, 154, 94, 191, 193, 3, 130, 146, 70, 128, 167, 126, 81, 7, 11, 148, 228, 239, 247, 21, 42, 89, 153, 161, 244, 110, 0, 29, 114, 132, 159, 218, 232, 260, 56, 92, 116, 282, 33, 113, 138, 12, 188, 44, 150, 197, 271, 169, 206, 90, 235, 103, 281, 184, 208, 216, 202, 214, 241, 129, 210, 276, 64, 27, 87, 139, 227, 187, 62, 43, 50, 69, 93, 144, 166, 265, 54, 83, 39, ] metainfo = dict( classes=( 'adhesive tape', 'air conditioner', 'alarm', 'album', 'arch', 'backpack', 'bag', 'balcony', 'ball', 'banister', 'bar', 'barricade', 'baseboard', 'basin', 'basket', 'bathtub', 'beam', 'beanbag', 'bed', 'bench', 'bicycle', 'bidet', 'bin', 'blackboard', 'blanket', 'blinds', 'board', 'body loofah', 'book', 'boots', 'bottle', 'bowl', 'box', 'bread', 'broom', 'brush', 'bucket', 'cabinet', 'calendar', 'camera', 'can', 'candle', 'candlestick', 'cap', 'car', 'carpet', 'cart', 'case', 'chair', 'chandelier', 'cleanser', 'clock', 'clothes', 'clothes dryer', 'coat hanger', 'coffee maker', 'coil', 'column', 'commode', 'computer', 'conducting wire', 'container', 'control', 'copier', 'cosmetics', 'couch', 'counter', 'countertop', 'crate', 'crib', 'cube', 'cup', 'curtain', 'cushion', 'decoration', 'desk', 'detergent', 'device', 'dish rack', 'dishwasher', 'dispenser', 'divider', 'door', 'door knob', 'doorframe', 'doorway', 'drawer', 'dress', 'dresser', 'drum', 'duct', 'dumbbell', 'dustpan', 'dvd', 'eraser', 'excercise equipment', 'fan', 'faucet', 'fence', 'file', 'fire extinguisher', 'fireplace', 'flowerpot', 'flush', 'folder', 'food', 'footstool', 'frame', 'fruit', 'furniture', 'garage door', 'garbage', 'glass', 'globe', 'glove', 'grab bar', 'grass', 'guitar', 'hair dryer', 'hamper', 'handle', 'hanger', 'hat', 'headboard', 'headphones', 'heater', 'helmets', 'holder', 'hook', 'humidifier', 'ironware', 'jacket', 'jalousie', 'jar', 'kettle', 'keyboard', 'kitchen island', 'kitchenware', 'knife', 'label', 'ladder', 'lamp', 'laptop', 'ledge', 'letter', 'light', 'luggage', 'machine', 'magazine', 'mailbox', 'map', 'mask', 'mat', 'mattress', 'menu', 'microwave', 'mirror', 'molding', 'monitor', 'mop', 'mouse', 'napkins', 'notebook', 'ottoman', 'oven', 'pack', 'package', 'pad', 'pan', 'panel', 'paper', 'paper cutter', 'partition', 'pedestal', 'pen', 'person', 'piano', 'picture', 'pillar', 'pillow', 'pipe', 'pitcher', 'plant', 'plate', 'player', 'plug', 'plunger', 'pool', 'pool table', 'poster', 'pot', 'price tag', 'printer', 'projector', 'purse', 'rack', 'radiator', 'radio', 'rail', 'range hood', 'refrigerator', 'remote control', 'ridge', 'rod', 'roll', 'roof', 'rope', 'sack', 'salt', 'scale', 'scissors', 'screen', 'seasoning', 'shampoo', 'sheet', 'shelf', 'shirt', 'shoe', 'shovel', 'shower', 'sign', 'sink', 'soap', 'soap dish', 'soap dispenser', 'socket', 'speaker', 'sponge', 'spoon', 'stairs', 'stall', 'stand', 'stapler', 'statue', 'steps', 'stick', 'stool', 'stopcock', 'stove', 'structure', 'sunglasses', 'support', 'switch', 'table', 'tablet', 'teapot', 'telephone', 'thermostat', 'tissue', 'tissue box', 'toaster', 'toilet', 'toilet paper', 'toiletry', 'tool', 'toothbrush', 'toothpaste', 'towel', 'toy', 'tray', 'treadmill', 'trophy', 'tube', 'tv', 'umbrella', 'urn', 'utensil', 'vacuum cleaner', 'vanity', 'vase', 'vent', 'ventilation', 'wardrobe', 'washbasin', 'washing machine', 'water cooler', 'water heater', 'window', 'window frame', 'windowsill', 'wine', 'wire', 'wood', 'wrap', ), classes_split=( [ 48, 177, 82, 179, 37, 243, 28, 277, 32, 84, 215, 145, 182, 170, 22, 72, 30, 141, 65, 257, 221, 225, 52, 75, 231, 158, 236, 156, 47, 74, 6, 18, 71, 242, 217, 251, 66, 263, 5, 45, 14, 73, 278, 198, 24, 23, 196, 252, 19, 135, 26, 229, 183, 200, 107, 272, 246, 269, 125, 59, 279, 15, 163, 258, 57, 195, 51, 88, 97, 58, 102, 36, 137, 31, 80, 160, 155, 61, 238, 96, 190, 25, 219, 152, 142, 201, 274, 249, 178, 192, ], [ 189, 164, 101, 205, 273, 233, 131, 180, 86, 220, 67, 268, 224, 270, 53, 203, 237, 226, 10, 133, 248, 41, 55, 16, 199, 134, 99, 185, 2, 20, 234, 194, 253, 35, 174, 8, 223, 13, 91, 262, 230, 121, 49, 63, 119, 162, 79, 168, 245, 267, 122, 104, 100, 1, 176, 280, 140, 209, 259, 143, 165, 147, 117, 85, 105, 95, 109, 207, 68, 175, 106, 60, 4, 46, 171, 204, 111, 211, 108, 120, 157, 222, 17, 264, 151, 98, 38, 261, 123, 78, 118, 127, 240, 124, ], [ 76, 149, 173, 250, 275, 255, 34, 77, 266, 283, 112, 115, 186, 136, 256, 40, 254, 172, 9, 212, 213, 181, 154, 94, 191, 193, 3, 130, 146, 70, 128, 167, 126, 81, 7, 11, 148, 228, 239, 247, 21, 42, 89, 153, 161, 244, 110, 0, 29, 114, 132, 159, 218, 232, 260, 56, 92, 116, 282, 33, 113, 138, 12, 188, 44, 150, 197, 271, 169, 206, 90, 235, 103, 281, 184, 208, 216, 202, 214, 241, 129, 210, 276, 64, 27, 87, 139, 227, 187, 62, 43, 50, 69, 93, 144, 166, 265, 54, 83, 39, ], ), box_type_3d='euler-depth') train_pipeline = [ dict(type='LoadAnnotations3D', with_visible_instance_masks=True), dict( type='MultiViewPipeline', n_images=10, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict( type='AggregateMultiViewPoints', coord_type='DEPTH', save_slices=True), dict( type='RandomFlip3D', sync_2d=False, flip_2d=False, flip_ratio_bev_horizontal=0.5, flip_ratio_bev_vertical=0.5), dict( type='GlobalRotScaleTrans', rot_range=[ -0.087266, 0.087266, ], scale_ratio_range=[ 0.9, 1.1, ], translation_std=[ 0.1, 0.1, 0.1, ], shift_height=False), dict(type='ConstructMultiSweeps'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ] test_pipeline = [ dict(type='LoadAnnotations3D', with_visible_instance_masks=True), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict( type='AggregateMultiViewPoints', coord_type='DEPTH', save_slices=True), dict(type='ConstructMultiSweeps'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ] train_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=8, dataset=dict( type='EmbodiedScanDataset', data_root='data', ann_file='embodiedscan_infos_train.pkl', pipeline=[ dict( type='LoadAnnotations3D', with_visible_instance_masks=True), dict( type='MultiViewPipeline', n_images=10, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict( type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict( type='AggregateMultiViewPoints', coord_type='DEPTH', save_slices=True), dict( type='RandomFlip3D', sync_2d=False, flip_2d=False, flip_ratio_bev_horizontal=0.5, flip_ratio_bev_vertical=0.5), dict( type='GlobalRotScaleTrans', rot_range=[ -0.087266, 0.087266, ], scale_ratio_range=[ 0.9, 1.1, ], translation_std=[ 0.1, 0.1, 0.1, ], shift_height=False), dict(type='ConstructMultiSweeps'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=False, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'adhesive tape', 'air conditioner', 'alarm', 'album', 'arch', 'backpack', 'bag', 'balcony', 'ball', 'banister', 'bar', 'barricade', 'baseboard', 'basin', 'basket', 'bathtub', 'beam', 'beanbag', 'bed', 'bench', 'bicycle', 'bidet', 'bin', 'blackboard', 'blanket', 'blinds', 'board', 'body loofah', 'book', 'boots', 'bottle', 'bowl', 'box', 'bread', 'broom', 'brush', 'bucket', 'cabinet', 'calendar', 'camera', 'can', 'candle', 'candlestick', 'cap', 'car', 'carpet', 'cart', 'case', 'chair', 'chandelier', 'cleanser', 'clock', 'clothes', 'clothes dryer', 'coat hanger', 'coffee maker', 'coil', 'column', 'commode', 'computer', 'conducting wire', 'container', 'control', 'copier', 'cosmetics', 'couch', 'counter', 'countertop', 'crate', 'crib', 'cube', 'cup', 'curtain', 'cushion', 'decoration', 'desk', 'detergent', 'device', 'dish rack', 'dishwasher', 'dispenser', 'divider', 'door', 'door knob', 'doorframe', 'doorway', 'drawer', 'dress', 'dresser', 'drum', 'duct', 'dumbbell', 'dustpan', 'dvd', 'eraser', 'excercise equipment', 'fan', 'faucet', 'fence', 'file', 'fire extinguisher', 'fireplace', 'flowerpot', 'flush', 'folder', 'food', 'footstool', 'frame', 'fruit', 'furniture', 'garage door', 'garbage', 'glass', 'globe', 'glove', 'grab bar', 'grass', 'guitar', 'hair dryer', 'hamper', 'handle', 'hanger', 'hat', 'headboard', 'headphones', 'heater', 'helmets', 'holder', 'hook', 'humidifier', 'ironware', 'jacket', 'jalousie', 'jar', 'kettle', 'keyboard', 'kitchen island', 'kitchenware', 'knife', 'label', 'ladder', 'lamp', 'laptop', 'ledge', 'letter', 'light', 'luggage', 'machine', 'magazine', 'mailbox', 'map', 'mask', 'mat', 'mattress', 'menu', 'microwave', 'mirror', 'molding', 'monitor', 'mop', 'mouse', 'napkins', 'notebook', 'ottoman', 'oven', 'pack', 'package', 'pad', 'pan', 'panel', 'paper', 'paper cutter', 'partition', 'pedestal', 'pen', 'person', 'piano', 'picture', 'pillar', 'pillow', 'pipe', 'pitcher', 'plant', 'plate', 'player', 'plug', 'plunger', 'pool', 'pool table', 'poster', 'pot', 'price tag', 'printer', 'projector', 'purse', 'rack', 'radiator', 'radio', 'rail', 'range hood', 'refrigerator', 'remote control', 'ridge', 'rod', 'roll', 'roof', 'rope', 'sack', 'salt', 'scale', 'scissors', 'screen', 'seasoning', 'shampoo', 'sheet', 'shelf', 'shirt', 'shoe', 'shovel', 'shower', 'sign', 'sink', 'soap', 'soap dish', 'soap dispenser', 'socket', 'speaker', 'sponge', 'spoon', 'stairs', 'stall', 'stand', 'stapler', 'statue', 'steps', 'stick', 'stool', 'stopcock', 'stove', 'structure', 'sunglasses', 'support', 'switch', 'table', 'tablet', 'teapot', 'telephone', 'thermostat', 'tissue', 'tissue box', 'toaster', 'toilet', 'toilet paper', 'toiletry', 'tool', 'toothbrush', 'toothpaste', 'towel', 'toy', 'tray', 'treadmill', 'trophy', 'tube', 'tv', 'umbrella', 'urn', 'utensil', 'vacuum cleaner', 'vanity', 'vase', 'vent', 'ventilation', 'wardrobe', 'washbasin', 'washing machine', 'water cooler', 'water heater', 'window', 'window frame', 'windowsill', 'wine', 'wire', 'wood', 'wrap', ), classes_split=( [ 48, 177, 82, 179, 37, 243, 28, 277, 32, 84, 215, 145, 182, 170, 22, 72, 30, 141, 65, 257, 221, 225, 52, 75, 231, 158, 236, 156, 47, 74, 6, 18, 71, 242, 217, 251, 66, 263, 5, 45, 14, 73, 278, 198, 24, 23, 196, 252, 19, 135, 26, 229, 183, 200, 107, 272, 246, 269, 125, 59, 279, 15, 163, 258, 57, 195, 51, 88, 97, 58, 102, 36, 137, 31, 80, 160, 155, 61, 238, 96, 190, 25, 219, 152, 142, 201, 274, 249, 178, 192, ], [ 189, 164, 101, 205, 273, 233, 131, 180, 86, 220, 67, 268, 224, 270, 53, 203, 237, 226, 10, 133, 248, 41, 55, 16, 199, 134, 99, 185, 2, 20, 234, 194, 253, 35, 174, 8, 223, 13, 91, 262, 230, 121, 49, 63, 119, 162, 79, 168, 245, 267, 122, 104, 100, 1, 176, 280, 140, 209, 259, 143, 165, 147, 117, 85, 105, 95, 109, 207, 68, 175, 106, 60, 4, 46, 171, 204, 111, 211, 108, 120, 157, 222, 17, 264, 151, 98, 38, 261, 123, 78, 118, 127, 240, 124, ], [ 76, 149, 173, 250, 275, 255, 34, 77, 266, 283, 112, 115, 186, 136, 256, 40, 254, 172, 9, 212, 213, 181, 154, 94, 191, 193, 3, 130, 146, 70, 128, 167, 126, 81, 7, 11, 148, 228, 239, 247, 21, 42, 89, 153, 161, 244, 110, 0, 29, 114, 132, 159, 218, 232, 260, 56, 92, 116, 282, 33, 113, 138, 12, 188, 44, 150, 197, 271, 169, 206, 90, 235, 103, 281, 184, 208, 216, 202, 214, 241, 129, 210, 276, 64, 27, 87, 139, 227, 187, 62, 43, 50, 69, 93, 144, 166, 265, 54, 83, 39, ], ), box_type_3d='euler-depth'), remove_dontcare=True))) val_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='EmbodiedScanDataset', data_root='data', ann_file='embodiedscan_infos_val.pkl', pipeline=[ dict(type='LoadAnnotations3D', with_visible_instance_masks=True), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict( type='AggregateMultiViewPoints', coord_type='DEPTH', save_slices=True), dict(type='ConstructMultiSweeps'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'adhesive tape', 'air conditioner', 'alarm', 'album', 'arch', 'backpack', 'bag', 'balcony', 'ball', 'banister', 'bar', 'barricade', 'baseboard', 'basin', 'basket', 'bathtub', 'beam', 'beanbag', 'bed', 'bench', 'bicycle', 'bidet', 'bin', 'blackboard', 'blanket', 'blinds', 'board', 'body loofah', 'book', 'boots', 'bottle', 'bowl', 'box', 'bread', 'broom', 'brush', 'bucket', 'cabinet', 'calendar', 'camera', 'can', 'candle', 'candlestick', 'cap', 'car', 'carpet', 'cart', 'case', 'chair', 'chandelier', 'cleanser', 'clock', 'clothes', 'clothes dryer', 'coat hanger', 'coffee maker', 'coil', 'column', 'commode', 'computer', 'conducting wire', 'container', 'control', 'copier', 'cosmetics', 'couch', 'counter', 'countertop', 'crate', 'crib', 'cube', 'cup', 'curtain', 'cushion', 'decoration', 'desk', 'detergent', 'device', 'dish rack', 'dishwasher', 'dispenser', 'divider', 'door', 'door knob', 'doorframe', 'doorway', 'drawer', 'dress', 'dresser', 'drum', 'duct', 'dumbbell', 'dustpan', 'dvd', 'eraser', 'excercise equipment', 'fan', 'faucet', 'fence', 'file', 'fire extinguisher', 'fireplace', 'flowerpot', 'flush', 'folder', 'food', 'footstool', 'frame', 'fruit', 'furniture', 'garage door', 'garbage', 'glass', 'globe', 'glove', 'grab bar', 'grass', 'guitar', 'hair dryer', 'hamper', 'handle', 'hanger', 'hat', 'headboard', 'headphones', 'heater', 'helmets', 'holder', 'hook', 'humidifier', 'ironware', 'jacket', 'jalousie', 'jar', 'kettle', 'keyboard', 'kitchen island', 'kitchenware', 'knife', 'label', 'ladder', 'lamp', 'laptop', 'ledge', 'letter', 'light', 'luggage', 'machine', 'magazine', 'mailbox', 'map', 'mask', 'mat', 'mattress', 'menu', 'microwave', 'mirror', 'molding', 'monitor', 'mop', 'mouse', 'napkins', 'notebook', 'ottoman', 'oven', 'pack', 'package', 'pad', 'pan', 'panel', 'paper', 'paper cutter', 'partition', 'pedestal', 'pen', 'person', 'piano', 'picture', 'pillar', 'pillow', 'pipe', 'pitcher', 'plant', 'plate', 'player', 'plug', 'plunger', 'pool', 'pool table', 'poster', 'pot', 'price tag', 'printer', 'projector', 'purse', 'rack', 'radiator', 'radio', 'rail', 'range hood', 'refrigerator', 'remote control', 'ridge', 'rod', 'roll', 'roof', 'rope', 'sack', 'salt', 'scale', 'scissors', 'screen', 'seasoning', 'shampoo', 'sheet', 'shelf', 'shirt', 'shoe', 'shovel', 'shower', 'sign', 'sink', 'soap', 'soap dish', 'soap dispenser', 'socket', 'speaker', 'sponge', 'spoon', 'stairs', 'stall', 'stand', 'stapler', 'statue', 'steps', 'stick', 'stool', 'stopcock', 'stove', 'structure', 'sunglasses', 'support', 'switch', 'table', 'tablet', 'teapot', 'telephone', 'thermostat', 'tissue', 'tissue box', 'toaster', 'toilet', 'toilet paper', 'toiletry', 'tool', 'toothbrush', 'toothpaste', 'towel', 'toy', 'tray', 'treadmill', 'trophy', 'tube', 'tv', 'umbrella', 'urn', 'utensil', 'vacuum cleaner', 'vanity', 'vase', 'vent', 'ventilation', 'wardrobe', 'washbasin', 'washing machine', 'water cooler', 'water heater', 'window', 'window frame', 'windowsill', 'wine', 'wire', 'wood', 'wrap', ), classes_split=( [ 48, 177, 82, 179, 37, 243, 28, 277, 32, 84, 215, 145, 182, 170, 22, 72, 30, 141, 65, 257, 221, 225, 52, 75, 231, 158, 236, 156, 47, 74, 6, 18, 71, 242, 217, 251, 66, 263, 5, 45, 14, 73, 278, 198, 24, 23, 196, 252, 19, 135, 26, 229, 183, 200, 107, 272, 246, 269, 125, 59, 279, 15, 163, 258, 57, 195, 51, 88, 97, 58, 102, 36, 137, 31, 80, 160, 155, 61, 238, 96, 190, 25, 219, 152, 142, 201, 274, 249, 178, 192, ], [ 189, 164, 101, 205, 273, 233, 131, 180, 86, 220, 67, 268, 224, 270, 53, 203, 237, 226, 10, 133, 248, 41, 55, 16, 199, 134, 99, 185, 2, 20, 234, 194, 253, 35, 174, 8, 223, 13, 91, 262, 230, 121, 49, 63, 119, 162, 79, 168, 245, 267, 122, 104, 100, 1, 176, 280, 140, 209, 259, 143, 165, 147, 117, 85, 105, 95, 109, 207, 68, 175, 106, 60, 4, 46, 171, 204, 111, 211, 108, 120, 157, 222, 17, 264, 151, 98, 38, 261, 123, 78, 118, 127, 240, 124, ], [ 76, 149, 173, 250, 275, 255, 34, 77, 266, 283, 112, 115, 186, 136, 256, 40, 254, 172, 9, 212, 213, 181, 154, 94, 191, 193, 3, 130, 146, 70, 128, 167, 126, 81, 7, 11, 148, 228, 239, 247, 21, 42, 89, 153, 161, 244, 110, 0, 29, 114, 132, 159, 218, 232, 260, 56, 92, 116, 282, 33, 113, 138, 12, 188, 44, 150, 197, 271, 169, 206, 90, 235, 103, 281, 184, 208, 216, 202, 214, 241, 129, 210, 276, 64, 27, 87, 139, 227, 187, 62, 43, 50, 69, 93, 144, 166, 265, 54, 83, 39, ], ), box_type_3d='euler-depth'), remove_dontcare=True)) test_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='EmbodiedScanDataset', data_root='data', ann_file='embodiedscan_infos_val.pkl', pipeline=[ dict(type='LoadAnnotations3D', with_visible_instance_masks=True), dict( type='MultiViewPipeline', n_images=50, ordered=True, transforms=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadDepthFromFile', backend_args=None), dict(type='ConvertRGBDToPoints', coord_type='CAMERA'), dict(type='PointSample', num_points=10000), dict(type='Resize', scale=( 480, 480, ), keep_ratio=False), ]), dict( type='AggregateMultiViewPoints', coord_type='DEPTH', save_slices=True), dict(type='ConstructMultiSweeps'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'adhesive tape', 'air conditioner', 'alarm', 'album', 'arch', 'backpack', 'bag', 'balcony', 'ball', 'banister', 'bar', 'barricade', 'baseboard', 'basin', 'basket', 'bathtub', 'beam', 'beanbag', 'bed', 'bench', 'bicycle', 'bidet', 'bin', 'blackboard', 'blanket', 'blinds', 'board', 'body loofah', 'book', 'boots', 'bottle', 'bowl', 'box', 'bread', 'broom', 'brush', 'bucket', 'cabinet', 'calendar', 'camera', 'can', 'candle', 'candlestick', 'cap', 'car', 'carpet', 'cart', 'case', 'chair', 'chandelier', 'cleanser', 'clock', 'clothes', 'clothes dryer', 'coat hanger', 'coffee maker', 'coil', 'column', 'commode', 'computer', 'conducting wire', 'container', 'control', 'copier', 'cosmetics', 'couch', 'counter', 'countertop', 'crate', 'crib', 'cube', 'cup', 'curtain', 'cushion', 'decoration', 'desk', 'detergent', 'device', 'dish rack', 'dishwasher', 'dispenser', 'divider', 'door', 'door knob', 'doorframe', 'doorway', 'drawer', 'dress', 'dresser', 'drum', 'duct', 'dumbbell', 'dustpan', 'dvd', 'eraser', 'excercise equipment', 'fan', 'faucet', 'fence', 'file', 'fire extinguisher', 'fireplace', 'flowerpot', 'flush', 'folder', 'food', 'footstool', 'frame', 'fruit', 'furniture', 'garage door', 'garbage', 'glass', 'globe', 'glove', 'grab bar', 'grass', 'guitar', 'hair dryer', 'hamper', 'handle', 'hanger', 'hat', 'headboard', 'headphones', 'heater', 'helmets', 'holder', 'hook', 'humidifier', 'ironware', 'jacket', 'jalousie', 'jar', 'kettle', 'keyboard', 'kitchen island', 'kitchenware', 'knife', 'label', 'ladder', 'lamp', 'laptop', 'ledge', 'letter', 'light', 'luggage', 'machine', 'magazine', 'mailbox', 'map', 'mask', 'mat', 'mattress', 'menu', 'microwave', 'mirror', 'molding', 'monitor', 'mop', 'mouse', 'napkins', 'notebook', 'ottoman', 'oven', 'pack', 'package', 'pad', 'pan', 'panel', 'paper', 'paper cutter', 'partition', 'pedestal', 'pen', 'person', 'piano', 'picture', 'pillar', 'pillow', 'pipe', 'pitcher', 'plant', 'plate', 'player', 'plug', 'plunger', 'pool', 'pool table', 'poster', 'pot', 'price tag', 'printer', 'projector', 'purse', 'rack', 'radiator', 'radio', 'rail', 'range hood', 'refrigerator', 'remote control', 'ridge', 'rod', 'roll', 'roof', 'rope', 'sack', 'salt', 'scale', 'scissors', 'screen', 'seasoning', 'shampoo', 'sheet', 'shelf', 'shirt', 'shoe', 'shovel', 'shower', 'sign', 'sink', 'soap', 'soap dish', 'soap dispenser', 'socket', 'speaker', 'sponge', 'spoon', 'stairs', 'stall', 'stand', 'stapler', 'statue', 'steps', 'stick', 'stool', 'stopcock', 'stove', 'structure', 'sunglasses', 'support', 'switch', 'table', 'tablet', 'teapot', 'telephone', 'thermostat', 'tissue', 'tissue box', 'toaster', 'toilet', 'toilet paper', 'toiletry', 'tool', 'toothbrush', 'toothpaste', 'towel', 'toy', 'tray', 'treadmill', 'trophy', 'tube', 'tv', 'umbrella', 'urn', 'utensil', 'vacuum cleaner', 'vanity', 'vase', 'vent', 'ventilation', 'wardrobe', 'washbasin', 'washing machine', 'water cooler', 'water heater', 'window', 'window frame', 'windowsill', 'wine', 'wire', 'wood', 'wrap', ), classes_split=( [ 48, 177, 82, 179, 37, 243, 28, 277, 32, 84, 215, 145, 182, 170, 22, 72, 30, 141, 65, 257, 221, 225, 52, 75, 231, 158, 236, 156, 47, 74, 6, 18, 71, 242, 217, 251, 66, 263, 5, 45, 14, 73, 278, 198, 24, 23, 196, 252, 19, 135, 26, 229, 183, 200, 107, 272, 246, 269, 125, 59, 279, 15, 163, 258, 57, 195, 51, 88, 97, 58, 102, 36, 137, 31, 80, 160, 155, 61, 238, 96, 190, 25, 219, 152, 142, 201, 274, 249, 178, 192, ], [ 189, 164, 101, 205, 273, 233, 131, 180, 86, 220, 67, 268, 224, 270, 53, 203, 237, 226, 10, 133, 248, 41, 55, 16, 199, 134, 99, 185, 2, 20, 234, 194, 253, 35, 174, 8, 223, 13, 91, 262, 230, 121, 49, 63, 119, 162, 79, 168, 245, 267, 122, 104, 100, 1, 176, 280, 140, 209, 259, 143, 165, 147, 117, 85, 105, 95, 109, 207, 68, 175, 106, 60, 4, 46, 171, 204, 111, 211, 108, 120, 157, 222, 17, 264, 151, 98, 38, 261, 123, 78, 118, 127, 240, 124, ], [ 76, 149, 173, 250, 275, 255, 34, 77, 266, 283, 112, 115, 186, 136, 256, 40, 254, 172, 9, 212, 213, 181, 154, 94, 191, 193, 3, 130, 146, 70, 128, 167, 126, 81, 7, 11, 148, 228, 239, 247, 21, 42, 89, 153, 161, 244, 110, 0, 29, 114, 132, 159, 218, 232, 260, 56, 92, 116, 282, 33, 113, 138, 12, 188, 44, 150, 197, 271, 169, 206, 90, 235, 103, 281, 184, 208, 216, 202, 214, 241, 129, 210, 276, 64, 27, 87, 139, 227, 187, 62, 43, 50, 69, 93, 144, 166, 265, 54, 83, 39, ], ), box_type_3d='euler-depth'), remove_dontcare=True)) val_evaluator = dict(type='IndoorDetMetric', batchwise_anns=True) test_evaluator = dict(type='IndoorDetMetric', batchwise_anns=True) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=12) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='AdamW', lr=0.0002, weight_decay=0.0001), clip_grad=dict(max_norm=10, norm_type=2)) param_scheduler = dict( type='MultiStepLR', begin=0, end=12, by_epoch=True, milestones=[ 8, 11, ], gamma=0.1) custom_hooks = [ dict(type='EmptyCacheHook', after_iter=True), ] launcher = 'slurm' work_dir = '/mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/cont-det3d-challenge-benchmark' 2024/04/12 18:14:27 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "vis_backend" registry tree. As a workaround, the current "vis_backend" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:14:34 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "hook" registry tree. As a workaround, the current "hook" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:14:34 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook (NORMAL ) EmptyCacheHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train: (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) EmptyCacheHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2024/04/12 18:14:36 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "loop" registry tree. As a workaround, the current "loop" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:14:36 - mmengine - WARNING - euler-depth is not a meta file, simply parsed as meta information 2024/04/12 18:16:17 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:17 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optimizer wrapper constructor" registry tree. As a workaround, the current "optimizer wrapper constructor" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:17 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optimizer" registry tree. As a workaround, the current "optimizer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:17 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "optim_wrapper" registry tree. As a workaround, the current "optim_wrapper" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:17 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:41 - mmengine - WARNING - The prefix is not set in metric class IndoorDetMetric. 2024/04/12 18:16:44 - mmengine - WARNING - Failed to search registry with scope "embodiedscan" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "embodiedscan" is a correct scope, or whether the registry is initialized. 2024/04/12 18:16:44 - mmengine - INFO - load model from: torchvision://resnet50 2024/04/12 18:16:44 - mmengine - INFO - Loads checkpoint by torchvision backend from path: torchvision://resnet50 2024/04/12 18:16:49 - mmengine - WARNING - The model and loaded state dict do not match exactly size mismatch for conv1.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from checkpoint, the shape in current model is torch.Size([16, 3, 7, 7]). size mismatch for bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 16, 1, 1]). size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.0.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.0.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.0.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.0.downsample.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.downsample.1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 64, 1, 1]). size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.1.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.1.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 64, 1, 1]). size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]). size mismatch for layer1.2.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([16]). size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 16, 1, 1]). size mismatch for layer1.2.bn3.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn3.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 64, 1, 1]). size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.0.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.0.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.0.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 64, 1, 1]). size mismatch for layer2.0.downsample.1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.downsample.1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.1.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.1.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.2.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.2.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 128, 1, 1]). size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]). size mismatch for layer2.3.bn2.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.bn2.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([32]). size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 32, 1, 1]). size mismatch for layer2.3.bn3.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn3.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]). size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.0.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.0.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.0.weight: copying a param with shape torch.Size([1024, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 1, 1]). size mismatch for layer3.0.downsample.1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.downsample.1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.1.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.1.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.2.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.2.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.3.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.3.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.4.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.4.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]). size mismatch for layer3.5.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer3.5.bn3.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn3.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]). size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.0.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.0.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.0.weight: copying a param with shape torch.Size([2048, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 256, 1, 1]). size mismatch for layer4.0.downsample.1.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.downsample.1.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.1.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.1.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([512, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]). size mismatch for layer4.2.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer4.2.conv3.weight: copying a param with shape torch.Size([2048, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer4.2.bn3.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn3.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). unexpected key in source state_dict: fc.weight, fc.bias Name of parameter - Initialization information backbone.conv1.weight - torch.Size([16, 3, 7, 7]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.conv1.weight - torch.Size([16, 16, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.downsample.0.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.downsample.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.0.downsample.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.conv1.weight - torch.Size([16, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.1.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.conv1.weight - torch.Size([16, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.conv2.weight - torch.Size([16, 16, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn2.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.conv3.weight - torch.Size([64, 16, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn3.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer1.2.bn3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.conv1.weight - torch.Size([32, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.downsample.0.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.downsample.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.0.downsample.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.1.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.2.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.conv1.weight - torch.Size([32, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.conv2.weight - torch.Size([32, 32, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.conv3.weight - torch.Size([128, 32, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn3.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer2.3.bn3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.conv1.weight - torch.Size([64, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.downsample.0.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.downsample.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.0.downsample.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.1.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.2.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.3.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.4.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.conv1.weight - torch.Size([64, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.conv2.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.conv3.weight - torch.Size([256, 64, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn3.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer3.5.bn3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.conv1.weight - torch.Size([128, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.downsample.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.0.downsample.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.conv1.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.1.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.conv1.weight - torch.Size([128, 512, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.conv2.weight - torch.Size([128, 128, 3, 3]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.conv3.weight - torch.Size([512, 128, 1, 1]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn3.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone.layer4.2.bn3.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.conv1.kernel - torch.Size([27, 3, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.norm1.weight - torch.Size([1, 64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.norm1.bias - torch.Size([1, 64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.0.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.0.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.downsample.0.kernel - torch.Size([1, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.0.downsample.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.0.downsample.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.1.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.1.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.1.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.1.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.1.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.1.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.2.conv1.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.2.norm1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.2.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.2.conv2.kernel - torch.Size([27, 64, 64]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer1.2.norm2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer1.2.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.conv1.kernel - torch.Size([27, 64, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.0.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.0.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.downsample.0.kernel - torch.Size([1, 64, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.0.downsample.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.0.downsample.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.1.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.1.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.1.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.1.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.1.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.1.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.2.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.2.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.2.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.2.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.2.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.2.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.3.conv1.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.3.norm1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.3.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.3.conv2.kernel - torch.Size([27, 128, 128]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer2.3.norm2.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer2.3.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.conv1.kernel - torch.Size([27, 128, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.0.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.0.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.downsample.0.kernel - torch.Size([1, 128, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.0.downsample.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.0.downsample.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.1.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.1.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.1.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.1.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.1.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.1.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.2.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.2.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.2.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.2.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.2.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.2.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.3.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.3.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.3.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.3.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.3.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.3.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.4.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.4.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.4.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.4.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.4.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.4.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.5.conv1.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.5.norm1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.5.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.5.conv2.kernel - torch.Size([27, 256, 256]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer3.5.norm2.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer3.5.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.conv1.kernel - torch.Size([27, 256, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.0.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.0.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.downsample.0.kernel - torch.Size([1, 256, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.0.downsample.1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.0.downsample.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.1.conv1.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.1.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.1.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.1.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.1.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.1.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.2.conv1.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.2.norm1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.2.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.2.conv2.kernel - torch.Size([27, 512, 512]): Initialized by user-defined `init_weights` in MinkResNet backbone_3d.layer4.2.norm2.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector backbone_3d.layer4.2.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_0.0.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_0.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_0.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.0.kernel - torch.Size([8, 256, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.4.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_1.4.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_1.0.kernel - torch.Size([27, 256, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_1.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_1.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.0.kernel - torch.Size([8, 512, 256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.1.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.3.kernel - torch.Size([27, 256, 256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.4.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_2.4.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_2.0.kernel - torch.Size([27, 512, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_2.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_2.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.0.kernel - torch.Size([8, 1024, 512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.3.kernel - torch.Size([27, 512, 512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.4.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.up_block_3.4.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_3.0.kernel - torch.Size([27, 1024, 128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_3.1.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.out_block_3.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.conv_center.kernel - torch.Size([128, 1]): Initialized by user-defined `init_weights` in FCAF3DHeadRotMat bbox_head.conv_reg.kernel - torch.Size([128, 12]): Initialized by user-defined `init_weights` in FCAF3DHeadRotMat bbox_head.conv_cls.kernel - torch.Size([128, 284]): Initialized by user-defined `init_weights` in FCAF3DHeadRotMat bbox_head.conv_cls.bias - torch.Size([1, 284]): Initialized by user-defined `init_weights` in FCAF3DHeadRotMat bbox_head.scales.0.scale - torch.Size([]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.scales.1.scale - torch.Size([]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.scales.2.scale - torch.Size([]): The value is the same before and after calling `init_weights` of Embodied3DDetector bbox_head.scales.3.scale - torch.Size([]): The value is the same before and after calling `init_weights` of Embodied3DDetector 2024/04/12 18:16:49 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2024/04/12 18:16:49 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2024/04/12 18:16:49 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/cont-det3d-challenge-benchmark. 2024/04/12 18:18:18 - mmengine - INFO - Epoch(train) [1][ 50/3111] lr: 2.0000e-04 eta: 18:28:59 time: 1.7848 data_time: 0.1453 memory: 16862 grad_norm: 1.7416 loss: 2.8012 loss_center: 0.6666 loss_bbox: 1.0441 loss_cls: 1.0905 2024/04/12 18:19:41 - mmengine - INFO - Epoch(train) [1][ 100/3111] lr: 2.0000e-04 eta: 17:48:47 time: 1.6600 data_time: 0.0553 memory: 16261 grad_norm: 1.5699 loss: 2.5462 loss_center: 0.7089 loss_bbox: 0.7873 loss_cls: 1.0500 2024/04/12 18:21:06 - mmengine - INFO - Epoch(train) [1][ 150/3111] lr: 2.0000e-04 eta: 17:40:01 time: 1.6869 data_time: 0.1022 memory: 13988 grad_norm: 1.2902 loss: 2.2461 loss_center: 0.6138 loss_bbox: 0.7614 loss_cls: 0.8708 2024/04/12 18:22:29 - mmengine - INFO - Epoch(train) [1][ 200/3111] lr: 2.0000e-04 eta: 17:32:52 time: 1.6735 data_time: 0.0863 memory: 12268 grad_norm: 1.7712 loss: 2.3883 loss_center: 0.7263 loss_bbox: 0.6736 loss_cls: 0.9883 2024/04/12 18:23:57 - mmengine - INFO - Epoch(train) [1][ 250/3111] lr: 2.0000e-04 eta: 17:37:10 time: 1.7476 data_time: 0.0661 memory: 16638 grad_norm: 1.7713 loss: 2.0766 loss_center: 0.6225 loss_bbox: 0.6011 loss_cls: 0.8530 2024/04/12 18:25:19 - mmengine - INFO - Epoch(train) [1][ 300/3111] lr: 2.0000e-04 eta: 17:29:59 time: 1.6545 data_time: 0.0533 memory: 18161 grad_norm: 1.6356 loss: 2.0761 loss_center: 0.6689 loss_bbox: 0.5679 loss_cls: 0.8393 2024/04/12 18:26:40 - mmengine - INFO - Epoch(train) [1][ 350/3111] lr: 2.0000e-04 eta: 17:20:07 time: 1.6053 data_time: 0.0742 memory: 15613 grad_norm: 1.5408 loss: 2.1591 loss_center: 0.7116 loss_bbox: 0.5391 loss_cls: 0.9084 2024/04/12 18:28:01 - mmengine - INFO - Epoch(train) [1][ 400/3111] lr: 2.0000e-04 eta: 17:13:54 time: 1.6250 data_time: 0.1487 memory: 15301 grad_norm: 1.4961 loss: 1.9668 loss_center: 0.6171 loss_bbox: 0.5734 loss_cls: 0.7762 2024/04/12 18:29:24 - mmengine - INFO - Epoch(train) [1][ 450/3111] lr: 2.0000e-04 eta: 17:11:42 time: 1.6680 data_time: 0.1770 memory: 15667 grad_norm: 1.3526 loss: 1.8347 loss_center: 0.5934 loss_bbox: 0.5087 loss_cls: 0.7326 2024/04/12 18:30:44 - mmengine - INFO - Epoch(train) [1][ 500/3111] lr: 2.0000e-04 eta: 17:05:15 time: 1.5960 data_time: 0.0799 memory: 16878 grad_norm: 1.2824 loss: 2.0198 loss_center: 0.6338 loss_bbox: 0.5904 loss_cls: 0.7956 2024/04/12 18:32:08 - mmengine - INFO - Epoch(train) [1][ 550/3111] lr: 2.0000e-04 eta: 17:04:19 time: 1.6783 data_time: 0.0599 memory: 13496 grad_norm: 1.1434 loss: 1.8865 loss_center: 0.6397 loss_bbox: 0.4874 loss_cls: 0.7594 2024/04/12 18:33:29 - mmengine - INFO - Epoch(train) [1][ 600/3111] lr: 2.0000e-04 eta: 17:00:15 time: 1.6185 data_time: 0.0651 memory: 18029 grad_norm: 1.4167 loss: 2.1294 loss_center: 0.7046 loss_bbox: 0.5783 loss_cls: 0.8465 2024/04/12 18:34:53 - mmengine - INFO - Epoch(train) [1][ 650/3111] lr: 2.0000e-04 eta: 16:59:15 time: 1.6748 data_time: 0.1287 memory: 15723 grad_norm: 1.3692 loss: 1.9562 loss_center: 0.5821 loss_bbox: 0.6360 loss_cls: 0.7381 2024/04/12 18:36:14 - mmengine - INFO - Epoch(train) [1][ 700/3111] lr: 2.0000e-04 eta: 16:56:28 time: 1.6352 data_time: 0.1471 memory: 18796 grad_norm: 1.5389 loss: 2.0265 loss_center: 0.6087 loss_bbox: 0.6247 loss_cls: 0.7931 2024/04/12 18:37:39 - mmengine - INFO - Epoch(train) [1][ 750/3111] lr: 2.0000e-04 eta: 16:56:26 time: 1.6982 data_time: 0.0645 memory: 14579 grad_norm: 1.4396 loss: 2.0417 loss_center: 0.6895 loss_bbox: 0.5234 loss_cls: 0.8288 2024/04/12 18:39:01 - mmengine - INFO - Epoch(train) [1][ 800/3111] lr: 2.0000e-04 eta: 16:53:42 time: 1.6319 data_time: 0.0865 memory: 16992 grad_norm: 1.5142 loss: 2.1016 loss_center: 0.6873 loss_bbox: 0.5848 loss_cls: 0.8296 2024/04/12 18:40:24 - mmengine - INFO - Epoch(train) [1][ 850/3111] lr: 2.0000e-04 eta: 16:52:08 time: 1.6598 data_time: 0.1065 memory: 15284 grad_norm: 1.7588 loss: 1.9979 loss_center: 0.6788 loss_bbox: 0.5084 loss_cls: 0.8107 2024/04/12 18:41:45 - mmengine - INFO - Epoch(train) [1][ 900/3111] lr: 2.0000e-04 eta: 16:48:59 time: 1.6125 data_time: 0.1029 memory: 16890 grad_norm: 1.6175 loss: 1.9348 loss_center: 0.5941 loss_bbox: 0.6138 loss_cls: 0.7270 2024/04/12 18:43:06 - mmengine - INFO - Epoch(train) [1][ 950/3111] lr: 2.0000e-04 eta: 16:46:28 time: 1.6262 data_time: 0.1353 memory: 16562 grad_norm: 1.2803 loss: 2.2541 loss_center: 0.8072 loss_bbox: 0.5141 loss_cls: 0.9329 2024/04/12 18:44:29 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 18:44:29 - mmengine - INFO - Epoch(train) [1][1000/3111] lr: 2.0000e-04 eta: 16:45:11 time: 1.6634 data_time: 0.1092 memory: 14909 grad_norm: 1.5004 loss: 1.9195 loss_center: 0.6457 loss_bbox: 0.5227 loss_cls: 0.7510 2024/04/12 18:45:47 - mmengine - INFO - Epoch(train) [1][1050/3111] lr: 2.0000e-04 eta: 16:40:59 time: 1.5621 data_time: 0.0661 memory: 17060 grad_norm: 1.0880 loss: 1.8492 loss_center: 0.5794 loss_bbox: 0.5512 loss_cls: 0.7186 2024/04/12 18:47:13 - mmengine - INFO - Epoch(train) [1][1100/3111] lr: 2.0000e-04 eta: 16:41:15 time: 1.7151 data_time: 0.1167 memory: 13963 grad_norm: 1.1461 loss: 1.9805 loss_center: 0.6874 loss_bbox: 0.5102 loss_cls: 0.7829 2024/04/12 18:48:32 - mmengine - INFO - Epoch(train) [1][1150/3111] lr: 2.0000e-04 eta: 16:37:48 time: 1.5792 data_time: 0.1499 memory: 17255 grad_norm: 1.2528 loss: 2.1434 loss_center: 0.7732 loss_bbox: 0.4966 loss_cls: 0.8736 2024/04/12 18:49:52 - mmengine - INFO - Epoch(train) [1][1200/3111] lr: 2.0000e-04 eta: 16:35:01 time: 1.5987 data_time: 0.0814 memory: 17510 grad_norm: 1.4057 loss: 1.8983 loss_center: 0.6405 loss_bbox: 0.5093 loss_cls: 0.7484 2024/04/12 18:51:13 - mmengine - INFO - Epoch(train) [1][1250/3111] lr: 2.0000e-04 eta: 16:33:03 time: 1.6275 data_time: 0.0992 memory: 15294 grad_norm: 1.1244 loss: 1.8585 loss_center: 0.6078 loss_bbox: 0.5308 loss_cls: 0.7199 2024/04/12 18:52:39 - mmengine - INFO - Epoch(train) [1][1300/3111] lr: 2.0000e-04 eta: 16:33:05 time: 1.7128 data_time: 0.1270 memory: 15215 grad_norm: 1.2924 loss: 1.8625 loss_center: 0.6256 loss_bbox: 0.5192 loss_cls: 0.7177 2024/04/12 18:53:59 - mmengine - INFO - Epoch(train) [1][1350/3111] lr: 2.0000e-04 eta: 16:30:27 time: 1.5970 data_time: 0.0653 memory: 18296 grad_norm: 1.4975 loss: 1.7459 loss_center: 0.6082 loss_bbox: 0.4634 loss_cls: 0.6743 2024/04/12 18:55:23 - mmengine - INFO - Epoch(train) [1][1400/3111] lr: 2.0000e-04 eta: 16:29:59 time: 1.6940 data_time: 0.2056 memory: 17738 grad_norm: 1.0607 loss: 1.8551 loss_center: 0.5974 loss_bbox: 0.5611 loss_cls: 0.6966 2024/04/12 18:56:48 - mmengine - INFO - Epoch(train) [1][1450/3111] lr: 2.0000e-04 eta: 16:29:17 time: 1.6859 data_time: 0.1026 memory: 16164 grad_norm: 1.1640 loss: 1.9607 loss_center: 0.6428 loss_bbox: 0.5517 loss_cls: 0.7662 2024/04/12 18:58:12 - mmengine - INFO - Epoch(train) [1][1500/3111] lr: 2.0000e-04 eta: 16:28:37 time: 1.6904 data_time: 0.0933 memory: 15168 grad_norm: 1.0601 loss: 1.7666 loss_center: 0.6218 loss_bbox: 0.4487 loss_cls: 0.6961 2024/04/12 18:59:35 - mmengine - INFO - Epoch(train) [1][1550/3111] lr: 2.0000e-04 eta: 16:27:06 time: 1.6482 data_time: 0.0811 memory: 15200 grad_norm: 1.3309 loss: 1.8564 loss_center: 0.6462 loss_bbox: 0.5141 loss_cls: 0.6962 2024/04/12 19:00:57 - mmengine - INFO - Epoch(train) [1][1600/3111] lr: 2.0000e-04 eta: 16:25:29 time: 1.6425 data_time: 0.1099 memory: 15151 grad_norm: 1.1524 loss: 1.9994 loss_center: 0.6350 loss_bbox: 0.5941 loss_cls: 0.7703 2024/04/12 19:02:17 - mmengine - INFO - Epoch(train) [1][1650/3111] lr: 2.0000e-04 eta: 16:23:07 time: 1.5998 data_time: 0.0638 memory: 15354 grad_norm: 1.2312 loss: 1.9868 loss_center: 0.7236 loss_bbox: 0.4604 loss_cls: 0.8028 2024/04/12 19:03:38 - mmengine - INFO - Epoch(train) [1][1700/3111] lr: 2.0000e-04 eta: 16:21:13 time: 1.6229 data_time: 0.0565 memory: 17405 grad_norm: 1.3189 loss: 1.8881 loss_center: 0.6690 loss_bbox: 0.4840 loss_cls: 0.7351 2024/04/12 19:04:56 - mmengine - INFO - Epoch(train) [1][1750/3111] lr: 2.0000e-04 eta: 16:18:26 time: 1.5694 data_time: 0.0683 memory: 14666 grad_norm: 1.1958 loss: 1.9481 loss_center: 0.7067 loss_bbox: 0.4625 loss_cls: 0.7789 2024/04/12 19:06:16 - mmengine - INFO - Epoch(train) [1][1800/3111] lr: 2.0000e-04 eta: 16:16:13 time: 1.5993 data_time: 0.0746 memory: 16106 grad_norm: 1.0989 loss: 1.7435 loss_center: 0.5407 loss_bbox: 0.5967 loss_cls: 0.6061 2024/04/12 19:07:36 - mmengine - INFO - Epoch(train) [1][1850/3111] lr: 2.0000e-04 eta: 16:13:56 time: 1.5917 data_time: 0.0552 memory: 17351 grad_norm: 1.1327 loss: 2.0249 loss_center: 0.7553 loss_bbox: 0.4574 loss_cls: 0.8122 2024/04/12 19:08:57 - mmengine - INFO - Epoch(train) [1][1900/3111] lr: 2.0000e-04 eta: 16:12:12 time: 1.6230 data_time: 0.0604 memory: 19338 grad_norm: 1.2881 loss: 1.8305 loss_center: 0.6352 loss_bbox: 0.4644 loss_cls: 0.7308 2024/04/12 19:10:22 - mmengine - INFO - Epoch(train) [1][1950/3111] lr: 2.0000e-04 eta: 16:11:47 time: 1.7097 data_time: 0.1339 memory: 18487 grad_norm: 1.1815 loss: 1.8406 loss_center: 0.6300 loss_bbox: 0.4931 loss_cls: 0.7175 2024/04/12 19:11:46 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 19:11:46 - mmengine - INFO - Epoch(train) [1][2000/3111] lr: 2.0000e-04 eta: 16:10:39 time: 1.6644 data_time: 0.1836 memory: 15906 grad_norm: 1.1879 loss: 1.8328 loss_center: 0.5902 loss_bbox: 0.5663 loss_cls: 0.6763 2024/04/12 19:13:09 - mmengine - INFO - Epoch(train) [1][2050/3111] lr: 2.0000e-04 eta: 16:09:37 time: 1.6716 data_time: 0.0991 memory: 15991 grad_norm: 1.4751 loss: 1.8394 loss_center: 0.6331 loss_bbox: 0.4715 loss_cls: 0.7349 2024/04/12 19:14:31 - mmengine - INFO - Epoch(train) [1][2100/3111] lr: 2.0000e-04 eta: 16:08:02 time: 1.6340 data_time: 0.2396 memory: 17525 grad_norm: 1.4342 loss: 1.7424 loss_center: 0.5783 loss_bbox: 0.5042 loss_cls: 0.6599 2024/04/12 19:15:49 - mmengine - INFO - Epoch(train) [1][2150/3111] lr: 2.0000e-04 eta: 16:05:22 time: 1.5539 data_time: 0.0755 memory: 17290 grad_norm: 1.1346 loss: 1.8458 loss_center: 0.6448 loss_bbox: 0.4773 loss_cls: 0.7238 2024/04/12 19:17:11 - mmengine - INFO - Epoch(train) [1][2200/3111] lr: 2.0000e-04 eta: 16:03:59 time: 1.6459 data_time: 0.1070 memory: 15804 grad_norm: 1.2009 loss: 1.9223 loss_center: 0.6652 loss_bbox: 0.5157 loss_cls: 0.7415 2024/04/12 19:18:34 - mmengine - INFO - Epoch(train) [1][2250/3111] lr: 2.0000e-04 eta: 16:02:55 time: 1.6702 data_time: 0.2087 memory: 16098 grad_norm: 1.2923 loss: 1.7691 loss_center: 0.6022 loss_bbox: 0.4824 loss_cls: 0.6845 2024/04/12 19:19:57 - mmengine - INFO - Epoch(train) [1][2300/3111] lr: 2.0000e-04 eta: 16:01:41 time: 1.6577 data_time: 0.1277 memory: 15408 grad_norm: 1.0782 loss: 1.8182 loss_center: 0.5868 loss_bbox: 0.5576 loss_cls: 0.6737 2024/04/12 19:21:20 - mmengine - INFO - Epoch(train) [1][2350/3111] lr: 2.0000e-04 eta: 16:00:24 time: 1.6538 data_time: 0.0836 memory: 15780 grad_norm: 1.3805 loss: 1.9530 loss_center: 0.7009 loss_bbox: 0.4704 loss_cls: 0.7817 2024/04/12 19:22:43 - mmengine - INFO - Epoch(train) [1][2400/3111] lr: 2.0000e-04 eta: 15:59:15 time: 1.6655 data_time: 0.0662 memory: 15502 grad_norm: 1.2930 loss: 1.8099 loss_center: 0.6656 loss_bbox: 0.4311 loss_cls: 0.7132 2024/04/12 19:24:07 - mmengine - INFO - Epoch(train) [1][2450/3111] lr: 2.0000e-04 eta: 15:58:14 time: 1.6786 data_time: 0.0718 memory: 18417 grad_norm: 1.0526 loss: 1.6812 loss_center: 0.5582 loss_bbox: 0.5242 loss_cls: 0.5988 2024/04/12 19:25:26 - mmengine - INFO - Epoch(train) [1][2500/3111] lr: 2.0000e-04 eta: 15:56:00 time: 1.5737 data_time: 0.2048 memory: 15831 grad_norm: 1.2429 loss: 1.9235 loss_center: 0.5776 loss_bbox: 0.7218 loss_cls: 0.6242 2024/04/12 19:26:46 - mmengine - INFO - Epoch(train) [1][2550/3111] lr: 2.0000e-04 eta: 15:54:11 time: 1.6077 data_time: 0.1223 memory: 15642 grad_norm: 1.3104 loss: 1.8717 loss_center: 0.6722 loss_bbox: 0.5048 loss_cls: 0.6948 2024/04/12 19:28:06 - mmengine - INFO - Epoch(train) [1][2600/3111] lr: 2.0000e-04 eta: 15:52:17 time: 1.5983 data_time: 0.0902 memory: 14931 grad_norm: 1.1368 loss: 1.8816 loss_center: 0.6273 loss_bbox: 0.5651 loss_cls: 0.6893 2024/04/12 19:29:34 - mmengine - INFO - Epoch(train) [1][2650/3111] lr: 2.0000e-04 eta: 15:52:03 time: 1.7490 data_time: 0.1256 memory: 19778 grad_norm: 1.1673 loss: 2.0132 loss_center: 0.6942 loss_bbox: 0.5792 loss_cls: 0.7398 2024/04/12 19:30:57 - mmengine - INFO - Epoch(train) [1][2700/3111] lr: 2.0000e-04 eta: 15:50:48 time: 1.6587 data_time: 0.2238 memory: 15502 grad_norm: 1.3837 loss: 1.6897 loss_center: 0.5392 loss_bbox: 0.5376 loss_cls: 0.6130 2024/04/12 19:32:22 - mmengine - INFO - Epoch(train) [1][2750/3111] lr: 2.0000e-04 eta: 15:50:00 time: 1.7026 data_time: 0.1532 memory: 15575 grad_norm: 1.1385 loss: 2.0048 loss_center: 0.6103 loss_bbox: 0.7207 loss_cls: 0.6738 2024/04/12 19:33:42 - mmengine - INFO - Epoch(train) [1][2800/3111] lr: 2.0000e-04 eta: 15:48:16 time: 1.6134 data_time: 0.0703 memory: 15999 grad_norm: 1.2003 loss: 1.7916 loss_center: 0.6350 loss_bbox: 0.4809 loss_cls: 0.6757 2024/04/12 19:35:06 - mmengine - INFO - Epoch(train) [1][2850/3111] lr: 2.0000e-04 eta: 15:47:04 time: 1.6649 data_time: 0.1435 memory: 20680 grad_norm: 1.1830 loss: 1.7451 loss_center: 0.6088 loss_bbox: 0.4911 loss_cls: 0.6452 2024/04/12 19:36:29 - mmengine - INFO - Epoch(train) [1][2900/3111] lr: 2.0000e-04 eta: 15:45:54 time: 1.6685 data_time: 0.0821 memory: 13069 grad_norm: 1.0485 loss: 1.7481 loss_center: 0.6526 loss_bbox: 0.4109 loss_cls: 0.6846 2024/04/12 19:37:50 - mmengine - INFO - Epoch(train) [1][2950/3111] lr: 2.0000e-04 eta: 15:44:11 time: 1.6131 data_time: 0.0699 memory: 15948 grad_norm: 1.4692 loss: 1.6221 loss_center: 0.5996 loss_bbox: 0.4006 loss_cls: 0.6218 2024/04/12 19:39:16 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 19:39:16 - mmengine - INFO - Epoch(train) [1][3000/3111] lr: 2.0000e-04 eta: 15:43:36 time: 1.7300 data_time: 0.1037 memory: 14773 grad_norm: 1.0825 loss: 1.9657 loss_center: 0.5692 loss_bbox: 0.7234 loss_cls: 0.6731 2024/04/12 19:40:37 - mmengine - INFO - Epoch(train) [1][3050/3111] lr: 2.0000e-04 eta: 15:41:59 time: 1.6232 data_time: 0.0755 memory: 13493 grad_norm: 1.0657 loss: 1.8965 loss_center: 0.7020 loss_bbox: 0.4511 loss_cls: 0.7434 2024/04/12 19:41:58 - mmengine - INFO - Epoch(train) [1][3100/3111] lr: 2.0000e-04 eta: 15:40:18 time: 1.6155 data_time: 0.1179 memory: 17375 grad_norm: 0.9414 loss: 1.6558 loss_center: 0.5528 loss_bbox: 0.5071 loss_cls: 0.5958 2024/04/12 19:42:15 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 19:42:15 - mmengine - INFO - Saving checkpoint at 1 epochs 2024/04/12 19:43:48 - mmengine - INFO - Epoch(train) [2][ 50/3111] lr: 2.0000e-04 eta: 15:38:30 time: 1.6571 data_time: 0.1284 memory: 14100 grad_norm: 1.0518 loss: 1.7773 loss_center: 0.6293 loss_bbox: 0.4759 loss_cls: 0.6721 2024/04/12 19:45:09 - mmengine - INFO - Epoch(train) [2][ 100/3111] lr: 2.0000e-04 eta: 15:36:45 time: 1.6057 data_time: 0.0956 memory: 16608 grad_norm: 1.0893 loss: 1.7429 loss_center: 0.6263 loss_bbox: 0.4672 loss_cls: 0.6494 2024/04/12 19:46:32 - mmengine - INFO - Epoch(train) [2][ 150/3111] lr: 2.0000e-04 eta: 15:35:38 time: 1.6766 data_time: 0.1007 memory: 19150 grad_norm: 1.0840 loss: 1.7165 loss_center: 0.6698 loss_bbox: 0.3784 loss_cls: 0.6683 2024/04/12 19:47:52 - mmengine - INFO - Epoch(train) [2][ 200/3111] lr: 2.0000e-04 eta: 15:33:50 time: 1.5983 data_time: 0.1093 memory: 15863 grad_norm: 1.1968 loss: 1.9084 loss_center: 0.6672 loss_bbox: 0.4878 loss_cls: 0.7534 2024/04/12 19:49:13 - mmengine - INFO - Epoch(train) [2][ 250/3111] lr: 2.0000e-04 eta: 15:32:06 time: 1.6034 data_time: 0.0729 memory: 14456 grad_norm: 1.0559 loss: 1.7501 loss_center: 0.6483 loss_bbox: 0.4298 loss_cls: 0.6721 2024/04/12 19:50:37 - mmengine - INFO - Epoch(train) [2][ 300/3111] lr: 2.0000e-04 eta: 15:31:00 time: 1.6792 data_time: 0.1209 memory: 15882 grad_norm: 1.0638 loss: 1.7325 loss_center: 0.6108 loss_bbox: 0.4522 loss_cls: 0.6695 2024/04/12 19:51:59 - mmengine - INFO - Epoch(train) [2][ 350/3111] lr: 2.0000e-04 eta: 15:29:37 time: 1.6463 data_time: 0.1435 memory: 18136 grad_norm: 1.2499 loss: 1.8274 loss_center: 0.6514 loss_bbox: 0.4805 loss_cls: 0.6954 2024/04/12 19:53:20 - mmengine - INFO - Epoch(train) [2][ 400/3111] lr: 2.0000e-04 eta: 15:28:01 time: 1.6175 data_time: 0.0941 memory: 15614 grad_norm: 1.1097 loss: 1.7299 loss_center: 0.6474 loss_bbox: 0.4320 loss_cls: 0.6506 2024/04/12 19:54:42 - mmengine - INFO - Epoch(train) [2][ 450/3111] lr: 2.0000e-04 eta: 15:26:40 time: 1.6494 data_time: 0.1164 memory: 16084 grad_norm: 1.0522 loss: 1.9088 loss_center: 0.6454 loss_bbox: 0.5916 loss_cls: 0.6718 2024/04/12 19:56:04 - mmengine - INFO - Epoch(train) [2][ 500/3111] lr: 2.0000e-04 eta: 15:25:17 time: 1.6442 data_time: 0.1007 memory: 15983 grad_norm: 0.9329 loss: 1.9189 loss_center: 0.7272 loss_bbox: 0.4642 loss_cls: 0.7274 2024/04/12 19:57:28 - mmengine - INFO - Epoch(train) [2][ 550/3111] lr: 2.0000e-04 eta: 15:24:02 time: 1.6631 data_time: 0.1914 memory: 14222 grad_norm: 0.9990 loss: 1.6576 loss_center: 0.5610 loss_bbox: 0.5086 loss_cls: 0.5881 2024/04/12 19:58:49 - mmengine - INFO - Epoch(train) [2][ 600/3111] lr: 2.0000e-04 eta: 15:22:34 time: 1.6339 data_time: 0.0605 memory: 14678 grad_norm: 1.0346 loss: 1.6565 loss_center: 0.6053 loss_bbox: 0.4171 loss_cls: 0.6341 2024/04/12 20:00:13 - mmengine - INFO - Epoch(train) [2][ 650/3111] lr: 2.0000e-04 eta: 15:21:22 time: 1.6697 data_time: 0.0966 memory: 12947 grad_norm: 1.0594 loss: 1.6287 loss_center: 0.5743 loss_bbox: 0.4610 loss_cls: 0.5933 2024/04/12 20:01:33 - mmengine - INFO - Epoch(train) [2][ 700/3111] lr: 2.0000e-04 eta: 15:19:45 time: 1.6133 data_time: 0.0837 memory: 16802 grad_norm: 1.1101 loss: 1.7489 loss_center: 0.6227 loss_bbox: 0.5077 loss_cls: 0.6185 2024/04/12 20:02:56 - mmengine - INFO - Epoch(train) [2][ 750/3111] lr: 2.0000e-04 eta: 15:18:27 time: 1.6559 data_time: 0.2496 memory: 19886 grad_norm: 1.0511 loss: 1.8480 loss_center: 0.6555 loss_bbox: 0.4652 loss_cls: 0.7274 2024/04/12 20:04:23 - mmengine - INFO - Epoch(train) [2][ 800/3111] lr: 2.0000e-04 eta: 15:17:39 time: 1.7270 data_time: 0.1539 memory: 16449 grad_norm: 1.0623 loss: 1.6851 loss_center: 0.5678 loss_bbox: 0.4901 loss_cls: 0.6272 2024/04/12 20:05:44 - mmengine - INFO - Epoch(train) [2][ 850/3111] lr: 2.0000e-04 eta: 15:16:10 time: 1.6318 data_time: 0.1062 memory: 13710 grad_norm: 1.0621 loss: 1.7861 loss_center: 0.6180 loss_bbox: 0.5205 loss_cls: 0.6476 2024/04/12 20:06:46 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 20:07:03 - mmengine - INFO - Epoch(train) [2][ 900/3111] lr: 2.0000e-04 eta: 15:14:16 time: 1.5710 data_time: 0.0789 memory: 14950 grad_norm: 1.1199 loss: 1.8452 loss_center: 0.6644 loss_bbox: 0.4633 loss_cls: 0.7175 2024/04/12 20:08:19 - mmengine - INFO - Epoch(train) [2][ 950/3111] lr: 2.0000e-04 eta: 15:12:02 time: 1.5211 data_time: 0.0875 memory: 18279 grad_norm: 1.1516 loss: 1.6292 loss_center: 0.5470 loss_bbox: 0.4841 loss_cls: 0.5981 2024/04/12 20:09:42 - mmengine - INFO - Epoch(train) [2][1000/3111] lr: 2.0000e-04 eta: 15:10:49 time: 1.6665 data_time: 0.1723 memory: 16838 grad_norm: 1.1736 loss: 1.8563 loss_center: 0.7146 loss_bbox: 0.4285 loss_cls: 0.7132 2024/04/12 20:11:06 - mmengine - INFO - Epoch(train) [2][1050/3111] lr: 2.0000e-04 eta: 15:09:41 time: 1.6811 data_time: 0.0995 memory: 14333 grad_norm: 1.1720 loss: 1.7561 loss_center: 0.6327 loss_bbox: 0.4629 loss_cls: 0.6604 2024/04/12 20:12:25 - mmengine - INFO - Epoch(train) [2][1100/3111] lr: 2.0000e-04 eta: 15:07:55 time: 1.5864 data_time: 0.0467 memory: 15886 grad_norm: 1.0850 loss: 1.7124 loss_center: 0.6617 loss_bbox: 0.4241 loss_cls: 0.6266 2024/04/12 20:13:49 - mmengine - INFO - Epoch(train) [2][1150/3111] lr: 2.0000e-04 eta: 15:06:45 time: 1.6742 data_time: 0.0624 memory: 14784 grad_norm: 0.9981 loss: 1.7757 loss_center: 0.6533 loss_bbox: 0.4582 loss_cls: 0.6643 2024/04/12 20:15:17 - mmengine - INFO - Epoch(train) [2][1200/3111] lr: 2.0000e-04 eta: 15:06:08 time: 1.7650 data_time: 0.0797 memory: 15527 grad_norm: 1.0774 loss: 1.9511 loss_center: 0.7607 loss_bbox: 0.4311 loss_cls: 0.7593 2024/04/12 20:16:38 - mmengine - INFO - Epoch(train) [2][1250/3111] lr: 2.0000e-04 eta: 15:04:33 time: 1.6118 data_time: 0.0862 memory: 16916 grad_norm: 1.0561 loss: 1.7759 loss_center: 0.6521 loss_bbox: 0.4713 loss_cls: 0.6525 2024/04/12 20:17:59 - mmengine - INFO - Epoch(train) [2][1300/3111] lr: 2.0000e-04 eta: 15:03:04 time: 1.6298 data_time: 0.0577 memory: 17393 grad_norm: 1.1343 loss: 1.8747 loss_center: 0.7391 loss_bbox: 0.4382 loss_cls: 0.6975 2024/04/12 20:19:22 - mmengine - INFO - Epoch(train) [2][1350/3111] lr: 2.0000e-04 eta: 15:01:45 time: 1.6542 data_time: 0.0597 memory: 19801 grad_norm: 1.1732 loss: 1.9031 loss_center: 0.6959 loss_bbox: 0.4859 loss_cls: 0.7213 2024/04/12 20:20:45 - mmengine - INFO - Epoch(train) [2][1400/3111] lr: 2.0000e-04 eta: 15:00:27 time: 1.6572 data_time: 0.0700 memory: 14766 grad_norm: 1.0970 loss: 1.7996 loss_center: 0.6961 loss_bbox: 0.4201 loss_cls: 0.6834 2024/04/12 20:22:09 - mmengine - INFO - Epoch(train) [2][1450/3111] lr: 2.0000e-04 eta: 14:59:13 time: 1.6694 data_time: 0.0906 memory: 19242 grad_norm: 1.1174 loss: 1.5683 loss_center: 0.5472 loss_bbox: 0.4415 loss_cls: 0.5796 2024/04/12 20:23:31 - mmengine - INFO - Epoch(train) [2][1500/3111] lr: 2.0000e-04 eta: 14:57:52 time: 1.6498 data_time: 0.1944 memory: 16181 grad_norm: 1.0871 loss: 1.7209 loss_center: 0.6411 loss_bbox: 0.4311 loss_cls: 0.6487 2024/04/12 20:24:51 - mmengine - INFO - Epoch(train) [2][1550/3111] lr: 2.0000e-04 eta: 14:56:11 time: 1.5934 data_time: 0.1346 memory: 16128 grad_norm: 1.1031 loss: 1.7343 loss_center: 0.6129 loss_bbox: 0.4902 loss_cls: 0.6312 2024/04/12 20:26:15 - mmengine - INFO - Epoch(train) [2][1600/3111] lr: 2.0000e-04 eta: 14:55:06 time: 1.6952 data_time: 0.0767 memory: 17469 grad_norm: 1.0061 loss: 1.7575 loss_center: 0.5943 loss_bbox: 0.5448 loss_cls: 0.6184 2024/04/12 20:27:42 - mmengine - INFO - Epoch(train) [2][1650/3111] lr: 2.0000e-04 eta: 14:54:13 time: 1.7316 data_time: 0.1295 memory: 17539 grad_norm: 1.1198 loss: 1.9472 loss_center: 0.6872 loss_bbox: 0.5221 loss_cls: 0.7379 2024/04/12 20:29:06 - mmengine - INFO - Epoch(train) [2][1700/3111] lr: 2.0000e-04 eta: 14:52:58 time: 1.6688 data_time: 0.0907 memory: 14291 grad_norm: 1.1832 loss: 1.8439 loss_center: 0.7400 loss_bbox: 0.4200 loss_cls: 0.6839 2024/04/12 20:30:26 - mmengine - INFO - Epoch(train) [2][1750/3111] lr: 2.0000e-04 eta: 14:51:26 time: 1.6199 data_time: 0.0780 memory: 17406 grad_norm: 1.0293 loss: 1.6361 loss_center: 0.5926 loss_bbox: 0.4304 loss_cls: 0.6131 2024/04/12 20:31:50 - mmengine - INFO - Epoch(train) [2][1800/3111] lr: 2.0000e-04 eta: 14:50:11 time: 1.6684 data_time: 0.1249 memory: 15465 grad_norm: 1.1854 loss: 1.7387 loss_center: 0.6476 loss_bbox: 0.4084 loss_cls: 0.6827 2024/04/12 20:33:12 - mmengine - INFO - Epoch(train) [2][1850/3111] lr: 2.0000e-04 eta: 14:48:49 time: 1.6513 data_time: 0.0922 memory: 17864 grad_norm: 0.9656 loss: 1.5760 loss_center: 0.5539 loss_bbox: 0.4407 loss_cls: 0.5813 2024/04/12 20:34:20 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 20:34:38 - mmengine - INFO - Epoch(train) [2][1900/3111] lr: 2.0000e-04 eta: 14:47:45 time: 1.7019 data_time: 0.1102 memory: 13657 grad_norm: 1.0922 loss: 1.9010 loss_center: 0.7087 loss_bbox: 0.4834 loss_cls: 0.7089 2024/04/12 20:36:03 - mmengine - INFO - Epoch(train) [2][1950/3111] lr: 2.0000e-04 eta: 14:46:45 time: 1.7183 data_time: 0.2031 memory: 18622 grad_norm: 1.1512 loss: 1.8858 loss_center: 0.6990 loss_bbox: 0.4890 loss_cls: 0.6978 2024/04/12 20:37:25 - mmengine - INFO - Epoch(train) [2][2000/3111] lr: 2.0000e-04 eta: 14:45:19 time: 1.6385 data_time: 0.1173 memory: 17221 grad_norm: 1.1534 loss: 1.7440 loss_center: 0.6294 loss_bbox: 0.4645 loss_cls: 0.6502 2024/04/12 20:38:49 - mmengine - INFO - Epoch(train) [2][2050/3111] lr: 2.0000e-04 eta: 14:44:04 time: 1.6733 data_time: 0.1880 memory: 14009 grad_norm: 1.1038 loss: 1.8875 loss_center: 0.6744 loss_bbox: 0.5387 loss_cls: 0.6743 2024/04/12 20:40:11 - mmengine - INFO - Epoch(train) [2][2100/3111] lr: 2.0000e-04 eta: 14:42:41 time: 1.6476 data_time: 0.1953 memory: 17103 grad_norm: 1.0293 loss: 1.5304 loss_center: 0.5464 loss_bbox: 0.4155 loss_cls: 0.5686 2024/04/12 20:41:34 - mmengine - INFO - Epoch(train) [2][2150/3111] lr: 2.0000e-04 eta: 14:41:20 time: 1.6523 data_time: 0.0969 memory: 14957 grad_norm: 0.9649 loss: 1.7977 loss_center: 0.7148 loss_bbox: 0.3856 loss_cls: 0.6972 2024/04/12 20:42:58 - mmengine - INFO - Epoch(train) [2][2200/3111] lr: 2.0000e-04 eta: 14:40:05 time: 1.6745 data_time: 0.2246 memory: 15872 grad_norm: 1.1055 loss: 1.5946 loss_center: 0.5873 loss_bbox: 0.4231 loss_cls: 0.5841 2024/04/12 20:44:21 - mmengine - INFO - Epoch(train) [2][2250/3111] lr: 2.0000e-04 eta: 14:38:47 time: 1.6637 data_time: 0.0764 memory: 18126 grad_norm: 1.0869 loss: 1.6518 loss_center: 0.6165 loss_bbox: 0.4056 loss_cls: 0.6297 2024/04/12 20:45:41 - mmengine - INFO - Epoch(train) [2][2300/3111] lr: 2.0000e-04 eta: 14:37:13 time: 1.6081 data_time: 0.0785 memory: 15593 grad_norm: 1.0484 loss: 1.5711 loss_center: 0.5913 loss_bbox: 0.3849 loss_cls: 0.5949 2024/04/12 20:47:02 - mmengine - INFO - Epoch(train) [2][2350/3111] lr: 2.0000e-04 eta: 14:35:40 time: 1.6134 data_time: 0.0851 memory: 13963 grad_norm: 1.0065 loss: 1.7239 loss_center: 0.6574 loss_bbox: 0.3865 loss_cls: 0.6801 2024/04/12 20:48:24 - mmengine - INFO - Epoch(train) [2][2400/3111] lr: 2.0000e-04 eta: 14:34:16 time: 1.6439 data_time: 0.1144 memory: 18942 grad_norm: 1.0258 loss: 1.5231 loss_center: 0.5509 loss_bbox: 0.4276 loss_cls: 0.5446 2024/04/12 20:49:46 - mmengine - INFO - Epoch(train) [2][2450/3111] lr: 2.0000e-04 eta: 14:32:49 time: 1.6307 data_time: 0.0798 memory: 15297 grad_norm: 1.0052 loss: 1.8693 loss_center: 0.7000 loss_bbox: 0.4843 loss_cls: 0.6850 2024/04/12 20:51:09 - mmengine - INFO - Epoch(train) [2][2500/3111] lr: 2.0000e-04 eta: 14:31:32 time: 1.6684 data_time: 0.2106 memory: 17084 grad_norm: 1.0653 loss: 1.9987 loss_center: 0.6164 loss_bbox: 0.7629 loss_cls: 0.6193 2024/04/12 20:52:29 - mmengine - INFO - Epoch(train) [2][2550/3111] lr: 2.0000e-04 eta: 14:29:57 time: 1.6042 data_time: 0.0970 memory: 15426 grad_norm: 1.0515 loss: 1.6532 loss_center: 0.5969 loss_bbox: 0.4443 loss_cls: 0.6120 2024/04/12 20:53:49 - mmengine - INFO - Epoch(train) [2][2600/3111] lr: 2.0000e-04 eta: 14:28:20 time: 1.5960 data_time: 0.0993 memory: 17373 grad_norm: 1.1368 loss: 1.5797 loss_center: 0.5467 loss_bbox: 0.4930 loss_cls: 0.5399 2024/04/12 20:55:12 - mmengine - INFO - Epoch(train) [2][2650/3111] lr: 2.0000e-04 eta: 14:26:59 time: 1.6534 data_time: 0.1002 memory: 17191 grad_norm: 1.0754 loss: 1.7100 loss_center: 0.6706 loss_bbox: 0.4016 loss_cls: 0.6378 2024/04/12 20:56:34 - mmengine - INFO - Epoch(train) [2][2700/3111] lr: 2.0000e-04 eta: 14:25:34 time: 1.6368 data_time: 0.0897 memory: 14922 grad_norm: 1.0437 loss: 1.6131 loss_center: 0.5997 loss_bbox: 0.4042 loss_cls: 0.6092 2024/04/12 20:58:01 - mmengine - INFO - Epoch(train) [2][2750/3111] lr: 2.0000e-04 eta: 14:24:38 time: 1.7451 data_time: 0.0762 memory: 16083 grad_norm: 1.2054 loss: 1.7382 loss_center: 0.6342 loss_bbox: 0.4202 loss_cls: 0.6839 2024/04/12 20:59:25 - mmengine - INFO - Epoch(train) [2][2800/3111] lr: 2.0000e-04 eta: 14:23:23 time: 1.6764 data_time: 0.0877 memory: 22420 grad_norm: 1.0300 loss: 1.7278 loss_center: 0.6328 loss_bbox: 0.4672 loss_cls: 0.6278 2024/04/12 21:00:48 - mmengine - INFO - Epoch(train) [2][2850/3111] lr: 2.0000e-04 eta: 14:22:07 time: 1.6740 data_time: 0.0710 memory: 17032 grad_norm: 0.9498 loss: 1.7864 loss_center: 0.6733 loss_bbox: 0.4669 loss_cls: 0.6462 2024/04/12 21:01:54 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 21:02:13 - mmengine - INFO - Epoch(train) [2][2900/3111] lr: 2.0000e-04 eta: 14:20:57 time: 1.6967 data_time: 0.0637 memory: 16081 grad_norm: 0.9784 loss: 1.8816 loss_center: 0.7315 loss_bbox: 0.4588 loss_cls: 0.6913 2024/04/12 21:03:35 - mmengine - INFO - Epoch(train) [2][2950/3111] lr: 2.0000e-04 eta: 14:19:28 time: 1.6254 data_time: 0.0918 memory: 19772 grad_norm: 1.0490 loss: 1.8687 loss_center: 0.7285 loss_bbox: 0.4214 loss_cls: 0.7188 2024/04/12 21:04:59 - mmengine - INFO - Epoch(train) [2][3000/3111] lr: 2.0000e-04 eta: 14:18:15 time: 1.6848 data_time: 0.0995 memory: 15790 grad_norm: 1.0473 loss: 1.8498 loss_center: 0.6345 loss_bbox: 0.6106 loss_cls: 0.6047 2024/04/12 21:06:22 - mmengine - INFO - Epoch(train) [2][3050/3111] lr: 2.0000e-04 eta: 14:16:56 time: 1.6640 data_time: 0.0691 memory: 15559 grad_norm: 0.9786 loss: 1.6598 loss_center: 0.6246 loss_bbox: 0.4140 loss_cls: 0.6212 2024/04/12 21:07:43 - mmengine - INFO - Epoch(train) [2][3100/3111] lr: 2.0000e-04 eta: 14:15:28 time: 1.6248 data_time: 0.1160 memory: 18155 grad_norm: 1.1345 loss: 1.6717 loss_center: 0.6019 loss_bbox: 0.5175 loss_cls: 0.5523 2024/04/12 21:08:04 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 21:08:04 - mmengine - INFO - Saving checkpoint at 2 epochs 2024/04/12 21:09:36 - mmengine - INFO - Epoch(train) [3][ 50/3111] lr: 2.0000e-04 eta: 14:14:03 time: 1.6697 data_time: 0.2088 memory: 16379 grad_norm: 1.0028 loss: 1.6669 loss_center: 0.6170 loss_bbox: 0.4135 loss_cls: 0.6364 2024/04/12 21:10:58 - mmengine - INFO - Epoch(train) [3][ 100/3111] lr: 2.0000e-04 eta: 14:12:39 time: 1.6436 data_time: 0.1006 memory: 16421 grad_norm: 0.9556 loss: 1.6055 loss_center: 0.5981 loss_bbox: 0.4201 loss_cls: 0.5873 2024/04/12 21:12:23 - mmengine - INFO - Epoch(train) [3][ 150/3111] lr: 2.0000e-04 eta: 14:11:28 time: 1.6964 data_time: 0.0962 memory: 14848 grad_norm: 0.9043 loss: 1.6488 loss_center: 0.6552 loss_bbox: 0.3763 loss_cls: 0.6172 2024/04/12 21:13:46 - mmengine - INFO - Epoch(train) [3][ 200/3111] lr: 2.0000e-04 eta: 14:10:10 time: 1.6717 data_time: 0.1030 memory: 19484 grad_norm: 0.9863 loss: 1.5785 loss_center: 0.6045 loss_bbox: 0.4028 loss_cls: 0.5713 2024/04/12 21:15:10 - mmengine - INFO - Epoch(train) [3][ 250/3111] lr: 2.0000e-04 eta: 14:08:54 time: 1.6771 data_time: 0.2007 memory: 16676 grad_norm: 1.0139 loss: 1.8334 loss_center: 0.6910 loss_bbox: 0.4734 loss_cls: 0.6690 2024/04/12 21:16:33 - mmengine - INFO - Epoch(train) [3][ 300/3111] lr: 2.0000e-04 eta: 14:07:32 time: 1.6527 data_time: 0.1559 memory: 17633 grad_norm: 0.9352 loss: 1.6881 loss_center: 0.6374 loss_bbox: 0.4378 loss_cls: 0.6129 2024/04/12 21:17:55 - mmengine - INFO - Epoch(train) [3][ 350/3111] lr: 2.0000e-04 eta: 14:06:10 time: 1.6542 data_time: 0.0720 memory: 15696 grad_norm: 1.6634 loss: 1.7622 loss_center: 0.6954 loss_bbox: 0.4217 loss_cls: 0.6450 2024/04/12 21:19:17 - mmengine - INFO - Epoch(train) [3][ 400/3111] lr: 2.0000e-04 eta: 14:04:45 time: 1.6383 data_time: 0.1671 memory: 14634 grad_norm: 1.0057 loss: 1.6136 loss_center: 0.6015 loss_bbox: 0.4284 loss_cls: 0.5837 2024/04/12 21:20:40 - mmengine - INFO - Epoch(train) [3][ 450/3111] lr: 2.0000e-04 eta: 14:03:24 time: 1.6556 data_time: 0.1678 memory: 18000 grad_norm: 0.9990 loss: 1.7213 loss_center: 0.6013 loss_bbox: 0.5107 loss_cls: 0.6094 2024/04/12 21:22:02 - mmengine - INFO - Epoch(train) [3][ 500/3111] lr: 2.0000e-04 eta: 14:01:56 time: 1.6288 data_time: 0.1387 memory: 14253 grad_norm: 0.9722 loss: 1.6085 loss_center: 0.5797 loss_bbox: 0.4172 loss_cls: 0.6116 2024/04/12 21:23:27 - mmengine - INFO - Epoch(train) [3][ 550/3111] lr: 2.0000e-04 eta: 14:00:45 time: 1.7001 data_time: 0.0602 memory: 14371 grad_norm: 0.9105 loss: 1.6970 loss_center: 0.6609 loss_bbox: 0.4211 loss_cls: 0.6149 2024/04/12 21:24:52 - mmengine - INFO - Epoch(train) [3][ 600/3111] lr: 2.0000e-04 eta: 13:59:33 time: 1.6978 data_time: 0.1425 memory: 18763 grad_norm: 1.0263 loss: 1.6839 loss_center: 0.5991 loss_bbox: 0.4881 loss_cls: 0.5967 2024/04/12 21:26:17 - mmengine - INFO - Epoch(train) [3][ 650/3111] lr: 2.0000e-04 eta: 13:58:23 time: 1.7070 data_time: 0.1362 memory: 14907 grad_norm: 0.9794 loss: 1.7940 loss_center: 0.6811 loss_bbox: 0.4490 loss_cls: 0.6638 2024/04/12 21:27:38 - mmengine - INFO - Epoch(train) [3][ 700/3111] lr: 2.0000e-04 eta: 13:56:52 time: 1.6126 data_time: 0.0612 memory: 17482 grad_norm: 0.9774 loss: 1.6024 loss_center: 0.6171 loss_bbox: 0.3879 loss_cls: 0.5975 2024/04/12 21:28:59 - mmengine - INFO - Epoch(train) [3][ 750/3111] lr: 2.0000e-04 eta: 13:55:26 time: 1.6378 data_time: 0.1053 memory: 17668 grad_norm: 1.0181 loss: 1.6920 loss_center: 0.6563 loss_bbox: 0.4502 loss_cls: 0.5855 2024/04/12 21:29:48 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 21:30:23 - mmengine - INFO - Epoch(train) [3][ 800/3111] lr: 2.0000e-04 eta: 13:54:08 time: 1.6710 data_time: 0.0987 memory: 16761 grad_norm: 1.0393 loss: 1.7394 loss_center: 0.6561 loss_bbox: 0.4534 loss_cls: 0.6300 2024/04/12 21:31:49 - mmengine - INFO - Epoch(train) [3][ 850/3111] lr: 2.0000e-04 eta: 13:52:59 time: 1.7128 data_time: 0.1029 memory: 15613 grad_norm: 1.1242 loss: 1.4958 loss_center: 0.5411 loss_bbox: 0.4293 loss_cls: 0.5254 2024/04/12 21:33:09 - mmengine - INFO - Epoch(train) [3][ 900/3111] lr: 2.0000e-04 eta: 13:51:29 time: 1.6165 data_time: 0.1252 memory: 14353 grad_norm: 0.9390 loss: 1.7318 loss_center: 0.6822 loss_bbox: 0.4166 loss_cls: 0.6330 2024/04/12 21:34:33 - mmengine - INFO - Epoch(train) [3][ 950/3111] lr: 2.0000e-04 eta: 13:50:11 time: 1.6748 data_time: 0.0781 memory: 13962 grad_norm: 0.9959 loss: 1.7350 loss_center: 0.6631 loss_bbox: 0.4424 loss_cls: 0.6295 2024/04/12 21:35:55 - mmengine - INFO - Epoch(train) [3][1000/3111] lr: 2.0000e-04 eta: 13:48:46 time: 1.6397 data_time: 0.2046 memory: 15661 grad_norm: 0.8859 loss: 1.5579 loss_center: 0.5771 loss_bbox: 0.4185 loss_cls: 0.5623 2024/04/12 21:37:19 - mmengine - INFO - Epoch(train) [3][1050/3111] lr: 2.0000e-04 eta: 13:47:27 time: 1.6715 data_time: 0.1362 memory: 14256 grad_norm: 1.0432 loss: 1.8394 loss_center: 0.7092 loss_bbox: 0.4541 loss_cls: 0.6761 2024/04/12 21:38:42 - mmengine - INFO - Epoch(train) [3][1100/3111] lr: 2.0000e-04 eta: 13:46:10 time: 1.6749 data_time: 0.1034 memory: 17627 grad_norm: 0.9993 loss: 1.7082 loss_center: 0.6592 loss_bbox: 0.4010 loss_cls: 0.6480 2024/04/12 21:40:06 - mmengine - INFO - Epoch(train) [3][1150/3111] lr: 2.0000e-04 eta: 13:44:49 time: 1.6634 data_time: 0.1464 memory: 15231 grad_norm: 0.8992 loss: 1.6653 loss_center: 0.6021 loss_bbox: 0.4709 loss_cls: 0.5923 2024/04/12 21:41:34 - mmengine - INFO - Epoch(train) [3][1200/3111] lr: 2.0000e-04 eta: 13:43:51 time: 1.7717 data_time: 0.1426 memory: 18291 grad_norm: 0.9700 loss: 2.1351 loss_center: 0.7339 loss_bbox: 0.6752 loss_cls: 0.7261 2024/04/12 21:42:58 - mmengine - INFO - Epoch(train) [3][1250/3111] lr: 2.0000e-04 eta: 13:42:32 time: 1.6706 data_time: 0.0673 memory: 14396 grad_norm: 0.9779 loss: 1.7309 loss_center: 0.6797 loss_bbox: 0.4111 loss_cls: 0.6401 2024/04/12 21:44:22 - mmengine - INFO - Epoch(train) [3][1300/3111] lr: 2.0000e-04 eta: 13:41:17 time: 1.6940 data_time: 0.0603 memory: 14008 grad_norm: 0.9612 loss: 1.6452 loss_center: 0.6218 loss_bbox: 0.4210 loss_cls: 0.6025 2024/04/12 21:45:44 - mmengine - INFO - Epoch(train) [3][1350/3111] lr: 2.0000e-04 eta: 13:39:48 time: 1.6209 data_time: 0.0722 memory: 16270 grad_norm: 0.9680 loss: 1.6235 loss_center: 0.5810 loss_bbox: 0.4741 loss_cls: 0.5684 2024/04/12 21:47:06 - mmengine - INFO - Epoch(train) [3][1400/3111] lr: 2.0000e-04 eta: 13:38:25 time: 1.6499 data_time: 0.0865 memory: 13870 grad_norm: 0.9014 loss: 1.7417 loss_center: 0.6905 loss_bbox: 0.4029 loss_cls: 0.6483 2024/04/12 21:48:28 - mmengine - INFO - Epoch(train) [3][1450/3111] lr: 2.0000e-04 eta: 13:36:58 time: 1.6314 data_time: 0.0758 memory: 19368 grad_norm: 0.8963 loss: 1.7214 loss_center: 0.6728 loss_bbox: 0.4279 loss_cls: 0.6207 2024/04/12 21:49:48 - mmengine - INFO - Epoch(train) [3][1500/3111] lr: 2.0000e-04 eta: 13:35:26 time: 1.5998 data_time: 0.0898 memory: 12972 grad_norm: 0.9708 loss: 1.7493 loss_center: 0.7063 loss_bbox: 0.3956 loss_cls: 0.6474 2024/04/12 21:51:12 - mmengine - INFO - Epoch(train) [3][1550/3111] lr: 2.0000e-04 eta: 13:34:09 time: 1.6823 data_time: 0.1367 memory: 21862 grad_norm: 0.9402 loss: 1.5969 loss_center: 0.5852 loss_bbox: 0.4417 loss_cls: 0.5700 2024/04/12 21:52:36 - mmengine - INFO - Epoch(train) [3][1600/3111] lr: 2.0000e-04 eta: 13:32:53 time: 1.6878 data_time: 0.0649 memory: 14026 grad_norm: 0.9944 loss: 1.6431 loss_center: 0.6484 loss_bbox: 0.3965 loss_cls: 0.5982 2024/04/12 21:53:58 - mmengine - INFO - Epoch(train) [3][1650/3111] lr: 2.0000e-04 eta: 13:31:27 time: 1.6349 data_time: 0.1224 memory: 14896 grad_norm: 0.8980 loss: 1.6656 loss_center: 0.6535 loss_bbox: 0.4270 loss_cls: 0.5851 2024/04/12 21:55:20 - mmengine - INFO - Epoch(train) [3][1700/3111] lr: 2.0000e-04 eta: 13:30:03 time: 1.6455 data_time: 0.0686 memory: 17447 grad_norm: 1.0284 loss: 1.6721 loss_center: 0.6784 loss_bbox: 0.3543 loss_cls: 0.6393 2024/04/12 21:56:43 - mmengine - INFO - Epoch(train) [3][1750/3111] lr: 2.0000e-04 eta: 13:28:41 time: 1.6564 data_time: 0.0793 memory: 16369 grad_norm: 0.9824 loss: 1.5002 loss_center: 0.5852 loss_bbox: 0.3802 loss_cls: 0.5347 2024/04/12 21:57:31 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 21:58:07 - mmengine - INFO - Epoch(train) [3][1800/3111] lr: 2.0000e-04 eta: 13:27:25 time: 1.6904 data_time: 0.1626 memory: 17714 grad_norm: 1.0308 loss: 1.7251 loss_center: 0.6005 loss_bbox: 0.5078 loss_cls: 0.6169 2024/04/12 21:59:33 - mmengine - INFO - Epoch(train) [3][1850/3111] lr: 2.0000e-04 eta: 13:26:14 time: 1.7153 data_time: 0.2257 memory: 16235 grad_norm: 0.9630 loss: 1.5783 loss_center: 0.6160 loss_bbox: 0.4108 loss_cls: 0.5515 2024/04/12 22:00:57 - mmengine - INFO - Epoch(train) [3][1900/3111] lr: 2.0000e-04 eta: 13:24:55 time: 1.6731 data_time: 0.1043 memory: 17536 grad_norm: 0.9426 loss: 1.6477 loss_center: 0.6295 loss_bbox: 0.4113 loss_cls: 0.6069 2024/04/12 22:02:23 - mmengine - INFO - Epoch(train) [3][1950/3111] lr: 2.0000e-04 eta: 13:23:45 time: 1.7265 data_time: 0.0687 memory: 14555 grad_norm: 0.9570 loss: 1.6700 loss_center: 0.6690 loss_bbox: 0.3827 loss_cls: 0.6183 2024/04/12 22:03:45 - mmengine - INFO - Epoch(train) [3][2000/3111] lr: 2.0000e-04 eta: 13:22:19 time: 1.6325 data_time: 0.0680 memory: 18647 grad_norm: 0.9058 loss: 1.7332 loss_center: 0.7136 loss_bbox: 0.4082 loss_cls: 0.6114 2024/04/12 22:05:07 - mmengine - INFO - Epoch(train) [3][2050/3111] lr: 2.0000e-04 eta: 13:20:54 time: 1.6428 data_time: 0.1008 memory: 13069 grad_norm: 1.0177 loss: 1.8488 loss_center: 0.7002 loss_bbox: 0.5023 loss_cls: 0.6463 2024/04/12 22:06:37 - mmengine - INFO - Epoch(train) [3][2100/3111] lr: 2.0000e-04 eta: 13:19:57 time: 1.8024 data_time: 0.0904 memory: 18434 grad_norm: 1.1192 loss: 1.7144 loss_center: 0.6597 loss_bbox: 0.4601 loss_cls: 0.5946 2024/04/12 22:08:01 - mmengine - INFO - Epoch(train) [3][2150/3111] lr: 2.0000e-04 eta: 13:18:39 time: 1.6823 data_time: 0.1385 memory: 17264 grad_norm: 1.0507 loss: 1.6334 loss_center: 0.5870 loss_bbox: 0.4619 loss_cls: 0.5844 2024/04/12 22:09:19 - mmengine - INFO - Epoch(train) [3][2200/3111] lr: 2.0000e-04 eta: 13:17:01 time: 1.5646 data_time: 0.1421 memory: 15752 grad_norm: 0.9194 loss: 1.7129 loss_center: 0.6877 loss_bbox: 0.3776 loss_cls: 0.6477 2024/04/12 22:10:37 - mmengine - INFO - Epoch(train) [3][2250/3111] lr: 2.0000e-04 eta: 13:15:22 time: 1.5583 data_time: 0.1145 memory: 20065 grad_norm: 0.8297 loss: 1.6116 loss_center: 0.5963 loss_bbox: 0.4432 loss_cls: 0.5721 2024/04/12 22:11:59 - mmengine - INFO - Epoch(train) [3][2300/3111] lr: 2.0000e-04 eta: 13:13:56 time: 1.6354 data_time: 0.0680 memory: 15463 grad_norm: 0.9340 loss: 1.7285 loss_center: 0.6897 loss_bbox: 0.3962 loss_cls: 0.6426 2024/04/12 22:13:21 - mmengine - INFO - Epoch(train) [3][2350/3111] lr: 2.0000e-04 eta: 13:12:30 time: 1.6341 data_time: 0.0729 memory: 15496 grad_norm: 1.0522 loss: 1.6268 loss_center: 0.5994 loss_bbox: 0.4383 loss_cls: 0.5890 2024/04/12 22:14:44 - mmengine - INFO - Epoch(train) [3][2400/3111] lr: 2.0000e-04 eta: 13:11:08 time: 1.6554 data_time: 0.0970 memory: 14157 grad_norm: 0.9933 loss: 1.6414 loss_center: 0.6749 loss_bbox: 0.3439 loss_cls: 0.6226 2024/04/12 22:16:09 - mmengine - INFO - Epoch(train) [3][2450/3111] lr: 2.0000e-04 eta: 13:09:56 time: 1.7153 data_time: 0.1167 memory: 16523 grad_norm: 0.9163 loss: 1.6331 loss_center: 0.6442 loss_bbox: 0.4074 loss_cls: 0.5815 2024/04/12 22:17:31 - mmengine - INFO - Epoch(train) [3][2500/3111] lr: 2.0000e-04 eta: 13:08:28 time: 1.6253 data_time: 0.0736 memory: 17147 grad_norm: 1.0628 loss: 1.5652 loss_center: 0.6269 loss_bbox: 0.3753 loss_cls: 0.5630 2024/04/12 22:18:53 - mmengine - INFO - Epoch(train) [3][2550/3111] lr: 2.0000e-04 eta: 13:07:05 time: 1.6501 data_time: 0.1449 memory: 16014 grad_norm: 1.0214 loss: 1.6952 loss_center: 0.6595 loss_bbox: 0.4303 loss_cls: 0.6054 2024/04/12 22:20:17 - mmengine - INFO - Epoch(train) [3][2600/3111] lr: 2.0000e-04 eta: 13:05:46 time: 1.6768 data_time: 0.1841 memory: 20560 grad_norm: 0.9537 loss: 1.6163 loss_center: 0.6019 loss_bbox: 0.4630 loss_cls: 0.5514 2024/04/12 22:21:39 - mmengine - INFO - Epoch(train) [3][2650/3111] lr: 2.0000e-04 eta: 13:04:22 time: 1.6425 data_time: 0.1311 memory: 13766 grad_norm: 0.9531 loss: 1.7706 loss_center: 0.6938 loss_bbox: 0.4155 loss_cls: 0.6613 2024/04/12 22:23:01 - mmengine - INFO - Epoch(train) [3][2700/3111] lr: 2.0000e-04 eta: 13:02:56 time: 1.6325 data_time: 0.0743 memory: 15250 grad_norm: 0.9351 loss: 1.5599 loss_center: 0.6286 loss_bbox: 0.3595 loss_cls: 0.5717 2024/04/12 22:24:20 - mmengine - INFO - Epoch(train) [3][2750/3111] lr: 2.0000e-04 eta: 13:01:21 time: 1.5771 data_time: 0.0590 memory: 14483 grad_norm: 0.8741 loss: 1.6484 loss_center: 0.6456 loss_bbox: 0.4059 loss_cls: 0.5970 2024/04/12 22:25:05 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 22:25:42 - mmengine - INFO - Epoch(train) [3][2800/3111] lr: 2.0000e-04 eta: 12:59:59 time: 1.6554 data_time: 0.0633 memory: 14841 grad_norm: 0.9392 loss: 1.5965 loss_center: 0.6252 loss_bbox: 0.4245 loss_cls: 0.5468 2024/04/12 22:27:06 - mmengine - INFO - Epoch(train) [3][2850/3111] lr: 2.0000e-04 eta: 12:58:37 time: 1.6626 data_time: 0.0595 memory: 18539 grad_norm: 1.1451 loss: 1.6609 loss_center: 0.6458 loss_bbox: 0.4073 loss_cls: 0.6078 2024/04/12 22:28:28 - mmengine - INFO - Epoch(train) [3][2900/3111] lr: 2.0000e-04 eta: 12:57:13 time: 1.6426 data_time: 0.1453 memory: 16718 grad_norm: 0.8825 loss: 1.7434 loss_center: 0.6948 loss_bbox: 0.4129 loss_cls: 0.6357 2024/04/12 22:29:54 - mmengine - INFO - Epoch(train) [3][2950/3111] lr: 2.0000e-04 eta: 12:56:01 time: 1.7199 data_time: 0.2014 memory: 17415 grad_norm: 0.9063 loss: 1.6845 loss_center: 0.6554 loss_bbox: 0.4356 loss_cls: 0.5935 2024/04/12 22:31:20 - mmengine - INFO - Epoch(train) [3][3000/3111] lr: 2.0000e-04 eta: 12:54:49 time: 1.7259 data_time: 0.0929 memory: 14118 grad_norm: 0.8959 loss: 1.6535 loss_center: 0.6656 loss_bbox: 0.4079 loss_cls: 0.5799 2024/04/12 22:32:42 - mmengine - INFO - Epoch(train) [3][3050/3111] lr: 2.0000e-04 eta: 12:53:25 time: 1.6446 data_time: 0.1646 memory: 19827 grad_norm: 0.9737 loss: 1.6614 loss_center: 0.6250 loss_bbox: 0.4589 loss_cls: 0.5774 2024/04/12 22:34:03 - mmengine - INFO - Epoch(train) [3][3100/3111] lr: 2.0000e-04 eta: 12:51:55 time: 1.6079 data_time: 0.1118 memory: 16147 grad_norm: 0.9757 loss: 1.6172 loss_center: 0.5950 loss_bbox: 0.4774 loss_cls: 0.5448 2024/04/12 22:34:20 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 22:34:20 - mmengine - INFO - Saving checkpoint at 3 epochs 2024/04/12 22:35:54 - mmengine - INFO - Epoch(train) [4][ 50/3111] lr: 2.0000e-04 eta: 12:50:19 time: 1.7085 data_time: 0.1228 memory: 15665 grad_norm: 0.9193 loss: 1.7442 loss_center: 0.6908 loss_bbox: 0.4176 loss_cls: 0.6359 2024/04/12 22:37:15 - mmengine - INFO - Epoch(train) [4][ 100/3111] lr: 2.0000e-04 eta: 12:48:50 time: 1.6078 data_time: 0.1150 memory: 18454 grad_norm: 0.9647 loss: 1.7851 loss_center: 0.6731 loss_bbox: 0.4702 loss_cls: 0.6418 2024/04/12 22:38:40 - mmengine - INFO - Epoch(train) [4][ 150/3111] lr: 2.0000e-04 eta: 12:47:36 time: 1.7153 data_time: 0.2883 memory: 20664 grad_norm: 0.9911 loss: 1.8017 loss_center: 0.6347 loss_bbox: 0.5371 loss_cls: 0.6299 2024/04/12 22:40:04 - mmengine - INFO - Epoch(train) [4][ 200/3111] lr: 2.0000e-04 eta: 12:46:16 time: 1.6692 data_time: 0.1078 memory: 17004 grad_norm: 0.9361 loss: 2.0484 loss_center: 0.7161 loss_bbox: 0.6544 loss_cls: 0.6779 2024/04/12 22:41:24 - mmengine - INFO - Epoch(train) [4][ 250/3111] lr: 2.0000e-04 eta: 12:44:47 time: 1.6109 data_time: 0.0958 memory: 15392 grad_norm: 1.0805 loss: 1.6530 loss_center: 0.6459 loss_bbox: 0.4166 loss_cls: 0.5905 2024/04/12 22:42:49 - mmengine - INFO - Epoch(train) [4][ 300/3111] lr: 2.0000e-04 eta: 12:43:29 time: 1.6889 data_time: 0.1079 memory: 17147 grad_norm: 0.9356 loss: 1.6927 loss_center: 0.6206 loss_bbox: 0.5016 loss_cls: 0.5705 2024/04/12 22:44:08 - mmengine - INFO - Epoch(train) [4][ 350/3111] lr: 2.0000e-04 eta: 12:41:55 time: 1.5749 data_time: 0.0928 memory: 17067 grad_norm: 0.9127 loss: 1.7099 loss_center: 0.6931 loss_bbox: 0.4222 loss_cls: 0.5946 2024/04/12 22:45:28 - mmengine - INFO - Epoch(train) [4][ 400/3111] lr: 2.0000e-04 eta: 12:40:25 time: 1.6013 data_time: 0.1570 memory: 18237 grad_norm: 0.9343 loss: 1.5840 loss_center: 0.5764 loss_bbox: 0.4822 loss_cls: 0.5255 2024/04/12 22:46:49 - mmengine - INFO - Epoch(train) [4][ 450/3111] lr: 2.0000e-04 eta: 12:38:58 time: 1.6223 data_time: 0.1207 memory: 15500 grad_norm: 0.8961 loss: 1.6481 loss_center: 0.5934 loss_bbox: 0.5058 loss_cls: 0.5489 2024/04/12 22:48:09 - mmengine - INFO - Epoch(train) [4][ 500/3111] lr: 2.0000e-04 eta: 12:37:28 time: 1.5978 data_time: 0.1192 memory: 14108 grad_norm: 0.8803 loss: 1.8093 loss_center: 0.7201 loss_bbox: 0.4253 loss_cls: 0.6639 2024/04/12 22:49:27 - mmengine - INFO - Epoch(train) [4][ 550/3111] lr: 2.0000e-04 eta: 12:35:54 time: 1.5702 data_time: 0.0851 memory: 15198 grad_norm: 0.8384 loss: 1.6292 loss_center: 0.6571 loss_bbox: 0.3670 loss_cls: 0.6052 2024/04/12 22:50:51 - mmengine - INFO - Epoch(train) [4][ 600/3111] lr: 2.0000e-04 eta: 12:34:33 time: 1.6673 data_time: 0.0652 memory: 14969 grad_norm: 0.9133 loss: 1.7129 loss_center: 0.6812 loss_bbox: 0.4412 loss_cls: 0.5905 2024/04/12 22:52:16 - mmengine - INFO - Epoch(train) [4][ 650/3111] lr: 2.0000e-04 eta: 12:33:20 time: 1.7184 data_time: 0.1062 memory: 14527 grad_norm: 0.8859 loss: 1.5569 loss_center: 0.5861 loss_bbox: 0.4114 loss_cls: 0.5594 2024/04/12 22:52:43 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 22:53:39 - mmengine - INFO - Epoch(train) [4][ 700/3111] lr: 2.0000e-04 eta: 12:31:56 time: 1.6435 data_time: 0.1131 memory: 14683 grad_norm: 0.8760 loss: 1.7582 loss_center: 0.6049 loss_bbox: 0.5811 loss_cls: 0.5722 2024/04/12 22:55:06 - mmengine - INFO - Epoch(train) [4][ 750/3111] lr: 2.0000e-04 eta: 12:30:45 time: 1.7402 data_time: 0.0634 memory: 18042 grad_norm: 0.9617 loss: 1.8341 loss_center: 0.7153 loss_bbox: 0.4542 loss_cls: 0.6646 2024/04/12 22:56:28 - mmengine - INFO - Epoch(train) [4][ 800/3111] lr: 2.0000e-04 eta: 12:29:23 time: 1.6570 data_time: 0.0957 memory: 15011 grad_norm: 0.8788 loss: 1.6248 loss_center: 0.6872 loss_bbox: 0.3671 loss_cls: 0.5704 2024/04/12 22:57:51 - mmengine - INFO - Epoch(train) [4][ 850/3111] lr: 2.0000e-04 eta: 12:28:00 time: 1.6491 data_time: 0.1078 memory: 16122 grad_norm: 0.9166 loss: 1.6666 loss_center: 0.6364 loss_bbox: 0.4432 loss_cls: 0.5870 2024/04/12 22:59:15 - mmengine - INFO - Epoch(train) [4][ 900/3111] lr: 2.0000e-04 eta: 12:26:42 time: 1.6890 data_time: 0.1090 memory: 12508 grad_norm: 0.9260 loss: 1.6676 loss_center: 0.6720 loss_bbox: 0.3789 loss_cls: 0.6166 2024/04/12 23:00:35 - mmengine - INFO - Epoch(train) [4][ 950/3111] lr: 2.0000e-04 eta: 12:25:11 time: 1.5915 data_time: 0.1254 memory: 14037 grad_norm: 0.9133 loss: 1.7295 loss_center: 0.6373 loss_bbox: 0.5008 loss_cls: 0.5913 2024/04/12 23:02:01 - mmengine - INFO - Epoch(train) [4][1000/3111] lr: 2.0000e-04 eta: 12:23:57 time: 1.7189 data_time: 0.0927 memory: 15538 grad_norm: 0.9541 loss: 1.6657 loss_center: 0.6732 loss_bbox: 0.4027 loss_cls: 0.5898 2024/04/12 23:03:25 - mmengine - INFO - Epoch(train) [4][1050/3111] lr: 2.0000e-04 eta: 12:22:37 time: 1.6748 data_time: 0.1174 memory: 15537 grad_norm: 0.8703 loss: 1.5876 loss_center: 0.6055 loss_bbox: 0.4142 loss_cls: 0.5679 2024/04/12 23:04:44 - mmengine - INFO - Epoch(train) [4][1100/3111] lr: 2.0000e-04 eta: 12:21:06 time: 1.5890 data_time: 0.1130 memory: 15218 grad_norm: 0.9266 loss: 1.6948 loss_center: 0.6753 loss_bbox: 0.4018 loss_cls: 0.6177 2024/04/12 23:06:12 - mmengine - INFO - Epoch(train) [4][1150/3111] lr: 2.0000e-04 eta: 12:19:58 time: 1.7673 data_time: 0.1015 memory: 17259 grad_norm: 1.0733 loss: 1.7574 loss_center: 0.6359 loss_bbox: 0.5139 loss_cls: 0.6075 2024/04/12 23:07:40 - mmengine - INFO - Epoch(train) [4][1200/3111] lr: 2.0000e-04 eta: 12:18:48 time: 1.7543 data_time: 0.1736 memory: 17290 grad_norm: 0.9597 loss: 1.5952 loss_center: 0.6058 loss_bbox: 0.4341 loss_cls: 0.5554 2024/04/12 23:09:06 - mmengine - INFO - Epoch(train) [4][1250/3111] lr: 2.0000e-04 eta: 12:17:32 time: 1.7072 data_time: 0.1001 memory: 16577 grad_norm: 0.8844 loss: 1.6605 loss_center: 0.6008 loss_bbox: 0.4907 loss_cls: 0.5690 2024/04/12 23:10:29 - mmengine - INFO - Epoch(train) [4][1300/3111] lr: 2.0000e-04 eta: 12:16:11 time: 1.6643 data_time: 0.1745 memory: 19022 grad_norm: 1.0421 loss: 1.6909 loss_center: 0.6728 loss_bbox: 0.4466 loss_cls: 0.5715 2024/04/12 23:11:53 - mmengine - INFO - Epoch(train) [4][1350/3111] lr: 2.0000e-04 eta: 12:14:51 time: 1.6782 data_time: 0.1031 memory: 14328 grad_norm: 0.9557 loss: 1.7027 loss_center: 0.6259 loss_bbox: 0.5064 loss_cls: 0.5704 2024/04/12 23:13:11 - mmengine - INFO - Epoch(train) [4][1400/3111] lr: 2.0000e-04 eta: 12:13:17 time: 1.5623 data_time: 0.0696 memory: 16281 grad_norm: 0.8927 loss: 1.6249 loss_center: 0.6562 loss_bbox: 0.3993 loss_cls: 0.5694 2024/04/12 23:14:36 - mmengine - INFO - Epoch(train) [4][1450/3111] lr: 2.0000e-04 eta: 12:12:00 time: 1.6990 data_time: 0.2229 memory: 16080 grad_norm: 0.9581 loss: 1.4966 loss_center: 0.5662 loss_bbox: 0.4120 loss_cls: 0.5184 2024/04/12 23:15:59 - mmengine - INFO - Epoch(train) [4][1500/3111] lr: 2.0000e-04 eta: 12:10:38 time: 1.6612 data_time: 0.0658 memory: 16342 grad_norm: 0.8457 loss: 1.6022 loss_center: 0.6685 loss_bbox: 0.3371 loss_cls: 0.5966 2024/04/12 23:17:20 - mmengine - INFO - Epoch(train) [4][1550/3111] lr: 2.0000e-04 eta: 12:09:10 time: 1.6150 data_time: 0.0896 memory: 16755 grad_norm: 0.8471 loss: 1.5223 loss_center: 0.6306 loss_bbox: 0.3689 loss_cls: 0.5228 2024/04/12 23:18:42 - mmengine - INFO - Epoch(train) [4][1600/3111] lr: 2.0000e-04 eta: 12:07:48 time: 1.6569 data_time: 0.1193 memory: 17766 grad_norm: 0.9859 loss: 1.4715 loss_center: 0.5467 loss_bbox: 0.4265 loss_cls: 0.4984 2024/04/12 23:20:09 - mmengine - INFO - Epoch(train) [4][1650/3111] lr: 2.0000e-04 eta: 12:06:35 time: 1.7328 data_time: 0.1393 memory: 15890 grad_norm: 0.9242 loss: 1.6192 loss_center: 0.6065 loss_bbox: 0.4599 loss_cls: 0.5528 2024/04/12 23:20:34 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 23:21:30 - mmengine - INFO - Epoch(train) [4][1700/3111] lr: 2.0000e-04 eta: 12:05:07 time: 1.6129 data_time: 0.0860 memory: 15802 grad_norm: 0.9282 loss: 1.7786 loss_center: 0.7039 loss_bbox: 0.4389 loss_cls: 0.6358 2024/04/12 23:22:52 - mmengine - INFO - Epoch(train) [4][1750/3111] lr: 2.0000e-04 eta: 12:03:43 time: 1.6487 data_time: 0.0802 memory: 14926 grad_norm: 0.8839 loss: 1.7913 loss_center: 0.6712 loss_bbox: 0.5578 loss_cls: 0.5623 2024/04/12 23:24:16 - mmengine - INFO - Epoch(train) [4][1800/3111] lr: 2.0000e-04 eta: 12:02:24 time: 1.6813 data_time: 0.1320 memory: 16260 grad_norm: 0.8878 loss: 1.5401 loss_center: 0.6140 loss_bbox: 0.3780 loss_cls: 0.5481 2024/04/12 23:25:42 - mmengine - INFO - Epoch(train) [4][1850/3111] lr: 2.0000e-04 eta: 12:01:08 time: 1.7098 data_time: 0.2200 memory: 14315 grad_norm: 0.8341 loss: 1.5556 loss_center: 0.5906 loss_bbox: 0.4044 loss_cls: 0.5606 2024/04/12 23:27:07 - mmengine - INFO - Epoch(train) [4][1900/3111] lr: 2.0000e-04 eta: 11:59:52 time: 1.7139 data_time: 0.0773 memory: 16817 grad_norm: 0.9164 loss: 1.7757 loss_center: 0.7260 loss_bbox: 0.4438 loss_cls: 0.6058 2024/04/12 23:28:30 - mmengine - INFO - Epoch(train) [4][1950/3111] lr: 2.0000e-04 eta: 11:58:29 time: 1.6542 data_time: 0.1837 memory: 16932 grad_norm: 0.8581 loss: 1.6219 loss_center: 0.5818 loss_bbox: 0.4740 loss_cls: 0.5661 2024/04/12 23:29:53 - mmengine - INFO - Epoch(train) [4][2000/3111] lr: 2.0000e-04 eta: 11:57:07 time: 1.6595 data_time: 0.1405 memory: 15578 grad_norm: 0.8968 loss: 1.6838 loss_center: 0.6670 loss_bbox: 0.4399 loss_cls: 0.5769 2024/04/12 23:31:14 - mmengine - INFO - Epoch(train) [4][2050/3111] lr: 2.0000e-04 eta: 11:55:39 time: 1.6130 data_time: 0.0915 memory: 16502 grad_norm: 0.8463 loss: 1.6333 loss_center: 0.6396 loss_bbox: 0.4112 loss_cls: 0.5826 2024/04/12 23:32:38 - mmengine - INFO - Epoch(train) [4][2100/3111] lr: 2.0000e-04 eta: 11:54:20 time: 1.6894 data_time: 0.1388 memory: 15999 grad_norm: 0.9077 loss: 1.6791 loss_center: 0.6300 loss_bbox: 0.4675 loss_cls: 0.5815 2024/04/12 23:34:01 - mmengine - INFO - Epoch(train) [4][2150/3111] lr: 2.0000e-04 eta: 11:52:58 time: 1.6549 data_time: 0.0828 memory: 17067 grad_norm: 0.8589 loss: 1.8014 loss_center: 0.6628 loss_bbox: 0.5016 loss_cls: 0.6370 2024/04/12 23:35:23 - mmengine - INFO - Epoch(train) [4][2200/3111] lr: 2.0000e-04 eta: 11:51:33 time: 1.6355 data_time: 0.1463 memory: 15966 grad_norm: 0.8607 loss: 1.5567 loss_center: 0.6111 loss_bbox: 0.4318 loss_cls: 0.5139 2024/04/12 23:36:49 - mmengine - INFO - Epoch(train) [4][2250/3111] lr: 2.0000e-04 eta: 11:50:18 time: 1.7262 data_time: 0.1025 memory: 17493 grad_norm: 0.9574 loss: 1.5223 loss_center: 0.6178 loss_bbox: 0.3616 loss_cls: 0.5429 2024/04/12 23:38:10 - mmengine - INFO - Epoch(train) [4][2300/3111] lr: 2.0000e-04 eta: 11:48:52 time: 1.6263 data_time: 0.1025 memory: 15932 grad_norm: 1.0158 loss: 1.4794 loss_center: 0.5665 loss_bbox: 0.4086 loss_cls: 0.5043 2024/04/12 23:39:33 - mmengine - INFO - Epoch(train) [4][2350/3111] lr: 2.0000e-04 eta: 11:47:30 time: 1.6581 data_time: 0.1195 memory: 17023 grad_norm: 0.9120 loss: 1.5608 loss_center: 0.5816 loss_bbox: 0.4347 loss_cls: 0.5445 2024/04/12 23:40:52 - mmengine - INFO - Epoch(train) [4][2400/3111] lr: 2.0000e-04 eta: 11:45:59 time: 1.5812 data_time: 0.1679 memory: 14928 grad_norm: 0.8230 loss: 1.6116 loss_center: 0.5862 loss_bbox: 0.4582 loss_cls: 0.5672 2024/04/12 23:42:15 - mmengine - INFO - Epoch(train) [4][2450/3111] lr: 2.0000e-04 eta: 11:44:36 time: 1.6560 data_time: 0.0577 memory: 16901 grad_norm: 0.9049 loss: 1.5892 loss_center: 0.6472 loss_bbox: 0.3977 loss_cls: 0.5443 2024/04/12 23:43:37 - mmengine - INFO - Epoch(train) [4][2500/3111] lr: 2.0000e-04 eta: 11:43:12 time: 1.6399 data_time: 0.1141 memory: 19160 grad_norm: 0.8679 loss: 1.6817 loss_center: 0.7197 loss_bbox: 0.3734 loss_cls: 0.5887 2024/04/12 23:44:56 - mmengine - INFO - Epoch(train) [4][2550/3111] lr: 2.0000e-04 eta: 11:41:40 time: 1.5681 data_time: 0.0633 memory: 14609 grad_norm: 0.9352 loss: 1.7410 loss_center: 0.7305 loss_bbox: 0.3687 loss_cls: 0.6419 2024/04/12 23:46:15 - mmengine - INFO - Epoch(train) [4][2600/3111] lr: 2.0000e-04 eta: 11:40:09 time: 1.5805 data_time: 0.1361 memory: 13451 grad_norm: 0.8256 loss: 1.4607 loss_center: 0.5532 loss_bbox: 0.4411 loss_cls: 0.4663 2024/04/12 23:47:41 - mmengine - INFO - Epoch(train) [4][2650/3111] lr: 2.0000e-04 eta: 11:38:54 time: 1.7221 data_time: 0.2012 memory: 15781 grad_norm: 0.9610 loss: 1.4964 loss_center: 0.5587 loss_bbox: 0.4197 loss_cls: 0.5180 2024/04/12 23:48:09 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/12 23:49:03 - mmengine - INFO - Epoch(train) [4][2700/3111] lr: 2.0000e-04 eta: 11:37:30 time: 1.6437 data_time: 0.1508 memory: 15894 grad_norm: 0.8579 loss: 1.5594 loss_center: 0.6705 loss_bbox: 0.3382 loss_cls: 0.5507 2024/04/12 23:50:22 - mmengine - INFO - Epoch(train) [4][2750/3111] lr: 2.0000e-04 eta: 11:36:00 time: 1.5869 data_time: 0.1135 memory: 16797 grad_norm: 0.9712 loss: 1.7482 loss_center: 0.7040 loss_bbox: 0.4110 loss_cls: 0.6332 2024/04/12 23:51:50 - mmengine - INFO - Epoch(train) [4][2800/3111] lr: 2.0000e-04 eta: 11:34:47 time: 1.7489 data_time: 0.0918 memory: 17524 grad_norm: 0.9435 loss: 1.5473 loss_center: 0.5372 loss_bbox: 0.4984 loss_cls: 0.5117 2024/04/12 23:53:12 - mmengine - INFO - Epoch(train) [4][2850/3111] lr: 2.0000e-04 eta: 11:33:24 time: 1.6516 data_time: 0.0758 memory: 15220 grad_norm: 0.9259 loss: 1.7506 loss_center: 0.7557 loss_bbox: 0.3702 loss_cls: 0.6247 2024/04/12 23:54:42 - mmengine - INFO - Epoch(train) [4][2900/3111] lr: 2.0000e-04 eta: 11:32:17 time: 1.8037 data_time: 0.2223 memory: 15353 grad_norm: 1.2543 loss: 1.7816 loss_center: 0.6553 loss_bbox: 0.5321 loss_cls: 0.5942 2024/04/12 23:56:04 - mmengine - INFO - Epoch(train) [4][2950/3111] lr: 2.0000e-04 eta: 11:30:51 time: 1.6282 data_time: 0.1011 memory: 14660 grad_norm: 0.9006 loss: 1.3838 loss_center: 0.5612 loss_bbox: 0.3433 loss_cls: 0.4794 2024/04/12 23:57:28 - mmengine - INFO - Epoch(train) [4][3000/3111] lr: 2.0000e-04 eta: 11:29:31 time: 1.6740 data_time: 0.0607 memory: 16368 grad_norm: 0.8340 loss: 1.6625 loss_center: 0.6622 loss_bbox: 0.4159 loss_cls: 0.5844 2024/04/12 23:58:47 - mmengine - INFO - Epoch(train) [4][3050/3111] lr: 2.0000e-04 eta: 11:28:02 time: 1.5924 data_time: 0.1089 memory: 17762 grad_norm: 0.8084 loss: 1.5717 loss_center: 0.6139 loss_bbox: 0.4162 loss_cls: 0.5416 2024/04/13 00:00:15 - mmengine - INFO - Epoch(train) [4][3100/3111] lr: 2.0000e-04 eta: 11:26:49 time: 1.7552 data_time: 0.1014 memory: 15553 grad_norm: 0.9258 loss: 1.8979 loss_center: 0.6740 loss_bbox: 0.6598 loss_cls: 0.5641 2024/04/13 00:00:32 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 00:00:32 - mmengine - INFO - Saving checkpoint at 4 epochs 2024/04/13 00:02:01 - mmengine - INFO - Epoch(train) [5][ 50/3111] lr: 2.0000e-04 eta: 11:25:02 time: 1.6209 data_time: 0.2347 memory: 16968 grad_norm: 0.8143 loss: 1.4815 loss_center: 0.5694 loss_bbox: 0.4231 loss_cls: 0.4890 2024/04/13 00:03:24 - mmengine - INFO - Epoch(train) [5][ 100/3111] lr: 2.0000e-04 eta: 11:23:38 time: 1.6448 data_time: 0.1381 memory: 13449 grad_norm: 0.8375 loss: 1.5560 loss_center: 0.6265 loss_bbox: 0.3795 loss_cls: 0.5500 2024/04/13 00:04:50 - mmengine - INFO - Epoch(train) [5][ 150/3111] lr: 2.0000e-04 eta: 11:22:22 time: 1.7261 data_time: 0.0661 memory: 16837 grad_norm: 0.9328 loss: 1.7375 loss_center: 0.6588 loss_bbox: 0.4652 loss_cls: 0.6135 2024/04/13 00:06:14 - mmengine - INFO - Epoch(train) [5][ 200/3111] lr: 2.0000e-04 eta: 11:21:02 time: 1.6850 data_time: 0.1423 memory: 16474 grad_norm: 0.9348 loss: 1.7803 loss_center: 0.6679 loss_bbox: 0.4917 loss_cls: 0.6207 2024/04/13 00:07:38 - mmengine - INFO - Epoch(train) [5][ 250/3111] lr: 2.0000e-04 eta: 11:19:41 time: 1.6737 data_time: 0.0669 memory: 13390 grad_norm: 0.8645 loss: 1.5332 loss_center: 0.6167 loss_bbox: 0.3747 loss_cls: 0.5419 2024/04/13 00:09:01 - mmengine - INFO - Epoch(train) [5][ 300/3111] lr: 2.0000e-04 eta: 11:18:19 time: 1.6634 data_time: 0.0643 memory: 16662 grad_norm: 0.8525 loss: 1.7348 loss_center: 0.7223 loss_bbox: 0.4018 loss_cls: 0.6107 2024/04/13 00:10:28 - mmengine - INFO - Epoch(train) [5][ 350/3111] lr: 2.0000e-04 eta: 11:17:05 time: 1.7391 data_time: 0.0920 memory: 16956 grad_norm: 0.8596 loss: 1.5440 loss_center: 0.5983 loss_bbox: 0.4208 loss_cls: 0.5249 2024/04/13 00:11:51 - mmengine - INFO - Epoch(train) [5][ 400/3111] lr: 2.0000e-04 eta: 11:15:43 time: 1.6661 data_time: 0.1917 memory: 19161 grad_norm: 0.9289 loss: 1.7808 loss_center: 0.6379 loss_bbox: 0.5447 loss_cls: 0.5981 2024/04/13 00:13:16 - mmengine - INFO - Epoch(train) [5][ 450/3111] lr: 2.0000e-04 eta: 11:14:23 time: 1.6904 data_time: 0.2368 memory: 20871 grad_norm: 0.8411 loss: 1.4624 loss_center: 0.5584 loss_bbox: 0.4279 loss_cls: 0.4761 2024/04/13 00:14:40 - mmengine - INFO - Epoch(train) [5][ 500/3111] lr: 2.0000e-04 eta: 11:13:03 time: 1.6759 data_time: 0.1289 memory: 17131 grad_norm: 0.8197 loss: 1.5631 loss_center: 0.5709 loss_bbox: 0.4825 loss_cls: 0.5098 2024/04/13 00:15:59 - mmengine - INFO - Epoch(train) [5][ 550/3111] lr: 2.0000e-04 eta: 11:11:34 time: 1.5937 data_time: 0.0733 memory: 15623 grad_norm: 0.8826 loss: 1.6224 loss_center: 0.6689 loss_bbox: 0.3762 loss_cls: 0.5774 2024/04/13 00:16:09 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 00:17:22 - mmengine - INFO - Epoch(train) [5][ 600/3111] lr: 2.0000e-04 eta: 11:10:10 time: 1.6480 data_time: 0.1217 memory: 20205 grad_norm: 0.8782 loss: 1.6563 loss_center: 0.6642 loss_bbox: 0.4397 loss_cls: 0.5524 2024/04/13 00:18:44 - mmengine - INFO - Epoch(train) [5][ 650/3111] lr: 2.0000e-04 eta: 11:08:48 time: 1.6546 data_time: 0.0934 memory: 15431 grad_norm: 0.9374 loss: 1.7878 loss_center: 0.7531 loss_bbox: 0.3775 loss_cls: 0.6572 2024/04/13 00:20:11 - mmengine - INFO - Epoch(train) [5][ 700/3111] lr: 2.0000e-04 eta: 11:07:31 time: 1.7270 data_time: 0.1000 memory: 19728 grad_norm: 0.8752 loss: 1.6443 loss_center: 0.6729 loss_bbox: 0.3863 loss_cls: 0.5850 2024/04/13 00:21:35 - mmengine - INFO - Epoch(train) [5][ 750/3111] lr: 2.0000e-04 eta: 11:06:10 time: 1.6735 data_time: 0.1175 memory: 16935 grad_norm: 0.9333 loss: 1.5265 loss_center: 0.5834 loss_bbox: 0.4178 loss_cls: 0.5252 2024/04/13 00:22:55 - mmengine - INFO - Epoch(train) [5][ 800/3111] lr: 2.0000e-04 eta: 11:04:44 time: 1.6150 data_time: 0.1199 memory: 20332 grad_norm: 0.8993 loss: 1.6130 loss_center: 0.5716 loss_bbox: 0.4911 loss_cls: 0.5503 2024/04/13 00:24:18 - mmengine - INFO - Epoch(train) [5][ 850/3111] lr: 2.0000e-04 eta: 11:03:22 time: 1.6628 data_time: 0.0701 memory: 14849 grad_norm: 0.9550 loss: 1.6287 loss_center: 0.6300 loss_bbox: 0.4361 loss_cls: 0.5626 2024/04/13 00:25:40 - mmengine - INFO - Epoch(train) [5][ 900/3111] lr: 2.0000e-04 eta: 11:01:57 time: 1.6400 data_time: 0.1295 memory: 15235 grad_norm: 0.8860 loss: 1.4921 loss_center: 0.5983 loss_bbox: 0.3898 loss_cls: 0.5040 2024/04/13 00:27:03 - mmengine - INFO - Epoch(train) [5][ 950/3111] lr: 2.0000e-04 eta: 11:00:34 time: 1.6530 data_time: 0.0610 memory: 17246 grad_norm: 0.8689 loss: 1.6517 loss_center: 0.6581 loss_bbox: 0.4295 loss_cls: 0.5642 2024/04/13 00:28:27 - mmengine - INFO - Epoch(train) [5][1000/3111] lr: 2.0000e-04 eta: 10:59:13 time: 1.6769 data_time: 0.0963 memory: 14209 grad_norm: 0.8644 loss: 1.5814 loss_center: 0.6349 loss_bbox: 0.3824 loss_cls: 0.5641 2024/04/13 00:29:51 - mmengine - INFO - Epoch(train) [5][1050/3111] lr: 2.0000e-04 eta: 10:57:54 time: 1.6888 data_time: 0.0631 memory: 13903 grad_norm: 0.8606 loss: 1.7970 loss_center: 0.6951 loss_bbox: 0.5037 loss_cls: 0.5982 2024/04/13 00:31:14 - mmengine - INFO - Epoch(train) [5][1100/3111] lr: 2.0000e-04 eta: 10:56:31 time: 1.6592 data_time: 0.0914 memory: 17658 grad_norm: 0.8477 loss: 1.5026 loss_center: 0.5854 loss_bbox: 0.4130 loss_cls: 0.5042 2024/04/13 00:32:34 - mmengine - INFO - Epoch(train) [5][1150/3111] lr: 2.0000e-04 eta: 10:55:02 time: 1.5879 data_time: 0.1668 memory: 14275 grad_norm: 0.9171 loss: 1.5337 loss_center: 0.5944 loss_bbox: 0.4099 loss_cls: 0.5295 2024/04/13 00:33:54 - mmengine - INFO - Epoch(train) [5][1200/3111] lr: 2.0000e-04 eta: 10:53:35 time: 1.5993 data_time: 0.0817 memory: 15666 grad_norm: 0.9404 loss: 1.7689 loss_center: 0.7230 loss_bbox: 0.4365 loss_cls: 0.6094 2024/04/13 00:35:21 - mmengine - INFO - Epoch(train) [5][1250/3111] lr: 2.0000e-04 eta: 10:52:19 time: 1.7358 data_time: 0.0824 memory: 15773 grad_norm: 0.8796 loss: 1.5346 loss_center: 0.5885 loss_bbox: 0.4105 loss_cls: 0.5355 2024/04/13 00:36:37 - mmengine - INFO - Epoch(train) [5][1300/3111] lr: 2.0000e-04 eta: 10:50:46 time: 1.5372 data_time: 0.1292 memory: 15694 grad_norm: 0.8199 loss: 1.4971 loss_center: 0.6209 loss_bbox: 0.3720 loss_cls: 0.5041 2024/04/13 00:38:01 - mmengine - INFO - Epoch(train) [5][1350/3111] lr: 2.0000e-04 eta: 10:49:25 time: 1.6772 data_time: 0.1259 memory: 14103 grad_norm: 0.8794 loss: 1.7556 loss_center: 0.7599 loss_bbox: 0.3673 loss_cls: 0.6284 2024/04/13 00:39:29 - mmengine - INFO - Epoch(train) [5][1400/3111] lr: 2.0000e-04 eta: 10:48:11 time: 1.7645 data_time: 0.3025 memory: 15919 grad_norm: 0.8181 loss: 1.6656 loss_center: 0.6924 loss_bbox: 0.3885 loss_cls: 0.5846 2024/04/13 00:40:52 - mmengine - INFO - Epoch(train) [5][1450/3111] lr: 2.0000e-04 eta: 10:46:49 time: 1.6579 data_time: 0.1542 memory: 18252 grad_norm: 0.8715 loss: 1.5886 loss_center: 0.6102 loss_bbox: 0.4395 loss_cls: 0.5388 2024/04/13 00:42:11 - mmengine - INFO - Epoch(train) [5][1500/3111] lr: 2.0000e-04 eta: 10:45:19 time: 1.5775 data_time: 0.0677 memory: 16518 grad_norm: 0.8459 loss: 1.6874 loss_center: 0.7225 loss_bbox: 0.3670 loss_cls: 0.5978 2024/04/13 00:43:35 - mmengine - INFO - Epoch(train) [5][1550/3111] lr: 2.0000e-04 eta: 10:43:58 time: 1.6675 data_time: 0.0999 memory: 16696 grad_norm: 0.8455 loss: 1.6260 loss_center: 0.6703 loss_bbox: 0.3836 loss_cls: 0.5721 2024/04/13 00:43:44 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 00:44:58 - mmengine - INFO - Epoch(train) [5][1600/3111] lr: 2.0000e-04 eta: 10:42:35 time: 1.6604 data_time: 0.1503 memory: 16462 grad_norm: 0.8392 loss: 1.5360 loss_center: 0.6127 loss_bbox: 0.3755 loss_cls: 0.5479 2024/04/13 00:46:24 - mmengine - INFO - Epoch(train) [5][1650/3111] lr: 2.0000e-04 eta: 10:41:18 time: 1.7207 data_time: 0.1100 memory: 17517 grad_norm: 0.9398 loss: 1.6083 loss_center: 0.6606 loss_bbox: 0.3785 loss_cls: 0.5692 2024/04/13 00:47:50 - mmengine - INFO - Epoch(train) [5][1700/3111] lr: 2.0000e-04 eta: 10:40:01 time: 1.7291 data_time: 0.1299 memory: 15789 grad_norm: 0.9128 loss: 1.5271 loss_center: 0.6480 loss_bbox: 0.3364 loss_cls: 0.5426 2024/04/13 00:49:11 - mmengine - INFO - Epoch(train) [5][1750/3111] lr: 2.0000e-04 eta: 10:38:34 time: 1.6098 data_time: 0.1003 memory: 13154 grad_norm: 0.8838 loss: 1.7369 loss_center: 0.6774 loss_bbox: 0.4557 loss_cls: 0.6038 2024/04/13 00:50:36 - mmengine - INFO - Epoch(train) [5][1800/3111] lr: 2.0000e-04 eta: 10:37:15 time: 1.6979 data_time: 0.1324 memory: 17732 grad_norm: 0.8897 loss: 1.6892 loss_center: 0.6692 loss_bbox: 0.4443 loss_cls: 0.5757 2024/04/13 00:52:00 - mmengine - INFO - Epoch(train) [5][1850/3111] lr: 2.0000e-04 eta: 10:35:54 time: 1.6836 data_time: 0.0998 memory: 14393 grad_norm: 0.8861 loss: 1.6078 loss_center: 0.6688 loss_bbox: 0.3803 loss_cls: 0.5587 2024/04/13 00:53:23 - mmengine - INFO - Epoch(train) [5][1900/3111] lr: 2.0000e-04 eta: 10:34:33 time: 1.6732 data_time: 0.0620 memory: 16375 grad_norm: 0.8439 loss: 1.6632 loss_center: 0.6683 loss_bbox: 0.3975 loss_cls: 0.5974 2024/04/13 00:54:44 - mmengine - INFO - Epoch(train) [5][1950/3111] lr: 2.0000e-04 eta: 10:33:07 time: 1.6168 data_time: 0.1596 memory: 14128 grad_norm: 0.9094 loss: 1.6494 loss_center: 0.6868 loss_bbox: 0.3524 loss_cls: 0.6102 2024/04/13 00:56:09 - mmengine - INFO - Epoch(train) [5][2000/3111] lr: 2.0000e-04 eta: 10:31:47 time: 1.6886 data_time: 0.0594 memory: 16330 grad_norm: 0.8828 loss: 1.5329 loss_center: 0.6171 loss_bbox: 0.3650 loss_cls: 0.5508 2024/04/13 00:57:37 - mmengine - INFO - Epoch(train) [5][2050/3111] lr: 2.0000e-04 eta: 10:30:33 time: 1.7744 data_time: 0.1952 memory: 15246 grad_norm: 0.8414 loss: 1.6504 loss_center: 0.7063 loss_bbox: 0.3565 loss_cls: 0.5876 2024/04/13 00:58:58 - mmengine - INFO - Epoch(train) [5][2100/3111] lr: 2.0000e-04 eta: 10:29:07 time: 1.6090 data_time: 0.0838 memory: 14989 grad_norm: 0.8370 loss: 1.5371 loss_center: 0.6423 loss_bbox: 0.3700 loss_cls: 0.5248 2024/04/13 01:00:17 - mmengine - INFO - Epoch(train) [5][2150/3111] lr: 2.0000e-04 eta: 10:27:39 time: 1.5868 data_time: 0.0693 memory: 13741 grad_norm: 0.8970 loss: 1.7804 loss_center: 0.7375 loss_bbox: 0.3921 loss_cls: 0.6508 2024/04/13 01:01:47 - mmengine - INFO - Epoch(train) [5][2200/3111] lr: 2.0000e-04 eta: 10:26:26 time: 1.7945 data_time: 0.1224 memory: 18233 grad_norm: 0.9336 loss: 1.7639 loss_center: 0.6613 loss_bbox: 0.5380 loss_cls: 0.5645 2024/04/13 01:03:07 - mmengine - INFO - Epoch(train) [5][2250/3111] lr: 2.0000e-04 eta: 10:25:00 time: 1.6108 data_time: 0.0640 memory: 15287 grad_norm: 0.8975 loss: 1.4114 loss_center: 0.5697 loss_bbox: 0.3773 loss_cls: 0.4643 2024/04/13 01:04:32 - mmengine - INFO - Epoch(train) [5][2300/3111] lr: 2.0000e-04 eta: 10:23:39 time: 1.6810 data_time: 0.0582 memory: 14668 grad_norm: 0.8032 loss: 1.6923 loss_center: 0.7513 loss_bbox: 0.3281 loss_cls: 0.6130 2024/04/13 01:05:55 - mmengine - INFO - Epoch(train) [5][2350/3111] lr: 2.0000e-04 eta: 10:22:17 time: 1.6705 data_time: 0.0995 memory: 14913 grad_norm: 0.8596 loss: 1.5811 loss_center: 0.6519 loss_bbox: 0.3857 loss_cls: 0.5435 2024/04/13 01:07:18 - mmengine - INFO - Epoch(train) [5][2400/3111] lr: 2.0000e-04 eta: 10:20:54 time: 1.6536 data_time: 0.1383 memory: 15824 grad_norm: 0.9482 loss: 1.5887 loss_center: 0.6463 loss_bbox: 0.3744 loss_cls: 0.5679 2024/04/13 01:08:42 - mmengine - INFO - Epoch(train) [5][2450/3111] lr: 2.0000e-04 eta: 10:19:33 time: 1.6796 data_time: 0.1211 memory: 16500 grad_norm: 0.9078 loss: 1.7388 loss_center: 0.7441 loss_bbox: 0.3677 loss_cls: 0.6269 2024/04/13 01:10:05 - mmengine - INFO - Epoch(train) [5][2500/3111] lr: 2.0000e-04 eta: 10:18:10 time: 1.6569 data_time: 0.1151 memory: 14776 grad_norm: 0.7858 loss: 1.6365 loss_center: 0.6505 loss_bbox: 0.4251 loss_cls: 0.5609 2024/04/13 01:11:23 - mmengine - INFO - Epoch(train) [5][2550/3111] lr: 2.0000e-04 eta: 10:16:42 time: 1.5784 data_time: 0.1072 memory: 15422 grad_norm: 0.8212 loss: 1.5966 loss_center: 0.6371 loss_bbox: 0.3708 loss_cls: 0.5887 2024/04/13 01:11:34 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 01:12:46 - mmengine - INFO - Epoch(train) [5][2600/3111] lr: 2.0000e-04 eta: 10:15:19 time: 1.6515 data_time: 0.0756 memory: 14559 grad_norm: 0.8772 loss: 1.7032 loss_center: 0.6746 loss_bbox: 0.4477 loss_cls: 0.5809 2024/04/13 01:14:10 - mmengine - INFO - Epoch(train) [5][2650/3111] lr: 2.0000e-04 eta: 10:13:57 time: 1.6803 data_time: 0.1329 memory: 15333 grad_norm: 0.9553 loss: 1.5838 loss_center: 0.5921 loss_bbox: 0.4782 loss_cls: 0.5134 2024/04/13 01:15:29 - mmengine - INFO - Epoch(train) [5][2700/3111] lr: 2.0000e-04 eta: 10:12:29 time: 1.5807 data_time: 0.1336 memory: 16392 grad_norm: 0.8383 loss: 1.6516 loss_center: 0.6626 loss_bbox: 0.4120 loss_cls: 0.5770 2024/04/13 01:16:55 - mmengine - INFO - Epoch(train) [5][2750/3111] lr: 2.0000e-04 eta: 10:11:11 time: 1.7201 data_time: 0.1284 memory: 15526 grad_norm: 0.8926 loss: 1.8408 loss_center: 0.7794 loss_bbox: 0.4081 loss_cls: 0.6532 2024/04/13 01:18:21 - mmengine - INFO - Epoch(train) [5][2800/3111] lr: 2.0000e-04 eta: 10:09:52 time: 1.7136 data_time: 0.0554 memory: 18447 grad_norm: 0.9837 loss: 1.5561 loss_center: 0.6641 loss_bbox: 0.3409 loss_cls: 0.5512 2024/04/13 01:19:47 - mmengine - INFO - Epoch(train) [5][2850/3111] lr: 2.0000e-04 eta: 10:08:34 time: 1.7175 data_time: 0.0726 memory: 16332 grad_norm: 0.8677 loss: 1.5877 loss_center: 0.6183 loss_bbox: 0.4106 loss_cls: 0.5588 2024/04/13 01:21:11 - mmengine - INFO - Epoch(train) [5][2900/3111] lr: 2.0000e-04 eta: 10:07:13 time: 1.6893 data_time: 0.0774 memory: 14457 grad_norm: 0.8194 loss: 1.5898 loss_center: 0.6551 loss_bbox: 0.3852 loss_cls: 0.5494 2024/04/13 01:22:34 - mmengine - INFO - Epoch(train) [5][2950/3111] lr: 2.0000e-04 eta: 10:05:51 time: 1.6638 data_time: 0.1273 memory: 17197 grad_norm: 0.8533 loss: 1.6069 loss_center: 0.6190 loss_bbox: 0.4491 loss_cls: 0.5389 2024/04/13 01:23:58 - mmengine - INFO - Epoch(train) [5][3000/3111] lr: 2.0000e-04 eta: 10:04:29 time: 1.6680 data_time: 0.1523 memory: 17983 grad_norm: 0.8192 loss: 1.6041 loss_center: 0.6422 loss_bbox: 0.3781 loss_cls: 0.5838 2024/04/13 01:25:21 - mmengine - INFO - Epoch(train) [5][3050/3111] lr: 2.0000e-04 eta: 10:03:07 time: 1.6684 data_time: 0.0740 memory: 15491 grad_norm: 0.8586 loss: 1.5287 loss_center: 0.6402 loss_bbox: 0.3480 loss_cls: 0.5404 2024/04/13 01:26:43 - mmengine - INFO - Epoch(train) [5][3100/3111] lr: 2.0000e-04 eta: 10:01:42 time: 1.6304 data_time: 0.0864 memory: 15696 grad_norm: 0.9243 loss: 1.5270 loss_center: 0.5717 loss_bbox: 0.4483 loss_cls: 0.5070 2024/04/13 01:26:59 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 01:26:59 - mmengine - INFO - Saving checkpoint at 5 epochs 2024/04/13 01:28:33 - mmengine - INFO - Epoch(train) [6][ 50/3111] lr: 2.0000e-04 eta: 10:00:01 time: 1.6851 data_time: 0.1641 memory: 15217 grad_norm: 0.8358 loss: 1.4195 loss_center: 0.5540 loss_bbox: 0.4001 loss_cls: 0.4654 2024/04/13 01:29:58 - mmengine - INFO - Epoch(train) [6][ 100/3111] lr: 2.0000e-04 eta: 9:58:40 time: 1.6929 data_time: 0.0730 memory: 18017 grad_norm: 0.8040 loss: 1.7459 loss_center: 0.7260 loss_bbox: 0.4026 loss_cls: 0.6174 2024/04/13 01:31:16 - mmengine - INFO - Epoch(train) [6][ 150/3111] lr: 2.0000e-04 eta: 9:57:12 time: 1.5744 data_time: 0.1486 memory: 14392 grad_norm: 0.8250 loss: 1.5927 loss_center: 0.6000 loss_bbox: 0.4341 loss_cls: 0.5585 2024/04/13 01:32:38 - mmengine - INFO - Epoch(train) [6][ 200/3111] lr: 2.0000e-04 eta: 9:55:46 time: 1.6222 data_time: 0.0913 memory: 13985 grad_norm: 0.8115 loss: 1.6374 loss_center: 0.7076 loss_bbox: 0.3685 loss_cls: 0.5613 2024/04/13 01:34:05 - mmengine - INFO - Epoch(train) [6][ 250/3111] lr: 2.0000e-04 eta: 9:54:30 time: 1.7565 data_time: 0.0905 memory: 17212 grad_norm: 0.8175 loss: 1.6856 loss_center: 0.6841 loss_bbox: 0.4045 loss_cls: 0.5971 2024/04/13 01:35:27 - mmengine - INFO - Epoch(train) [6][ 300/3111] lr: 2.0000e-04 eta: 9:53:06 time: 1.6349 data_time: 0.0641 memory: 13977 grad_norm: 0.9208 loss: 1.5365 loss_center: 0.6048 loss_bbox: 0.4037 loss_cls: 0.5279 2024/04/13 01:36:50 - mmengine - INFO - Epoch(train) [6][ 350/3111] lr: 2.0000e-04 eta: 9:51:43 time: 1.6566 data_time: 0.0843 memory: 12991 grad_norm: 0.8631 loss: 1.6462 loss_center: 0.6819 loss_bbox: 0.3825 loss_cls: 0.5818 2024/04/13 01:38:15 - mmengine - INFO - Epoch(train) [6][ 400/3111] lr: 2.0000e-04 eta: 9:50:23 time: 1.6962 data_time: 0.1062 memory: 18088 grad_norm: 0.9370 loss: 1.6137 loss_center: 0.6833 loss_bbox: 0.3525 loss_cls: 0.5779 2024/04/13 01:39:29 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 01:39:36 - mmengine - INFO - Epoch(train) [6][ 450/3111] lr: 2.0000e-04 eta: 9:48:58 time: 1.6310 data_time: 0.1581 memory: 16974 grad_norm: 0.9230 loss: 1.5346 loss_center: 0.5680 loss_bbox: 0.4619 loss_cls: 0.5047 2024/04/13 01:40:59 - mmengine - INFO - Epoch(train) [6][ 500/3111] lr: 2.0000e-04 eta: 9:47:36 time: 1.6571 data_time: 0.0703 memory: 16784 grad_norm: 0.9370 loss: 1.6936 loss_center: 0.6714 loss_bbox: 0.4539 loss_cls: 0.5683 2024/04/13 01:42:21 - mmengine - INFO - Epoch(train) [6][ 550/3111] lr: 2.0000e-04 eta: 9:46:11 time: 1.6358 data_time: 0.1383 memory: 14617 grad_norm: 0.8112 loss: 1.6135 loss_center: 0.6255 loss_bbox: 0.4541 loss_cls: 0.5340 2024/04/13 01:43:40 - mmengine - INFO - Epoch(train) [6][ 600/3111] lr: 2.0000e-04 eta: 9:44:43 time: 1.5765 data_time: 0.0824 memory: 16553 grad_norm: 0.8129 loss: 1.5251 loss_center: 0.6674 loss_bbox: 0.3164 loss_cls: 0.5414 2024/04/13 01:44:59 - mmengine - INFO - Epoch(train) [6][ 650/3111] lr: 2.0000e-04 eta: 9:43:15 time: 1.5795 data_time: 0.1127 memory: 16320 grad_norm: 0.8689 loss: 1.6045 loss_center: 0.6315 loss_bbox: 0.4499 loss_cls: 0.5231 2024/04/13 01:46:21 - mmengine - INFO - Epoch(train) [6][ 700/3111] lr: 2.0000e-04 eta: 9:41:51 time: 1.6371 data_time: 0.0840 memory: 22792 grad_norm: 0.8998 loss: 1.6367 loss_center: 0.6389 loss_bbox: 0.4286 loss_cls: 0.5693 2024/04/13 01:47:40 - mmengine - INFO - Epoch(train) [6][ 750/3111] lr: 2.0000e-04 eta: 9:40:24 time: 1.5921 data_time: 0.0593 memory: 15927 grad_norm: 0.7922 loss: 1.6484 loss_center: 0.6933 loss_bbox: 0.3608 loss_cls: 0.5943 2024/04/13 01:49:06 - mmengine - INFO - Epoch(train) [6][ 800/3111] lr: 2.0000e-04 eta: 9:39:05 time: 1.7070 data_time: 0.2028 memory: 19049 grad_norm: 0.7939 loss: 1.6204 loss_center: 0.6666 loss_bbox: 0.3803 loss_cls: 0.5734 2024/04/13 01:50:26 - mmengine - INFO - Epoch(train) [6][ 850/3111] lr: 2.0000e-04 eta: 9:37:39 time: 1.6088 data_time: 0.1569 memory: 17317 grad_norm: 0.8627 loss: 1.4594 loss_center: 0.5545 loss_bbox: 0.4128 loss_cls: 0.4920 2024/04/13 01:51:45 - mmengine - INFO - Epoch(train) [6][ 900/3111] lr: 2.0000e-04 eta: 9:36:11 time: 1.5815 data_time: 0.1126 memory: 17613 grad_norm: 0.7984 loss: 1.7324 loss_center: 0.7485 loss_bbox: 0.3631 loss_cls: 0.6208 2024/04/13 01:53:11 - mmengine - INFO - Epoch(train) [6][ 950/3111] lr: 2.0000e-04 eta: 9:34:52 time: 1.7116 data_time: 0.0888 memory: 16025 grad_norm: 0.8388 loss: 1.6119 loss_center: 0.6543 loss_bbox: 0.3934 loss_cls: 0.5641 2024/04/13 01:54:33 - mmengine - INFO - Epoch(train) [6][1000/3111] lr: 2.0000e-04 eta: 9:33:28 time: 1.6362 data_time: 0.1056 memory: 16799 grad_norm: 0.9271 loss: 1.7604 loss_center: 0.7440 loss_bbox: 0.3597 loss_cls: 0.6567 2024/04/13 01:55:50 - mmengine - INFO - Epoch(train) [6][1050/3111] lr: 2.0000e-04 eta: 9:31:59 time: 1.5499 data_time: 0.0972 memory: 17106 grad_norm: 0.8546 loss: 1.4633 loss_center: 0.5689 loss_bbox: 0.4080 loss_cls: 0.4863 2024/04/13 01:57:14 - mmengine - INFO - Epoch(train) [6][1100/3111] lr: 2.0000e-04 eta: 9:30:38 time: 1.6844 data_time: 0.0522 memory: 13981 grad_norm: 0.7831 loss: 1.5219 loss_center: 0.6248 loss_bbox: 0.3647 loss_cls: 0.5324 2024/04/13 01:58:38 - mmengine - INFO - Epoch(train) [6][1150/3111] lr: 2.0000e-04 eta: 9:29:16 time: 1.6772 data_time: 0.1094 memory: 15177 grad_norm: 0.8659 loss: 1.6739 loss_center: 0.7097 loss_bbox: 0.3771 loss_cls: 0.5871 2024/04/13 02:00:03 - mmengine - INFO - Epoch(train) [6][1200/3111] lr: 2.0000e-04 eta: 9:27:56 time: 1.6937 data_time: 0.0882 memory: 13828 grad_norm: 0.8805 loss: 1.5914 loss_center: 0.6642 loss_bbox: 0.3868 loss_cls: 0.5405 2024/04/13 02:01:30 - mmengine - INFO - Epoch(train) [6][1250/3111] lr: 2.0000e-04 eta: 9:26:38 time: 1.7453 data_time: 0.0596 memory: 15215 grad_norm: 0.8509 loss: 1.5397 loss_center: 0.6139 loss_bbox: 0.4255 loss_cls: 0.5003 2024/04/13 02:02:53 - mmengine - INFO - Epoch(train) [6][1300/3111] lr: 2.0000e-04 eta: 9:25:15 time: 1.6487 data_time: 0.1715 memory: 15675 grad_norm: 0.9354 loss: 1.7066 loss_center: 0.7205 loss_bbox: 0.3805 loss_cls: 0.6056 2024/04/13 02:04:17 - mmengine - INFO - Epoch(train) [6][1350/3111] lr: 2.0000e-04 eta: 9:23:54 time: 1.6832 data_time: 0.1189 memory: 15561 grad_norm: 0.8255 loss: 1.5617 loss_center: 0.6638 loss_bbox: 0.3577 loss_cls: 0.5402 2024/04/13 02:05:41 - mmengine - INFO - Epoch(train) [6][1400/3111] lr: 2.0000e-04 eta: 9:22:32 time: 1.6810 data_time: 0.1230 memory: 13813 grad_norm: 0.9001 loss: 1.7712 loss_center: 0.6555 loss_bbox: 0.5659 loss_cls: 0.5498 2024/04/13 02:06:57 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 02:07:06 - mmengine - INFO - Epoch(train) [6][1450/3111] lr: 2.0000e-04 eta: 9:21:12 time: 1.6960 data_time: 0.0790 memory: 20774 grad_norm: 0.9251 loss: 1.5958 loss_center: 0.6172 loss_bbox: 0.4519 loss_cls: 0.5267 2024/04/13 02:08:28 - mmengine - INFO - Epoch(train) [6][1500/3111] lr: 2.0000e-04 eta: 9:19:48 time: 1.6405 data_time: 0.0538 memory: 16154 grad_norm: 0.8165 loss: 1.6612 loss_center: 0.6968 loss_bbox: 0.3754 loss_cls: 0.5891 2024/04/13 02:09:51 - mmengine - INFO - Epoch(train) [6][1550/3111] lr: 2.0000e-04 eta: 9:18:26 time: 1.6612 data_time: 0.0721 memory: 16444 grad_norm: 0.8370 loss: 1.6332 loss_center: 0.6530 loss_bbox: 0.4169 loss_cls: 0.5633 2024/04/13 02:11:16 - mmengine - INFO - Epoch(train) [6][1600/3111] lr: 2.0000e-04 eta: 9:17:05 time: 1.7007 data_time: 0.0701 memory: 15849 grad_norm: 0.8401 loss: 1.5787 loss_center: 0.6046 loss_bbox: 0.4541 loss_cls: 0.5200 2024/04/13 02:12:37 - mmengine - INFO - Epoch(train) [6][1650/3111] lr: 2.0000e-04 eta: 9:15:41 time: 1.6342 data_time: 0.0762 memory: 13605 grad_norm: 0.8333 loss: 1.7790 loss_center: 0.7791 loss_bbox: 0.3801 loss_cls: 0.6198 2024/04/13 02:13:59 - mmengine - INFO - Epoch(train) [6][1700/3111] lr: 2.0000e-04 eta: 9:14:17 time: 1.6330 data_time: 0.1604 memory: 16760 grad_norm: 0.8375 loss: 1.6304 loss_center: 0.5942 loss_bbox: 0.4995 loss_cls: 0.5367 2024/04/13 02:15:22 - mmengine - INFO - Epoch(train) [6][1750/3111] lr: 2.0000e-04 eta: 9:12:54 time: 1.6570 data_time: 0.1686 memory: 13304 grad_norm: 0.8791 loss: 1.5752 loss_center: 0.6088 loss_bbox: 0.4149 loss_cls: 0.5515 2024/04/13 02:16:46 - mmengine - INFO - Epoch(train) [6][1800/3111] lr: 2.0000e-04 eta: 9:11:33 time: 1.6797 data_time: 0.1736 memory: 16337 grad_norm: 0.8882 loss: 1.5789 loss_center: 0.6816 loss_bbox: 0.3716 loss_cls: 0.5257 2024/04/13 02:18:09 - mmengine - INFO - Epoch(train) [6][1850/3111] lr: 2.0000e-04 eta: 9:10:11 time: 1.6683 data_time: 0.2189 memory: 16273 grad_norm: 0.8256 loss: 1.4257 loss_center: 0.5532 loss_bbox: 0.3841 loss_cls: 0.4884 2024/04/13 02:19:36 - mmengine - INFO - Epoch(train) [6][1900/3111] lr: 2.0000e-04 eta: 9:08:52 time: 1.7255 data_time: 0.1176 memory: 14997 grad_norm: 0.8319 loss: 1.6871 loss_center: 0.6702 loss_bbox: 0.4291 loss_cls: 0.5878 2024/04/13 02:21:04 - mmengine - INFO - Epoch(train) [6][1950/3111] lr: 2.0000e-04 eta: 9:07:35 time: 1.7678 data_time: 0.0820 memory: 20121 grad_norm: 0.9169 loss: 1.5369 loss_center: 0.6348 loss_bbox: 0.3438 loss_cls: 0.5583 2024/04/13 02:22:27 - mmengine - INFO - Epoch(train) [6][2000/3111] lr: 2.0000e-04 eta: 9:06:12 time: 1.6564 data_time: 0.1154 memory: 17942 grad_norm: 0.8442 loss: 1.5160 loss_center: 0.5822 loss_bbox: 0.4257 loss_cls: 0.5082 2024/04/13 02:23:53 - mmengine - INFO - Epoch(train) [6][2050/3111] lr: 2.0000e-04 eta: 9:04:53 time: 1.7179 data_time: 0.0780 memory: 16651 grad_norm: 0.8444 loss: 1.5718 loss_center: 0.6758 loss_bbox: 0.3732 loss_cls: 0.5228 2024/04/13 02:25:17 - mmengine - INFO - Epoch(train) [6][2100/3111] lr: 2.0000e-04 eta: 9:03:31 time: 1.6794 data_time: 0.0709 memory: 21010 grad_norm: 0.8914 loss: 1.8043 loss_center: 0.6368 loss_bbox: 0.6588 loss_cls: 0.5086 2024/04/13 02:26:44 - mmengine - INFO - Epoch(train) [6][2150/3111] lr: 2.0000e-04 eta: 9:02:13 time: 1.7471 data_time: 0.0801 memory: 16820 grad_norm: 0.8800 loss: 1.6636 loss_center: 0.7095 loss_bbox: 0.3799 loss_cls: 0.5742 2024/04/13 02:28:07 - mmengine - INFO - Epoch(train) [6][2200/3111] lr: 2.0000e-04 eta: 9:00:50 time: 1.6492 data_time: 0.0867 memory: 14783 grad_norm: 0.8206 loss: 1.5830 loss_center: 0.6371 loss_bbox: 0.4249 loss_cls: 0.5210 2024/04/13 02:29:25 - mmengine - INFO - Epoch(train) [6][2250/3111] lr: 2.0000e-04 eta: 8:59:22 time: 1.5684 data_time: 0.0861 memory: 15356 grad_norm: 0.8226 loss: 1.5139 loss_center: 0.6238 loss_bbox: 0.3833 loss_cls: 0.5068 2024/04/13 02:30:43 - mmengine - INFO - Epoch(train) [6][2300/3111] lr: 2.0000e-04 eta: 8:57:54 time: 1.5634 data_time: 0.0735 memory: 16462 grad_norm: 0.8220 loss: 1.5587 loss_center: 0.6795 loss_bbox: 0.3208 loss_cls: 0.5584 2024/04/13 02:32:07 - mmengine - INFO - Epoch(train) [6][2350/3111] lr: 2.0000e-04 eta: 8:56:33 time: 1.6815 data_time: 0.0788 memory: 17462 grad_norm: 0.8447 loss: 1.6768 loss_center: 0.6759 loss_bbox: 0.4337 loss_cls: 0.5671 2024/04/13 02:33:29 - mmengine - INFO - Epoch(train) [6][2400/3111] lr: 2.0000e-04 eta: 8:55:09 time: 1.6336 data_time: 0.0607 memory: 14087 grad_norm: 0.8882 loss: 1.7540 loss_center: 0.7280 loss_bbox: 0.4021 loss_cls: 0.6240 2024/04/13 02:34:42 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 02:34:51 - mmengine - INFO - Epoch(train) [6][2450/3111] lr: 2.0000e-04 eta: 8:53:45 time: 1.6498 data_time: 0.0779 memory: 15137 grad_norm: 0.8364 loss: 1.5074 loss_center: 0.6175 loss_bbox: 0.3503 loss_cls: 0.5397 2024/04/13 02:36:15 - mmengine - INFO - Epoch(train) [6][2500/3111] lr: 2.0000e-04 eta: 8:52:24 time: 1.6781 data_time: 0.1479 memory: 14207 grad_norm: 0.9167 loss: 1.4730 loss_center: 0.5761 loss_bbox: 0.3996 loss_cls: 0.4973 2024/04/13 02:37:36 - mmengine - INFO - Epoch(train) [6][2550/3111] lr: 2.0000e-04 eta: 8:50:59 time: 1.6170 data_time: 0.2012 memory: 13616 grad_norm: 0.8537 loss: 1.5856 loss_center: 0.6401 loss_bbox: 0.3777 loss_cls: 0.5678 2024/04/13 02:39:03 - mmengine - INFO - Epoch(train) [6][2600/3111] lr: 2.0000e-04 eta: 8:49:40 time: 1.7433 data_time: 0.0600 memory: 17905 grad_norm: 0.9204 loss: 1.6430 loss_center: 0.6276 loss_bbox: 0.4532 loss_cls: 0.5622 2024/04/13 02:40:29 - mmengine - INFO - Epoch(train) [6][2650/3111] lr: 2.0000e-04 eta: 8:48:20 time: 1.7074 data_time: 0.1481 memory: 16088 grad_norm: 0.7883 loss: 1.5926 loss_center: 0.6409 loss_bbox: 0.4116 loss_cls: 0.5400 2024/04/13 02:41:57 - mmengine - INFO - Epoch(train) [6][2700/3111] lr: 2.0000e-04 eta: 8:47:02 time: 1.7572 data_time: 0.1210 memory: 17154 grad_norm: 0.8638 loss: 1.7055 loss_center: 0.7135 loss_bbox: 0.3730 loss_cls: 0.6189 2024/04/13 02:43:19 - mmengine - INFO - Epoch(train) [6][2750/3111] lr: 2.0000e-04 eta: 8:45:40 time: 1.6579 data_time: 0.1854 memory: 15611 grad_norm: 0.8283 loss: 1.4190 loss_center: 0.5959 loss_bbox: 0.3386 loss_cls: 0.4845 2024/04/13 02:44:41 - mmengine - INFO - Epoch(train) [6][2800/3111] lr: 2.0000e-04 eta: 8:44:16 time: 1.6397 data_time: 0.1153 memory: 19714 grad_norm: 0.8733 loss: 1.6859 loss_center: 0.6486 loss_bbox: 0.4461 loss_cls: 0.5912 2024/04/13 02:46:06 - mmengine - INFO - Epoch(train) [6][2850/3111] lr: 2.0000e-04 eta: 8:42:55 time: 1.6910 data_time: 0.0994 memory: 13649 grad_norm: 0.8879 loss: 1.7083 loss_center: 0.6968 loss_bbox: 0.4218 loss_cls: 0.5897 2024/04/13 02:47:28 - mmengine - INFO - Epoch(train) [6][2900/3111] lr: 2.0000e-04 eta: 8:41:31 time: 1.6358 data_time: 0.1095 memory: 15387 grad_norm: 0.8083 loss: 1.5749 loss_center: 0.6703 loss_bbox: 0.3568 loss_cls: 0.5478 2024/04/13 02:48:51 - mmengine - INFO - Epoch(train) [6][2950/3111] lr: 2.0000e-04 eta: 8:40:08 time: 1.6576 data_time: 0.0991 memory: 16021 grad_norm: 0.8189 loss: 1.7631 loss_center: 0.6661 loss_bbox: 0.4948 loss_cls: 0.6021 2024/04/13 02:50:17 - mmengine - INFO - Epoch(train) [6][3000/3111] lr: 2.0000e-04 eta: 8:38:48 time: 1.7178 data_time: 0.0882 memory: 14772 grad_norm: 0.8679 loss: 1.4208 loss_center: 0.5713 loss_bbox: 0.3781 loss_cls: 0.4713 2024/04/13 02:51:43 - mmengine - INFO - Epoch(train) [6][3050/3111] lr: 2.0000e-04 eta: 8:37:28 time: 1.7210 data_time: 0.0778 memory: 15929 grad_norm: 0.8656 loss: 1.7067 loss_center: 0.6492 loss_bbox: 0.4934 loss_cls: 0.5641 2024/04/13 02:53:04 - mmengine - INFO - Epoch(train) [6][3100/3111] lr: 2.0000e-04 eta: 8:36:04 time: 1.6290 data_time: 0.1128 memory: 15378 grad_norm: 0.8749 loss: 1.6291 loss_center: 0.6722 loss_bbox: 0.4228 loss_cls: 0.5341 2024/04/13 02:53:22 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 02:53:22 - mmengine - INFO - Saving checkpoint at 6 epochs 2024/04/13 02:54:53 - mmengine - INFO - Epoch(train) [7][ 50/3111] lr: 2.0000e-04 eta: 8:34:20 time: 1.6159 data_time: 0.0757 memory: 16031 grad_norm: 0.9625 loss: 1.6272 loss_center: 0.6862 loss_bbox: 0.4016 loss_cls: 0.5394 2024/04/13 02:56:15 - mmengine - INFO - Epoch(train) [7][ 100/3111] lr: 2.0000e-04 eta: 8:32:56 time: 1.6420 data_time: 0.0837 memory: 13605 grad_norm: 0.8403 loss: 1.4719 loss_center: 0.6022 loss_bbox: 0.3507 loss_cls: 0.5190 2024/04/13 02:57:37 - mmengine - INFO - Epoch(train) [7][ 150/3111] lr: 2.0000e-04 eta: 8:31:33 time: 1.6383 data_time: 0.1289 memory: 18637 grad_norm: 0.8420 loss: 1.5172 loss_center: 0.6029 loss_bbox: 0.4066 loss_cls: 0.5077 2024/04/13 02:58:59 - mmengine - INFO - Epoch(train) [7][ 200/3111] lr: 2.0000e-04 eta: 8:30:09 time: 1.6530 data_time: 0.1690 memory: 14483 grad_norm: 1.0181 loss: 1.7546 loss_center: 0.7277 loss_bbox: 0.3990 loss_cls: 0.6280 2024/04/13 03:00:22 - mmengine - INFO - Epoch(train) [7][ 250/3111] lr: 2.0000e-04 eta: 8:28:46 time: 1.6516 data_time: 0.0978 memory: 15745 grad_norm: 0.8783 loss: 1.7126 loss_center: 0.7050 loss_bbox: 0.4160 loss_cls: 0.5916 2024/04/13 03:01:47 - mmengine - INFO - Epoch(train) [7][ 300/3111] lr: 2.0000e-04 eta: 8:27:26 time: 1.7060 data_time: 0.1402 memory: 15470 grad_norm: 0.8327 loss: 1.5335 loss_center: 0.6134 loss_bbox: 0.4055 loss_cls: 0.5146 2024/04/13 03:02:42 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 03:03:10 - mmengine - INFO - Epoch(train) [7][ 350/3111] lr: 2.0000e-04 eta: 8:26:03 time: 1.6520 data_time: 0.1265 memory: 14191 grad_norm: 0.7504 loss: 1.5960 loss_center: 0.6828 loss_bbox: 0.3533 loss_cls: 0.5599 2024/04/13 03:04:31 - mmengine - INFO - Epoch(train) [7][ 400/3111] lr: 2.0000e-04 eta: 8:24:38 time: 1.6247 data_time: 0.1093 memory: 14697 grad_norm: 0.7747 loss: 1.4810 loss_center: 0.6200 loss_bbox: 0.3547 loss_cls: 0.5062 2024/04/13 03:05:54 - mmengine - INFO - Epoch(train) [7][ 450/3111] lr: 2.0000e-04 eta: 8:23:15 time: 1.6519 data_time: 0.1305 memory: 17421 grad_norm: 0.8007 loss: 1.7256 loss_center: 0.7125 loss_bbox: 0.3928 loss_cls: 0.6203 2024/04/13 03:07:19 - mmengine - INFO - Epoch(train) [7][ 500/3111] lr: 2.0000e-04 eta: 8:21:54 time: 1.6984 data_time: 0.0858 memory: 15014 grad_norm: 0.7986 loss: 1.4859 loss_center: 0.6037 loss_bbox: 0.3761 loss_cls: 0.5061 2024/04/13 03:08:39 - mmengine - INFO - Epoch(train) [7][ 550/3111] lr: 2.0000e-04 eta: 8:20:29 time: 1.6027 data_time: 0.1450 memory: 15108 grad_norm: 0.8128 loss: 1.4521 loss_center: 0.5647 loss_bbox: 0.4226 loss_cls: 0.4649 2024/04/13 03:10:03 - mmengine - INFO - Epoch(train) [7][ 600/3111] lr: 2.0000e-04 eta: 8:19:07 time: 1.6782 data_time: 0.0660 memory: 13626 grad_norm: 0.8414 loss: 1.6665 loss_center: 0.6737 loss_bbox: 0.4183 loss_cls: 0.5745 2024/04/13 03:11:23 - mmengine - INFO - Epoch(train) [7][ 650/3111] lr: 2.0000e-04 eta: 8:17:41 time: 1.5991 data_time: 0.2403 memory: 14974 grad_norm: 0.8216 loss: 1.3823 loss_center: 0.5243 loss_bbox: 0.4316 loss_cls: 0.4265 2024/04/13 03:12:46 - mmengine - INFO - Epoch(train) [7][ 700/3111] lr: 2.0000e-04 eta: 8:16:19 time: 1.6664 data_time: 0.1401 memory: 14697 grad_norm: 0.8368 loss: 1.4630 loss_center: 0.5604 loss_bbox: 0.3980 loss_cls: 0.5046 2024/04/13 03:14:09 - mmengine - INFO - Epoch(train) [7][ 750/3111] lr: 2.0000e-04 eta: 8:14:56 time: 1.6677 data_time: 0.0579 memory: 13324 grad_norm: 0.8254 loss: 1.6939 loss_center: 0.7342 loss_bbox: 0.3531 loss_cls: 0.6066 2024/04/13 03:15:29 - mmengine - INFO - Epoch(train) [7][ 800/3111] lr: 2.0000e-04 eta: 8:13:30 time: 1.5868 data_time: 0.0677 memory: 16196 grad_norm: 0.7889 loss: 1.4907 loss_center: 0.6376 loss_bbox: 0.3394 loss_cls: 0.5137 2024/04/13 03:16:51 - mmengine - INFO - Epoch(train) [7][ 850/3111] lr: 2.0000e-04 eta: 8:12:06 time: 1.6387 data_time: 0.0670 memory: 17106 grad_norm: 0.8168 loss: 1.5571 loss_center: 0.6093 loss_bbox: 0.4322 loss_cls: 0.5155 2024/04/13 03:18:13 - mmengine - INFO - Epoch(train) [7][ 900/3111] lr: 2.0000e-04 eta: 8:10:43 time: 1.6578 data_time: 0.1249 memory: 15548 grad_norm: 0.8878 loss: 1.4631 loss_center: 0.5810 loss_bbox: 0.3907 loss_cls: 0.4914 2024/04/13 03:19:36 - mmengine - INFO - Epoch(train) [7][ 950/3111] lr: 2.0000e-04 eta: 8:09:21 time: 1.6568 data_time: 0.0867 memory: 18888 grad_norm: 0.7965 loss: 1.5787 loss_center: 0.6435 loss_bbox: 0.3817 loss_cls: 0.5535 2024/04/13 03:21:02 - mmengine - INFO - Epoch(train) [7][1000/3111] lr: 2.0000e-04 eta: 8:08:00 time: 1.7045 data_time: 0.1474 memory: 15843 grad_norm: 0.7912 loss: 1.4989 loss_center: 0.5915 loss_bbox: 0.3938 loss_cls: 0.5137 2024/04/13 03:22:26 - mmengine - INFO - Epoch(train) [7][1050/3111] lr: 2.0000e-04 eta: 8:06:38 time: 1.6806 data_time: 0.1247 memory: 13639 grad_norm: 0.7495 loss: 1.6633 loss_center: 0.7095 loss_bbox: 0.3569 loss_cls: 0.5969 2024/04/13 03:23:44 - mmengine - INFO - Epoch(train) [7][1100/3111] lr: 2.0000e-04 eta: 8:05:12 time: 1.5780 data_time: 0.1502 memory: 15858 grad_norm: 0.8494 loss: 1.7456 loss_center: 0.7080 loss_bbox: 0.4324 loss_cls: 0.6052 2024/04/13 03:25:06 - mmengine - INFO - Epoch(train) [7][1150/3111] lr: 2.0000e-04 eta: 8:03:48 time: 1.6327 data_time: 0.0680 memory: 15672 grad_norm: 0.7920 loss: 1.5106 loss_center: 0.6220 loss_bbox: 0.3613 loss_cls: 0.5273 2024/04/13 03:26:31 - mmengine - INFO - Epoch(train) [7][1200/3111] lr: 2.0000e-04 eta: 8:02:26 time: 1.6925 data_time: 0.0937 memory: 15260 grad_norm: 0.7931 loss: 1.5278 loss_center: 0.6616 loss_bbox: 0.3515 loss_cls: 0.5147 2024/04/13 03:27:52 - mmengine - INFO - Epoch(train) [7][1250/3111] lr: 2.0000e-04 eta: 8:01:02 time: 1.6252 data_time: 0.0861 memory: 15613 grad_norm: 1.0825 loss: 1.5959 loss_center: 0.6061 loss_bbox: 0.4572 loss_cls: 0.5326 2024/04/13 03:29:15 - mmengine - INFO - Epoch(train) [7][1300/3111] lr: 2.0000e-04 eta: 7:59:39 time: 1.6535 data_time: 0.1178 memory: 16272 grad_norm: 0.8535 loss: 1.7393 loss_center: 0.7031 loss_bbox: 0.4248 loss_cls: 0.6113 2024/04/13 03:30:13 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 03:30:39 - mmengine - INFO - Epoch(train) [7][1350/3111] lr: 2.0000e-04 eta: 7:58:17 time: 1.6818 data_time: 0.0570 memory: 13897 grad_norm: 0.8519 loss: 1.4405 loss_center: 0.5922 loss_bbox: 0.3676 loss_cls: 0.4807 2024/04/13 03:32:05 - mmengine - INFO - Epoch(train) [7][1400/3111] lr: 2.0000e-04 eta: 7:56:57 time: 1.7206 data_time: 0.0728 memory: 16460 grad_norm: 0.7794 loss: 1.6123 loss_center: 0.6496 loss_bbox: 0.4321 loss_cls: 0.5306 2024/04/13 03:33:31 - mmengine - INFO - Epoch(train) [7][1450/3111] lr: 2.0000e-04 eta: 7:55:37 time: 1.7296 data_time: 0.2314 memory: 15201 grad_norm: 0.7947 loss: 1.5828 loss_center: 0.6505 loss_bbox: 0.3866 loss_cls: 0.5457 2024/04/13 03:34:54 - mmengine - INFO - Epoch(train) [7][1500/3111] lr: 2.0000e-04 eta: 7:54:14 time: 1.6537 data_time: 0.1511 memory: 16910 grad_norm: 0.7878 loss: 1.6055 loss_center: 0.6852 loss_bbox: 0.3389 loss_cls: 0.5814 2024/04/13 03:36:14 - mmengine - INFO - Epoch(train) [7][1550/3111] lr: 2.0000e-04 eta: 7:52:49 time: 1.6018 data_time: 0.1072 memory: 17271 grad_norm: 0.8294 loss: 1.5646 loss_center: 0.6337 loss_bbox: 0.4102 loss_cls: 0.5207 2024/04/13 03:37:38 - mmengine - INFO - Epoch(train) [7][1600/3111] lr: 2.0000e-04 eta: 7:51:27 time: 1.6712 data_time: 0.1267 memory: 17894 grad_norm: 0.8186 loss: 1.6546 loss_center: 0.6163 loss_bbox: 0.4780 loss_cls: 0.5603 2024/04/13 03:39:03 - mmengine - INFO - Epoch(train) [7][1650/3111] lr: 2.0000e-04 eta: 7:50:06 time: 1.7118 data_time: 0.0764 memory: 18347 grad_norm: 0.7810 loss: 1.6587 loss_center: 0.6004 loss_bbox: 0.5187 loss_cls: 0.5396 2024/04/13 03:40:27 - mmengine - INFO - Epoch(train) [7][1700/3111] lr: 2.0000e-04 eta: 7:48:44 time: 1.6852 data_time: 0.1504 memory: 16127 grad_norm: 0.8050 loss: 1.7213 loss_center: 0.7220 loss_bbox: 0.3745 loss_cls: 0.6248 2024/04/13 03:41:53 - mmengine - INFO - Epoch(train) [7][1750/3111] lr: 2.0000e-04 eta: 7:47:23 time: 1.7026 data_time: 0.1435 memory: 17174 grad_norm: 0.7367 loss: 1.5811 loss_center: 0.6065 loss_bbox: 0.4530 loss_cls: 0.5216 2024/04/13 03:43:11 - mmengine - INFO - Epoch(train) [7][1800/3111] lr: 2.0000e-04 eta: 7:45:57 time: 1.5721 data_time: 0.1308 memory: 16278 grad_norm: 0.7391 loss: 1.5207 loss_center: 0.6058 loss_bbox: 0.4247 loss_cls: 0.4902 2024/04/13 03:44:35 - mmengine - INFO - Epoch(train) [7][1850/3111] lr: 2.0000e-04 eta: 7:44:35 time: 1.6715 data_time: 0.0843 memory: 15996 grad_norm: 0.8109 loss: 1.6858 loss_center: 0.7169 loss_bbox: 0.3842 loss_cls: 0.5847 2024/04/13 03:45:57 - mmengine - INFO - Epoch(train) [7][1900/3111] lr: 2.0000e-04 eta: 7:43:11 time: 1.6460 data_time: 0.1174 memory: 16584 grad_norm: 0.8764 loss: 1.6737 loss_center: 0.6993 loss_bbox: 0.4107 loss_cls: 0.5637 2024/04/13 03:47:22 - mmengine - INFO - Epoch(train) [7][1950/3111] lr: 2.0000e-04 eta: 7:41:50 time: 1.6992 data_time: 0.0981 memory: 15151 grad_norm: 0.7973 loss: 1.4770 loss_center: 0.5821 loss_bbox: 0.4073 loss_cls: 0.4877 2024/04/13 03:48:44 - mmengine - INFO - Epoch(train) [7][2000/3111] lr: 2.0000e-04 eta: 7:40:26 time: 1.6304 data_time: 0.1100 memory: 16010 grad_norm: 0.8255 loss: 1.3743 loss_center: 0.5701 loss_bbox: 0.3399 loss_cls: 0.4643 2024/04/13 03:50:09 - mmengine - INFO - Epoch(train) [7][2050/3111] lr: 2.0000e-04 eta: 7:39:05 time: 1.7031 data_time: 0.1102 memory: 17438 grad_norm: 0.8448 loss: 1.6210 loss_center: 0.6633 loss_bbox: 0.4165 loss_cls: 0.5412 2024/04/13 03:51:29 - mmengine - INFO - Epoch(train) [7][2100/3111] lr: 2.0000e-04 eta: 7:37:40 time: 1.6028 data_time: 0.0805 memory: 15544 grad_norm: 0.7942 loss: 1.4696 loss_center: 0.6175 loss_bbox: 0.3687 loss_cls: 0.4834 2024/04/13 03:52:51 - mmengine - INFO - Epoch(train) [7][2150/3111] lr: 2.0000e-04 eta: 7:36:16 time: 1.6347 data_time: 0.1625 memory: 16392 grad_norm: 0.7585 loss: 1.4700 loss_center: 0.5923 loss_bbox: 0.3850 loss_cls: 0.4927 2024/04/13 03:54:13 - mmengine - INFO - Epoch(train) [7][2200/3111] lr: 2.0000e-04 eta: 7:34:53 time: 1.6427 data_time: 0.1183 memory: 16744 grad_norm: 0.8734 loss: 1.5290 loss_center: 0.6093 loss_bbox: 0.4138 loss_cls: 0.5059 2024/04/13 03:55:37 - mmengine - INFO - Epoch(train) [7][2250/3111] lr: 2.0000e-04 eta: 7:33:31 time: 1.6887 data_time: 0.2015 memory: 18566 grad_norm: 0.8456 loss: 1.4794 loss_center: 0.5716 loss_bbox: 0.4052 loss_cls: 0.5025 2024/04/13 03:57:01 - mmengine - INFO - Epoch(train) [7][2300/3111] lr: 2.0000e-04 eta: 7:32:08 time: 1.6659 data_time: 0.1482 memory: 17601 grad_norm: 0.7779 loss: 1.5075 loss_center: 0.6030 loss_bbox: 0.4298 loss_cls: 0.4747 2024/04/13 03:57:55 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 03:58:23 - mmengine - INFO - Epoch(train) [7][2350/3111] lr: 2.0000e-04 eta: 7:30:45 time: 1.6484 data_time: 0.0544 memory: 13256 grad_norm: 0.7717 loss: 1.6216 loss_center: 0.6764 loss_bbox: 0.3737 loss_cls: 0.5714 2024/04/13 03:59:48 - mmengine - INFO - Epoch(train) [7][2400/3111] lr: 2.0000e-04 eta: 7:29:24 time: 1.6977 data_time: 0.0642 memory: 14196 grad_norm: 0.7797 loss: 1.5282 loss_center: 0.6146 loss_bbox: 0.4006 loss_cls: 0.5129 2024/04/13 04:01:11 - mmengine - INFO - Epoch(train) [7][2450/3111] lr: 2.0000e-04 eta: 7:28:01 time: 1.6608 data_time: 0.1207 memory: 17286 grad_norm: 0.8279 loss: 1.6155 loss_center: 0.6704 loss_bbox: 0.3989 loss_cls: 0.5462 2024/04/13 04:02:34 - mmengine - INFO - Epoch(train) [7][2500/3111] lr: 2.0000e-04 eta: 7:26:39 time: 1.6667 data_time: 0.1673 memory: 15015 grad_norm: 0.7628 loss: 1.5874 loss_center: 0.6810 loss_bbox: 0.3431 loss_cls: 0.5634 2024/04/13 04:03:57 - mmengine - INFO - Epoch(train) [7][2550/3111] lr: 2.0000e-04 eta: 7:25:15 time: 1.6528 data_time: 0.1257 memory: 19549 grad_norm: 0.8238 loss: 1.5614 loss_center: 0.6402 loss_bbox: 0.3803 loss_cls: 0.5409 2024/04/13 04:05:20 - mmengine - INFO - Epoch(train) [7][2600/3111] lr: 2.0000e-04 eta: 7:23:52 time: 1.6538 data_time: 0.1473 memory: 15168 grad_norm: 0.8607 loss: 1.5323 loss_center: 0.6073 loss_bbox: 0.4068 loss_cls: 0.5182 2024/04/13 04:06:44 - mmengine - INFO - Epoch(train) [7][2650/3111] lr: 2.0000e-04 eta: 7:22:31 time: 1.6869 data_time: 0.1818 memory: 16704 grad_norm: 0.8352 loss: 1.5348 loss_center: 0.6361 loss_bbox: 0.3690 loss_cls: 0.5296 2024/04/13 04:08:07 - mmengine - INFO - Epoch(train) [7][2700/3111] lr: 2.0000e-04 eta: 7:21:08 time: 1.6649 data_time: 0.0919 memory: 17259 grad_norm: 0.8490 loss: 1.5106 loss_center: 0.5819 loss_bbox: 0.4121 loss_cls: 0.5166 2024/04/13 04:09:31 - mmengine - INFO - Epoch(train) [7][2750/3111] lr: 2.0000e-04 eta: 7:19:46 time: 1.6839 data_time: 0.0684 memory: 13318 grad_norm: 0.8635 loss: 1.6208 loss_center: 0.7146 loss_bbox: 0.3380 loss_cls: 0.5682 2024/04/13 04:10:55 - mmengine - INFO - Epoch(train) [7][2800/3111] lr: 2.0000e-04 eta: 7:18:23 time: 1.6656 data_time: 0.1010 memory: 14053 grad_norm: 0.9335 loss: 1.5022 loss_center: 0.5911 loss_bbox: 0.4086 loss_cls: 0.5025 2024/04/13 04:12:15 - mmengine - INFO - Epoch(train) [7][2850/3111] lr: 2.0000e-04 eta: 7:16:59 time: 1.6139 data_time: 0.1224 memory: 14298 grad_norm: 0.7523 loss: 1.4162 loss_center: 0.5922 loss_bbox: 0.3633 loss_cls: 0.4607 2024/04/13 04:13:43 - mmengine - INFO - Epoch(train) [7][2900/3111] lr: 2.0000e-04 eta: 7:15:40 time: 1.7612 data_time: 0.0632 memory: 13655 grad_norm: 0.8346 loss: 1.5389 loss_center: 0.6081 loss_bbox: 0.4452 loss_cls: 0.4857 2024/04/13 04:15:06 - mmengine - INFO - Epoch(train) [7][2950/3111] lr: 2.0000e-04 eta: 7:14:17 time: 1.6606 data_time: 0.0557 memory: 16715 grad_norm: 0.8743 loss: 1.8366 loss_center: 0.7655 loss_bbox: 0.4238 loss_cls: 0.6472 2024/04/13 04:16:31 - mmengine - INFO - Epoch(train) [7][3000/3111] lr: 2.0000e-04 eta: 7:12:55 time: 1.6875 data_time: 0.0666 memory: 13735 grad_norm: 0.7964 loss: 1.6085 loss_center: 0.6997 loss_bbox: 0.3647 loss_cls: 0.5440 2024/04/13 04:17:53 - mmengine - INFO - Epoch(train) [7][3050/3111] lr: 2.0000e-04 eta: 7:11:32 time: 1.6486 data_time: 0.0709 memory: 15965 grad_norm: 0.8606 loss: 1.6190 loss_center: 0.6924 loss_bbox: 0.3816 loss_cls: 0.5450 2024/04/13 04:19:21 - mmengine - INFO - Epoch(train) [7][3100/3111] lr: 2.0000e-04 eta: 7:10:13 time: 1.7551 data_time: 0.0698 memory: 17789 grad_norm: 0.8928 loss: 1.5635 loss_center: 0.6267 loss_bbox: 0.4101 loss_cls: 0.5267 2024/04/13 04:19:39 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 04:19:39 - mmengine - INFO - Saving checkpoint at 7 epochs 2024/04/13 04:21:13 - mmengine - INFO - Epoch(train) [8][ 50/3111] lr: 2.0000e-04 eta: 7:08:33 time: 1.7026 data_time: 0.1189 memory: 15084 grad_norm: 0.7883 loss: 1.7111 loss_center: 0.7208 loss_bbox: 0.3810 loss_cls: 0.6094 2024/04/13 04:22:38 - mmengine - INFO - Epoch(train) [8][ 100/3111] lr: 2.0000e-04 eta: 7:07:12 time: 1.7124 data_time: 0.0856 memory: 16200 grad_norm: 0.7727 loss: 1.4837 loss_center: 0.6121 loss_bbox: 0.3818 loss_cls: 0.4898 2024/04/13 04:23:57 - mmengine - INFO - Epoch(train) [8][ 150/3111] lr: 2.0000e-04 eta: 7:05:46 time: 1.5705 data_time: 0.0888 memory: 17143 grad_norm: 0.8079 loss: 1.5398 loss_center: 0.6022 loss_bbox: 0.4340 loss_cls: 0.5036 2024/04/13 04:25:21 - mmengine - INFO - Epoch(train) [8][ 200/3111] lr: 2.0000e-04 eta: 7:04:24 time: 1.6956 data_time: 0.2114 memory: 17102 grad_norm: 0.9190 loss: 1.5217 loss_center: 0.6156 loss_bbox: 0.4044 loss_cls: 0.5016 2024/04/13 04:26:00 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 04:26:47 - mmengine - INFO - Epoch(train) [8][ 250/3111] lr: 2.0000e-04 eta: 7:03:03 time: 1.7035 data_time: 0.1671 memory: 17388 grad_norm: 0.8259 loss: 1.5537 loss_center: 0.6026 loss_bbox: 0.4245 loss_cls: 0.5267 2024/04/13 04:28:11 - mmengine - INFO - Epoch(train) [8][ 300/3111] lr: 2.0000e-04 eta: 7:01:41 time: 1.6869 data_time: 0.1515 memory: 16557 grad_norm: 0.8904 loss: 1.5208 loss_center: 0.6705 loss_bbox: 0.3373 loss_cls: 0.5130 2024/04/13 04:29:41 - mmengine - INFO - Epoch(train) [8][ 350/3111] lr: 2.0000e-04 eta: 7:00:23 time: 1.7970 data_time: 0.2133 memory: 15061 grad_norm: 0.8405 loss: 1.3928 loss_center: 0.5535 loss_bbox: 0.3689 loss_cls: 0.4705 2024/04/13 04:30:59 - mmengine - INFO - Epoch(train) [8][ 400/3111] lr: 2.0000e-04 eta: 6:58:56 time: 1.5619 data_time: 0.0580 memory: 12288 grad_norm: 0.8003 loss: 1.5244 loss_center: 0.6638 loss_bbox: 0.3542 loss_cls: 0.5064 2024/04/13 04:32:24 - mmengine - INFO - Epoch(train) [8][ 450/3111] lr: 2.0000e-04 eta: 6:57:35 time: 1.6951 data_time: 0.1664 memory: 14505 grad_norm: 0.8868 loss: 1.5400 loss_center: 0.5977 loss_bbox: 0.4179 loss_cls: 0.5244 2024/04/13 04:33:47 - mmengine - INFO - Epoch(train) [8][ 500/3111] lr: 2.0000e-04 eta: 6:56:12 time: 1.6695 data_time: 0.0735 memory: 16037 grad_norm: 0.8187 loss: 1.5777 loss_center: 0.6055 loss_bbox: 0.4705 loss_cls: 0.5017 2024/04/13 04:35:11 - mmengine - INFO - Epoch(train) [8][ 550/3111] lr: 2.0000e-04 eta: 6:54:50 time: 1.6741 data_time: 0.0741 memory: 15467 grad_norm: 0.8643 loss: 1.6268 loss_center: 0.6372 loss_bbox: 0.4459 loss_cls: 0.5437 2024/04/13 04:36:35 - mmengine - INFO - Epoch(train) [8][ 600/3111] lr: 2.0000e-04 eta: 6:53:28 time: 1.6833 data_time: 0.1004 memory: 13600 grad_norm: 0.8187 loss: 1.4814 loss_center: 0.6238 loss_bbox: 0.3620 loss_cls: 0.4957 2024/04/13 04:37:55 - mmengine - INFO - Epoch(train) [8][ 650/3111] lr: 2.0000e-04 eta: 6:52:03 time: 1.5987 data_time: 0.1478 memory: 16602 grad_norm: 0.7774 loss: 1.6045 loss_center: 0.7095 loss_bbox: 0.3183 loss_cls: 0.5767 2024/04/13 04:39:17 - mmengine - INFO - Epoch(train) [8][ 700/3111] lr: 2.0000e-04 eta: 6:50:39 time: 1.6383 data_time: 0.0969 memory: 16272 grad_norm: 0.7983 loss: 1.5360 loss_center: 0.6437 loss_bbox: 0.3842 loss_cls: 0.5080 2024/04/13 04:40:38 - mmengine - INFO - Epoch(train) [8][ 750/3111] lr: 2.0000e-04 eta: 6:49:15 time: 1.6137 data_time: 0.1286 memory: 19603 grad_norm: 0.7549 loss: 1.6121 loss_center: 0.6481 loss_bbox: 0.4187 loss_cls: 0.5453 2024/04/13 04:41:57 - mmengine - INFO - Epoch(train) [8][ 800/3111] lr: 2.0000e-04 eta: 6:47:50 time: 1.5942 data_time: 0.1228 memory: 18711 grad_norm: 0.8121 loss: 1.5490 loss_center: 0.6509 loss_bbox: 0.3774 loss_cls: 0.5208 2024/04/13 04:43:22 - mmengine - INFO - Epoch(train) [8][ 850/3111] lr: 2.0000e-04 eta: 6:46:28 time: 1.6929 data_time: 0.0591 memory: 13856 grad_norm: 0.7971 loss: 1.6789 loss_center: 0.7891 loss_bbox: 0.3051 loss_cls: 0.5846 2024/04/13 04:44:42 - mmengine - INFO - Epoch(train) [8][ 900/3111] lr: 2.0000e-04 eta: 6:45:03 time: 1.5959 data_time: 0.1249 memory: 18716 grad_norm: 0.8163 loss: 1.4452 loss_center: 0.6108 loss_bbox: 0.3517 loss_cls: 0.4827 2024/04/13 04:46:05 - mmengine - INFO - Epoch(train) [8][ 950/3111] lr: 2.0000e-04 eta: 6:43:40 time: 1.6560 data_time: 0.1581 memory: 15362 grad_norm: 0.7582 loss: 1.5593 loss_center: 0.5974 loss_bbox: 0.4376 loss_cls: 0.5243 2024/04/13 04:47:28 - mmengine - INFO - Epoch(train) [8][1000/3111] lr: 2.0000e-04 eta: 6:42:17 time: 1.6751 data_time: 0.0860 memory: 13975 grad_norm: 0.8132 loss: 1.5591 loss_center: 0.6575 loss_bbox: 0.3738 loss_cls: 0.5278 2024/04/13 04:48:49 - mmengine - INFO - Epoch(train) [8][1050/3111] lr: 2.0000e-04 eta: 6:40:53 time: 1.6111 data_time: 0.1455 memory: 19398 grad_norm: 0.8197 loss: 1.5617 loss_center: 0.6582 loss_bbox: 0.3597 loss_cls: 0.5438 2024/04/13 04:50:14 - mmengine - INFO - Epoch(train) [8][1100/3111] lr: 2.0000e-04 eta: 6:39:31 time: 1.7002 data_time: 0.1237 memory: 16215 grad_norm: 0.8234 loss: 1.5589 loss_center: 0.6235 loss_bbox: 0.4461 loss_cls: 0.4893 2024/04/13 04:51:39 - mmengine - INFO - Epoch(train) [8][1150/3111] lr: 2.0000e-04 eta: 6:38:10 time: 1.6983 data_time: 0.0789 memory: 15155 grad_norm: 0.7481 loss: 1.3718 loss_center: 0.5556 loss_bbox: 0.3526 loss_cls: 0.4636 2024/04/13 04:53:03 - mmengine - INFO - Epoch(train) [8][1200/3111] lr: 2.0000e-04 eta: 6:36:48 time: 1.6873 data_time: 0.2214 memory: 15709 grad_norm: 0.8030 loss: 1.3295 loss_center: 0.5304 loss_bbox: 0.3672 loss_cls: 0.4319 2024/04/13 04:53:42 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 04:54:30 - mmengine - INFO - Epoch(train) [8][1250/3111] lr: 2.0000e-04 eta: 6:35:27 time: 1.7334 data_time: 0.0590 memory: 16049 grad_norm: 0.8367 loss: 1.7021 loss_center: 0.7187 loss_bbox: 0.4135 loss_cls: 0.5699 2024/04/13 04:55:59 - mmengine - INFO - Epoch(train) [8][1300/3111] lr: 2.0000e-04 eta: 6:34:08 time: 1.7750 data_time: 0.1072 memory: 17304 grad_norm: 0.8111 loss: 1.5048 loss_center: 0.6178 loss_bbox: 0.4047 loss_cls: 0.4823 2024/04/13 04:57:23 - mmengine - INFO - Epoch(train) [8][1350/3111] lr: 2.0000e-04 eta: 6:32:46 time: 1.6923 data_time: 0.0725 memory: 14324 grad_norm: 0.8096 loss: 1.6900 loss_center: 0.7379 loss_bbox: 0.3654 loss_cls: 0.5868 2024/04/13 04:58:51 - mmengine - INFO - Epoch(train) [8][1400/3111] lr: 2.0000e-04 eta: 6:31:26 time: 1.7635 data_time: 0.0683 memory: 15701 grad_norm: 0.8434 loss: 1.6619 loss_center: 0.6946 loss_bbox: 0.4189 loss_cls: 0.5485 2024/04/13 05:00:18 - mmengine - INFO - Epoch(train) [8][1450/3111] lr: 2.0000e-04 eta: 6:30:05 time: 1.7327 data_time: 0.0711 memory: 14895 grad_norm: 0.7766 loss: 1.5495 loss_center: 0.6307 loss_bbox: 0.3865 loss_cls: 0.5323 2024/04/13 05:01:40 - mmengine - INFO - Epoch(train) [8][1500/3111] lr: 2.0000e-04 eta: 6:28:42 time: 1.6360 data_time: 0.1242 memory: 15824 grad_norm: 0.8085 loss: 1.6494 loss_center: 0.6738 loss_bbox: 0.4125 loss_cls: 0.5632 2024/04/13 05:03:04 - mmengine - INFO - Epoch(train) [8][1550/3111] lr: 2.0000e-04 eta: 6:27:19 time: 1.6781 data_time: 0.1253 memory: 15993 grad_norm: 0.8258 loss: 1.5562 loss_center: 0.7004 loss_bbox: 0.3268 loss_cls: 0.5289 2024/04/13 05:04:32 - mmengine - INFO - Epoch(train) [8][1600/3111] lr: 2.0000e-04 eta: 6:25:59 time: 1.7561 data_time: 0.1034 memory: 19509 grad_norm: 0.8768 loss: 1.7436 loss_center: 0.7319 loss_bbox: 0.4133 loss_cls: 0.5984 2024/04/13 05:05:52 - mmengine - INFO - Epoch(train) [8][1650/3111] lr: 2.0000e-04 eta: 6:24:35 time: 1.6035 data_time: 0.0662 memory: 13729 grad_norm: 0.7926 loss: 1.6853 loss_center: 0.7186 loss_bbox: 0.3904 loss_cls: 0.5763 2024/04/13 05:07:11 - mmengine - INFO - Epoch(train) [8][1700/3111] lr: 2.0000e-04 eta: 6:23:09 time: 1.5803 data_time: 0.0783 memory: 14205 grad_norm: 0.7476 loss: 1.6486 loss_center: 0.6532 loss_bbox: 0.4460 loss_cls: 0.5495 2024/04/13 05:08:35 - mmengine - INFO - Epoch(train) [8][1750/3111] lr: 2.0000e-04 eta: 6:21:47 time: 1.6902 data_time: 0.0643 memory: 15892 grad_norm: 0.8310 loss: 1.7550 loss_center: 0.7511 loss_bbox: 0.3823 loss_cls: 0.6216 2024/04/13 05:10:00 - mmengine - INFO - Epoch(train) [8][1800/3111] lr: 2.0000e-04 eta: 6:20:25 time: 1.7021 data_time: 0.0753 memory: 15883 grad_norm: 0.7606 loss: 1.6062 loss_center: 0.6927 loss_bbox: 0.3671 loss_cls: 0.5465 2024/04/13 05:11:24 - mmengine - INFO - Epoch(train) [8][1850/3111] lr: 2.0000e-04 eta: 6:19:03 time: 1.6641 data_time: 0.1771 memory: 16556 grad_norm: 0.8507 loss: 1.4945 loss_center: 0.6019 loss_bbox: 0.3814 loss_cls: 0.5112 2024/04/13 05:12:47 - mmengine - INFO - Epoch(train) [8][1900/3111] lr: 2.0000e-04 eta: 6:17:40 time: 1.6736 data_time: 0.0780 memory: 14420 grad_norm: 0.7511 loss: 1.5941 loss_center: 0.6464 loss_bbox: 0.4095 loss_cls: 0.5381 2024/04/13 05:14:10 - mmengine - INFO - Epoch(train) [8][1950/3111] lr: 2.0000e-04 eta: 6:16:17 time: 1.6437 data_time: 0.0765 memory: 14992 grad_norm: 0.7708 loss: 1.3539 loss_center: 0.5900 loss_bbox: 0.3147 loss_cls: 0.4493 2024/04/13 05:15:36 - mmengine - INFO - Epoch(train) [8][2000/3111] lr: 2.0000e-04 eta: 6:14:56 time: 1.7268 data_time: 0.0581 memory: 14170 grad_norm: 0.7730 loss: 1.5538 loss_center: 0.6806 loss_bbox: 0.3387 loss_cls: 0.5345 2024/04/13 05:16:56 - mmengine - INFO - Epoch(train) [8][2050/3111] lr: 2.0000e-04 eta: 6:13:31 time: 1.6024 data_time: 0.1185 memory: 21070 grad_norm: 0.8106 loss: 1.4622 loss_center: 0.6389 loss_bbox: 0.3130 loss_cls: 0.5103 2024/04/13 05:18:25 - mmengine - INFO - Epoch(train) [8][2100/3111] lr: 2.0000e-04 eta: 6:12:11 time: 1.7713 data_time: 0.0613 memory: 13679 grad_norm: 0.8202 loss: 1.4384 loss_center: 0.6205 loss_bbox: 0.3325 loss_cls: 0.4854 2024/04/13 05:19:45 - mmengine - INFO - Epoch(train) [8][2150/3111] lr: 2.0000e-04 eta: 6:10:47 time: 1.6177 data_time: 0.0596 memory: 15600 grad_norm: 0.7552 loss: 1.4520 loss_center: 0.6592 loss_bbox: 0.2866 loss_cls: 0.5062 2024/04/13 05:21:05 - mmengine - INFO - Epoch(train) [8][2200/3111] lr: 2.0000e-04 eta: 6:09:22 time: 1.5836 data_time: 0.0788 memory: 13539 grad_norm: 1.0851 loss: 1.4188 loss_center: 0.6252 loss_bbox: 0.3362 loss_cls: 0.4574 2024/04/13 05:21:43 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 05:22:28 - mmengine - INFO - Epoch(train) [8][2250/3111] lr: 2.0000e-04 eta: 6:07:59 time: 1.6594 data_time: 0.0738 memory: 17248 grad_norm: 0.7713 loss: 1.6048 loss_center: 0.6762 loss_bbox: 0.3759 loss_cls: 0.5527 2024/04/13 05:23:48 - mmengine - INFO - Epoch(train) [8][2300/3111] lr: 2.0000e-04 eta: 6:06:35 time: 1.6114 data_time: 0.0927 memory: 20034 grad_norm: 0.7425 loss: 1.6937 loss_center: 0.7182 loss_bbox: 0.4025 loss_cls: 0.5730 2024/04/13 05:25:10 - mmengine - INFO - Epoch(train) [8][2350/3111] lr: 2.0000e-04 eta: 6:05:11 time: 1.6353 data_time: 0.0842 memory: 16054 grad_norm: 0.8318 loss: 1.4575 loss_center: 0.5994 loss_bbox: 0.3540 loss_cls: 0.5041 2024/04/13 05:26:35 - mmengine - INFO - Epoch(train) [8][2400/3111] lr: 2.0000e-04 eta: 6:03:49 time: 1.7023 data_time: 0.0716 memory: 14413 grad_norm: 0.8464 loss: 1.6158 loss_center: 0.7105 loss_bbox: 0.3369 loss_cls: 0.5684 2024/04/13 05:28:00 - mmengine - INFO - Epoch(train) [8][2450/3111] lr: 2.0000e-04 eta: 6:02:27 time: 1.7013 data_time: 0.0971 memory: 18498 grad_norm: 0.7728 loss: 1.5194 loss_center: 0.5938 loss_bbox: 0.4143 loss_cls: 0.5113 2024/04/13 05:29:32 - mmengine - INFO - Epoch(train) [8][2500/3111] lr: 2.0000e-04 eta: 6:01:09 time: 1.8401 data_time: 0.0641 memory: 18641 grad_norm: 0.7408 loss: 1.6443 loss_center: 0.6562 loss_bbox: 0.4378 loss_cls: 0.5503 2024/04/13 05:30:53 - mmengine - INFO - Epoch(train) [8][2550/3111] lr: 2.0000e-04 eta: 5:59:45 time: 1.6154 data_time: 0.0781 memory: 15305 grad_norm: 0.7226 loss: 1.5197 loss_center: 0.6830 loss_bbox: 0.3286 loss_cls: 0.5081 2024/04/13 05:32:19 - mmengine - INFO - Epoch(train) [8][2600/3111] lr: 2.0000e-04 eta: 5:58:24 time: 1.7255 data_time: 0.0860 memory: 14033 grad_norm: 0.7885 loss: 1.5397 loss_center: 0.6554 loss_bbox: 0.3588 loss_cls: 0.5256 2024/04/13 05:33:41 - mmengine - INFO - Epoch(train) [8][2650/3111] lr: 2.0000e-04 eta: 5:57:00 time: 1.6316 data_time: 0.0943 memory: 14694 grad_norm: 0.8230 loss: 1.4810 loss_center: 0.6412 loss_bbox: 0.3459 loss_cls: 0.4939 2024/04/13 05:35:03 - mmengine - INFO - Epoch(train) [8][2700/3111] lr: 2.0000e-04 eta: 5:55:37 time: 1.6477 data_time: 0.0731 memory: 15733 grad_norm: 0.7900 loss: 1.4033 loss_center: 0.6099 loss_bbox: 0.3289 loss_cls: 0.4646 2024/04/13 05:36:28 - mmengine - INFO - Epoch(train) [8][2750/3111] lr: 2.0000e-04 eta: 5:54:15 time: 1.6974 data_time: 0.1053 memory: 15990 grad_norm: 1.0088 loss: 1.8047 loss_center: 0.7746 loss_bbox: 0.4067 loss_cls: 0.6234 2024/04/13 05:37:50 - mmengine - INFO - Epoch(train) [8][2800/3111] lr: 2.0000e-04 eta: 5:52:51 time: 1.6478 data_time: 0.0952 memory: 14456 grad_norm: 1.0570 loss: 1.4715 loss_center: 0.6202 loss_bbox: 0.3510 loss_cls: 0.5003 2024/04/13 05:39:14 - mmengine - INFO - Epoch(train) [8][2850/3111] lr: 2.0000e-04 eta: 5:51:29 time: 1.6651 data_time: 0.1256 memory: 15628 grad_norm: 0.7932 loss: 1.6988 loss_center: 0.6761 loss_bbox: 0.4658 loss_cls: 0.5569 2024/04/13 05:40:39 - mmengine - INFO - Epoch(train) [8][2900/3111] lr: 2.0000e-04 eta: 5:50:07 time: 1.7151 data_time: 0.1270 memory: 16108 grad_norm: 0.8684 loss: 1.5994 loss_center: 0.6677 loss_bbox: 0.3644 loss_cls: 0.5674 2024/04/13 05:42:02 - mmengine - INFO - Epoch(train) [8][2950/3111] lr: 2.0000e-04 eta: 5:48:44 time: 1.6511 data_time: 0.0823 memory: 17490 grad_norm: 0.7535 loss: 1.5276 loss_center: 0.5845 loss_bbox: 0.4240 loss_cls: 0.5191 2024/04/13 05:43:25 - mmengine - INFO - Epoch(train) [8][3000/3111] lr: 2.0000e-04 eta: 5:47:21 time: 1.6602 data_time: 0.1090 memory: 18156 grad_norm: 0.7998 loss: 1.6009 loss_center: 0.6404 loss_bbox: 0.4629 loss_cls: 0.4976 2024/04/13 05:44:50 - mmengine - INFO - Epoch(train) [8][3050/3111] lr: 2.0000e-04 eta: 5:45:59 time: 1.6986 data_time: 0.2496 memory: 15968 grad_norm: 0.7594 loss: 1.4634 loss_center: 0.6155 loss_bbox: 0.3402 loss_cls: 0.5078 2024/04/13 05:46:12 - mmengine - INFO - Epoch(train) [8][3100/3111] lr: 2.0000e-04 eta: 5:44:35 time: 1.6461 data_time: 0.0937 memory: 15229 grad_norm: 0.8815 loss: 1.5320 loss_center: 0.6673 loss_bbox: 0.3360 loss_cls: 0.5287 2024/04/13 05:46:31 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 05:46:31 - mmengine - INFO - Saving checkpoint at 8 epochs 2024/04/13 05:48:00 - mmengine - INFO - Epoch(train) [9][ 50/3111] lr: 2.0000e-05 eta: 5:42:53 time: 1.6049 data_time: 0.1116 memory: 15431 grad_norm: 0.7577 loss: 1.6562 loss_center: 0.6806 loss_bbox: 0.4017 loss_cls: 0.5739 2024/04/13 05:49:28 - mmengine - INFO - Epoch(train) [9][ 100/3111] lr: 2.0000e-05 eta: 5:41:33 time: 1.7532 data_time: 0.0704 memory: 16397 grad_norm: 0.7549 loss: 1.4725 loss_center: 0.6704 loss_bbox: 0.3330 loss_cls: 0.4691 2024/04/13 05:49:48 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 05:50:49 - mmengine - INFO - Epoch(train) [9][ 150/3111] lr: 2.0000e-05 eta: 5:40:08 time: 1.6193 data_time: 0.1246 memory: 17774 grad_norm: 0.7056 loss: 1.7515 loss_center: 0.6121 loss_bbox: 0.6408 loss_cls: 0.4986 2024/04/13 05:52:10 - mmengine - INFO - Epoch(train) [9][ 200/3111] lr: 2.0000e-05 eta: 5:38:45 time: 1.6313 data_time: 0.1778 memory: 18985 grad_norm: 0.6662 loss: 1.4003 loss_center: 0.5452 loss_bbox: 0.4083 loss_cls: 0.4467 2024/04/13 05:53:31 - mmengine - INFO - Epoch(train) [9][ 250/3111] lr: 2.0000e-05 eta: 5:37:21 time: 1.6142 data_time: 0.1348 memory: 16199 grad_norm: 0.7504 loss: 1.6479 loss_center: 0.6412 loss_bbox: 0.4443 loss_cls: 0.5624 2024/04/13 05:54:53 - mmengine - INFO - Epoch(train) [9][ 300/3111] lr: 2.0000e-05 eta: 5:35:57 time: 1.6351 data_time: 0.0939 memory: 18380 grad_norm: 0.7772 loss: 1.4772 loss_center: 0.6137 loss_bbox: 0.3688 loss_cls: 0.4946 2024/04/13 05:56:17 - mmengine - INFO - Epoch(train) [9][ 350/3111] lr: 2.0000e-05 eta: 5:34:34 time: 1.6750 data_time: 0.0608 memory: 16122 grad_norm: 0.7702 loss: 1.5510 loss_center: 0.6482 loss_bbox: 0.3697 loss_cls: 0.5331 2024/04/13 05:57:44 - mmengine - INFO - Epoch(train) [9][ 400/3111] lr: 2.0000e-05 eta: 5:33:13 time: 1.7362 data_time: 0.1106 memory: 15298 grad_norm: 0.7216 loss: 1.5311 loss_center: 0.6481 loss_bbox: 0.3575 loss_cls: 0.5255 2024/04/13 05:59:08 - mmengine - INFO - Epoch(train) [9][ 450/3111] lr: 2.0000e-05 eta: 5:31:51 time: 1.6927 data_time: 0.1256 memory: 15508 grad_norm: 0.7740 loss: 1.6791 loss_center: 0.6959 loss_bbox: 0.4197 loss_cls: 0.5635 2024/04/13 06:00:32 - mmengine - INFO - Epoch(train) [9][ 500/3111] lr: 2.0000e-05 eta: 5:30:29 time: 1.6818 data_time: 0.1272 memory: 16865 grad_norm: 0.7767 loss: 1.4693 loss_center: 0.6184 loss_bbox: 0.3590 loss_cls: 0.4918 2024/04/13 06:01:59 - mmengine - INFO - Epoch(train) [9][ 550/3111] lr: 2.0000e-05 eta: 5:29:07 time: 1.7247 data_time: 0.2148 memory: 16150 grad_norm: 0.7328 loss: 1.6318 loss_center: 0.6364 loss_bbox: 0.4590 loss_cls: 0.5364 2024/04/13 06:03:22 - mmengine - INFO - Epoch(train) [9][ 600/3111] lr: 2.0000e-05 eta: 5:27:44 time: 1.6607 data_time: 0.0580 memory: 13629 grad_norm: 0.7555 loss: 1.5155 loss_center: 0.6503 loss_bbox: 0.3573 loss_cls: 0.5079 2024/04/13 06:04:41 - mmengine - INFO - Epoch(train) [9][ 650/3111] lr: 2.0000e-05 eta: 5:26:19 time: 1.5801 data_time: 0.0669 memory: 16119 grad_norm: 0.7215 loss: 1.4827 loss_center: 0.6032 loss_bbox: 0.4140 loss_cls: 0.4654 2024/04/13 06:06:06 - mmengine - INFO - Epoch(train) [9][ 700/3111] lr: 2.0000e-05 eta: 5:24:57 time: 1.7015 data_time: 0.0693 memory: 17833 grad_norm: 0.7665 loss: 1.6064 loss_center: 0.6329 loss_bbox: 0.4655 loss_cls: 0.5081 2024/04/13 06:07:29 - mmengine - INFO - Epoch(train) [9][ 750/3111] lr: 2.0000e-05 eta: 5:23:34 time: 1.6675 data_time: 0.0731 memory: 14161 grad_norm: 0.7737 loss: 1.5683 loss_center: 0.6668 loss_bbox: 0.3574 loss_cls: 0.5441 2024/04/13 06:08:51 - mmengine - INFO - Epoch(train) [9][ 800/3111] lr: 2.0000e-05 eta: 5:22:11 time: 1.6452 data_time: 0.1717 memory: 18393 grad_norm: 0.7377 loss: 1.6867 loss_center: 0.6840 loss_bbox: 0.4416 loss_cls: 0.5611 2024/04/13 06:10:15 - mmengine - INFO - Epoch(train) [9][ 850/3111] lr: 2.0000e-05 eta: 5:20:48 time: 1.6681 data_time: 0.1580 memory: 19726 grad_norm: 0.8229 loss: 1.6927 loss_center: 0.6572 loss_bbox: 0.5198 loss_cls: 0.5157 2024/04/13 06:11:40 - mmengine - INFO - Epoch(train) [9][ 900/3111] lr: 2.0000e-05 eta: 5:19:26 time: 1.7146 data_time: 0.0947 memory: 15448 grad_norm: 0.7812 loss: 1.6033 loss_center: 0.6903 loss_bbox: 0.3748 loss_cls: 0.5382 2024/04/13 06:13:03 - mmengine - INFO - Epoch(train) [9][ 950/3111] lr: 2.0000e-05 eta: 5:18:03 time: 1.6440 data_time: 0.0818 memory: 14134 grad_norm: 0.7907 loss: 1.6337 loss_center: 0.7360 loss_bbox: 0.3360 loss_cls: 0.5617 2024/04/13 06:14:25 - mmengine - INFO - Epoch(train) [9][1000/3111] lr: 2.0000e-05 eta: 5:16:40 time: 1.6498 data_time: 0.0998 memory: 14819 grad_norm: 0.7564 loss: 1.4717 loss_center: 0.6156 loss_bbox: 0.3797 loss_cls: 0.4763 2024/04/13 06:15:46 - mmengine - INFO - Epoch(train) [9][1050/3111] lr: 2.0000e-05 eta: 5:15:16 time: 1.6192 data_time: 0.0611 memory: 15420 grad_norm: 0.7532 loss: 1.4837 loss_center: 0.6488 loss_bbox: 0.3532 loss_cls: 0.4818 2024/04/13 06:17:11 - mmengine - INFO - Epoch(train) [9][1100/3111] lr: 2.0000e-05 eta: 5:13:53 time: 1.6874 data_time: 0.0761 memory: 14038 grad_norm: 0.8547 loss: 1.5568 loss_center: 0.6827 loss_bbox: 0.3308 loss_cls: 0.5433 2024/04/13 06:17:31 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 06:18:34 - mmengine - INFO - Epoch(train) [9][1150/3111] lr: 2.0000e-05 eta: 5:12:31 time: 1.6752 data_time: 0.1554 memory: 16472 grad_norm: 0.7084 loss: 1.4415 loss_center: 0.5841 loss_bbox: 0.4039 loss_cls: 0.4535 2024/04/13 06:19:58 - mmengine - INFO - Epoch(train) [9][1200/3111] lr: 2.0000e-05 eta: 5:11:08 time: 1.6652 data_time: 0.1076 memory: 17241 grad_norm: 0.7449 loss: 1.6037 loss_center: 0.6758 loss_bbox: 0.4222 loss_cls: 0.5057 2024/04/13 06:21:20 - mmengine - INFO - Epoch(train) [9][1250/3111] lr: 2.0000e-05 eta: 5:09:45 time: 1.6520 data_time: 0.0678 memory: 17271 grad_norm: 0.7659 loss: 1.4849 loss_center: 0.5839 loss_bbox: 0.4324 loss_cls: 0.4685 2024/04/13 06:22:42 - mmengine - INFO - Epoch(train) [9][1300/3111] lr: 2.0000e-05 eta: 5:08:21 time: 1.6421 data_time: 0.0746 memory: 16032 grad_norm: 0.7522 loss: 1.6843 loss_center: 0.7461 loss_bbox: 0.3729 loss_cls: 0.5652 2024/04/13 06:24:07 - mmengine - INFO - Epoch(train) [9][1350/3111] lr: 2.0000e-05 eta: 5:06:59 time: 1.6896 data_time: 0.2812 memory: 19421 grad_norm: 0.7850 loss: 1.3833 loss_center: 0.5539 loss_bbox: 0.3680 loss_cls: 0.4614 2024/04/13 06:25:29 - mmengine - INFO - Epoch(train) [9][1400/3111] lr: 2.0000e-05 eta: 5:05:35 time: 1.6445 data_time: 0.1296 memory: 15002 grad_norm: 0.7853 loss: 1.5553 loss_center: 0.6900 loss_bbox: 0.3624 loss_cls: 0.5029 2024/04/13 06:26:52 - mmengine - INFO - Epoch(train) [9][1450/3111] lr: 2.0000e-05 eta: 5:04:13 time: 1.6687 data_time: 0.0949 memory: 16149 grad_norm: 0.8526 loss: 1.5854 loss_center: 0.7064 loss_bbox: 0.3636 loss_cls: 0.5155 2024/04/13 06:28:13 - mmengine - INFO - Epoch(train) [9][1500/3111] lr: 2.0000e-05 eta: 5:02:48 time: 1.6053 data_time: 0.1706 memory: 14678 grad_norm: 0.7362 loss: 1.4284 loss_center: 0.6181 loss_bbox: 0.3391 loss_cls: 0.4712 2024/04/13 06:29:35 - mmengine - INFO - Epoch(train) [9][1550/3111] lr: 2.0000e-05 eta: 5:01:25 time: 1.6446 data_time: 0.0570 memory: 16125 grad_norm: 0.7758 loss: 1.5792 loss_center: 0.6597 loss_bbox: 0.3592 loss_cls: 0.5603 2024/04/13 06:30:54 - mmengine - INFO - Epoch(train) [9][1600/3111] lr: 2.0000e-05 eta: 5:00:00 time: 1.5748 data_time: 0.1403 memory: 15780 grad_norm: 0.7625 loss: 1.5287 loss_center: 0.6134 loss_bbox: 0.4131 loss_cls: 0.5022 2024/04/13 06:32:17 - mmengine - INFO - Epoch(train) [9][1650/3111] lr: 2.0000e-05 eta: 4:58:37 time: 1.6632 data_time: 0.1079 memory: 13966 grad_norm: 0.7402 loss: 1.5255 loss_center: 0.6616 loss_bbox: 0.3373 loss_cls: 0.5266 2024/04/13 06:33:41 - mmengine - INFO - Epoch(train) [9][1700/3111] lr: 2.0000e-05 eta: 4:57:15 time: 1.6882 data_time: 0.1483 memory: 19311 grad_norm: 0.7528 loss: 1.4493 loss_center: 0.6018 loss_bbox: 0.3667 loss_cls: 0.4808 2024/04/13 06:34:59 - mmengine - INFO - Epoch(train) [9][1750/3111] lr: 2.0000e-05 eta: 4:55:50 time: 1.5453 data_time: 0.0964 memory: 15478 grad_norm: 0.7319 loss: 1.5189 loss_center: 0.6877 loss_bbox: 0.3241 loss_cls: 0.5071 2024/04/13 06:36:25 - mmengine - INFO - Epoch(train) [9][1800/3111] lr: 2.0000e-05 eta: 4:54:28 time: 1.7313 data_time: 0.0579 memory: 15037 grad_norm: 0.7685 loss: 1.7141 loss_center: 0.7647 loss_bbox: 0.3421 loss_cls: 0.6073 2024/04/13 06:37:48 - mmengine - INFO - Epoch(train) [9][1850/3111] lr: 2.0000e-05 eta: 4:53:05 time: 1.6616 data_time: 0.1020 memory: 20146 grad_norm: 0.7565 loss: 1.5893 loss_center: 0.6842 loss_bbox: 0.4008 loss_cls: 0.5043 2024/04/13 06:39:12 - mmengine - INFO - Epoch(train) [9][1900/3111] lr: 2.0000e-05 eta: 4:51:43 time: 1.6817 data_time: 0.0944 memory: 19621 grad_norm: 0.7587 loss: 1.4801 loss_center: 0.6208 loss_bbox: 0.3731 loss_cls: 0.4863 2024/04/13 06:40:37 - mmengine - INFO - Epoch(train) [9][1950/3111] lr: 2.0000e-05 eta: 4:50:20 time: 1.7032 data_time: 0.2661 memory: 14374 grad_norm: 0.7785 loss: 1.4456 loss_center: 0.6399 loss_bbox: 0.3416 loss_cls: 0.4641 2024/04/13 06:42:02 - mmengine - INFO - Epoch(train) [9][2000/3111] lr: 2.0000e-05 eta: 4:48:58 time: 1.6983 data_time: 0.1514 memory: 15644 grad_norm: 0.7515 loss: 1.3781 loss_center: 0.5372 loss_bbox: 0.3919 loss_cls: 0.4491 2024/04/13 06:43:26 - mmengine - INFO - Epoch(train) [9][2050/3111] lr: 2.0000e-05 eta: 4:47:36 time: 1.6785 data_time: 0.0703 memory: 12777 grad_norm: 0.7946 loss: 1.6275 loss_center: 0.6911 loss_bbox: 0.3878 loss_cls: 0.5486 2024/04/13 06:44:48 - mmengine - INFO - Epoch(train) [9][2100/3111] lr: 2.0000e-05 eta: 4:46:12 time: 1.6421 data_time: 0.0620 memory: 17464 grad_norm: 0.7194 loss: 1.6210 loss_center: 0.7083 loss_bbox: 0.3697 loss_cls: 0.5429 2024/04/13 06:45:08 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 06:46:11 - mmengine - INFO - Epoch(train) [9][2150/3111] lr: 2.0000e-05 eta: 4:44:49 time: 1.6565 data_time: 0.1502 memory: 16690 grad_norm: 0.7382 loss: 1.4756 loss_center: 0.6280 loss_bbox: 0.3897 loss_cls: 0.4579 2024/04/13 06:47:36 - mmengine - INFO - Epoch(train) [9][2200/3111] lr: 2.0000e-05 eta: 4:43:27 time: 1.6917 data_time: 0.1278 memory: 14118 grad_norm: 0.7610 loss: 1.4018 loss_center: 0.5994 loss_bbox: 0.3401 loss_cls: 0.4623 2024/04/13 06:48:59 - mmengine - INFO - Epoch(train) [9][2250/3111] lr: 2.0000e-05 eta: 4:42:04 time: 1.6611 data_time: 0.0802 memory: 16141 grad_norm: 0.7723 loss: 1.6285 loss_center: 0.7074 loss_bbox: 0.3839 loss_cls: 0.5373 2024/04/13 06:50:22 - mmengine - INFO - Epoch(train) [9][2300/3111] lr: 2.0000e-05 eta: 4:40:41 time: 1.6665 data_time: 0.0912 memory: 21126 grad_norm: 0.7699 loss: 1.4903 loss_center: 0.6297 loss_bbox: 0.3586 loss_cls: 0.5020 2024/04/13 06:51:49 - mmengine - INFO - Epoch(train) [9][2350/3111] lr: 2.0000e-05 eta: 4:39:19 time: 1.7321 data_time: 0.0765 memory: 16397 grad_norm: 0.7629 loss: 1.6330 loss_center: 0.7344 loss_bbox: 0.3315 loss_cls: 0.5671 2024/04/13 06:53:17 - mmengine - INFO - Epoch(train) [9][2400/3111] lr: 2.0000e-05 eta: 4:37:58 time: 1.7681 data_time: 0.2296 memory: 16893 grad_norm: 0.9865 loss: 1.6730 loss_center: 0.6333 loss_bbox: 0.5072 loss_cls: 0.5325 2024/04/13 06:54:39 - mmengine - INFO - Epoch(train) [9][2450/3111] lr: 2.0000e-05 eta: 4:36:35 time: 1.6337 data_time: 0.0560 memory: 16413 grad_norm: 0.7284 loss: 1.5056 loss_center: 0.6285 loss_bbox: 0.3940 loss_cls: 0.4831 2024/04/13 06:56:04 - mmengine - INFO - Epoch(train) [9][2500/3111] lr: 2.0000e-05 eta: 4:35:12 time: 1.7005 data_time: 0.0665 memory: 14775 grad_norm: 0.7039 loss: 1.4133 loss_center: 0.6212 loss_bbox: 0.3363 loss_cls: 0.4558 2024/04/13 06:57:29 - mmengine - INFO - Epoch(train) [9][2550/3111] lr: 2.0000e-05 eta: 4:33:50 time: 1.7075 data_time: 0.2122 memory: 14212 grad_norm: 0.7307 loss: 1.4597 loss_center: 0.5985 loss_bbox: 0.3629 loss_cls: 0.4982 2024/04/13 06:58:54 - mmengine - INFO - Epoch(train) [9][2600/3111] lr: 2.0000e-05 eta: 4:32:28 time: 1.6931 data_time: 0.0718 memory: 17495 grad_norm: 0.8043 loss: 1.4376 loss_center: 0.6276 loss_bbox: 0.3600 loss_cls: 0.4500 2024/04/13 07:00:17 - mmengine - INFO - Epoch(train) [9][2650/3111] lr: 2.0000e-05 eta: 4:31:05 time: 1.6647 data_time: 0.1163 memory: 19406 grad_norm: 0.7634 loss: 1.4456 loss_center: 0.6109 loss_bbox: 0.3575 loss_cls: 0.4772 2024/04/13 07:01:41 - mmengine - INFO - Epoch(train) [9][2700/3111] lr: 2.0000e-05 eta: 4:29:42 time: 1.6781 data_time: 0.0758 memory: 16070 grad_norm: 0.7722 loss: 1.5980 loss_center: 0.7088 loss_bbox: 0.3560 loss_cls: 0.5331 2024/04/13 07:03:06 - mmengine - INFO - Epoch(train) [9][2750/3111] lr: 2.0000e-05 eta: 4:28:20 time: 1.6974 data_time: 0.1259 memory: 15636 grad_norm: 0.8448 loss: 1.5447 loss_center: 0.6647 loss_bbox: 0.3815 loss_cls: 0.4984 2024/04/13 07:04:24 - mmengine - INFO - Epoch(train) [9][2800/3111] lr: 2.0000e-05 eta: 4:26:55 time: 1.5612 data_time: 0.1732 memory: 18603 grad_norm: 1.0383 loss: 1.8038 loss_center: 0.6875 loss_bbox: 0.5720 loss_cls: 0.5443 2024/04/13 07:05:44 - mmengine - INFO - Epoch(train) [9][2850/3111] lr: 2.0000e-05 eta: 4:25:31 time: 1.6041 data_time: 0.0656 memory: 19687 grad_norm: 0.6913 loss: 1.5999 loss_center: 0.6834 loss_bbox: 0.3710 loss_cls: 0.5455 2024/04/13 07:07:09 - mmengine - INFO - Epoch(train) [9][2900/3111] lr: 2.0000e-05 eta: 4:24:08 time: 1.7031 data_time: 0.0889 memory: 14345 grad_norm: 0.7548 loss: 1.5898 loss_center: 0.6591 loss_bbox: 0.3920 loss_cls: 0.5387 2024/04/13 07:08:30 - mmengine - INFO - Epoch(train) [9][2950/3111] lr: 2.0000e-05 eta: 4:22:44 time: 1.6044 data_time: 0.1518 memory: 16220 grad_norm: 0.8043 loss: 1.5840 loss_center: 0.6693 loss_bbox: 0.3683 loss_cls: 0.5464 2024/04/13 07:09:50 - mmengine - INFO - Epoch(train) [9][3000/3111] lr: 2.0000e-05 eta: 4:21:20 time: 1.6055 data_time: 0.1620 memory: 15880 grad_norm: 0.7157 loss: 1.4587 loss_center: 0.6413 loss_bbox: 0.3407 loss_cls: 0.4767 2024/04/13 07:11:17 - mmengine - INFO - Epoch(train) [9][3050/3111] lr: 2.0000e-05 eta: 4:19:59 time: 1.7350 data_time: 0.0666 memory: 19988 grad_norm: 0.7732 loss: 1.3909 loss_center: 0.5907 loss_bbox: 0.3297 loss_cls: 0.4705 2024/04/13 07:12:42 - mmengine - INFO - Epoch(train) [9][3100/3111] lr: 2.0000e-05 eta: 4:18:36 time: 1.7066 data_time: 0.0620 memory: 15362 grad_norm: 0.7818 loss: 1.5537 loss_center: 0.7069 loss_bbox: 0.3079 loss_cls: 0.5389 2024/04/13 07:13:02 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 07:13:02 - mmengine - INFO - Saving checkpoint at 9 epochs 2024/04/13 07:13:12 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 07:14:29 - mmengine - INFO - Epoch(train) [10][ 50/3111] lr: 2.0000e-05 eta: 4:16:54 time: 1.5712 data_time: 0.1664 memory: 18606 grad_norm: 0.8156 loss: 1.4100 loss_center: 0.5610 loss_bbox: 0.3977 loss_cls: 0.4513 2024/04/13 07:15:50 - mmengine - INFO - Epoch(train) [10][ 100/3111] lr: 2.0000e-05 eta: 4:15:31 time: 1.6150 data_time: 0.0559 memory: 15848 grad_norm: 0.7907 loss: 1.3648 loss_center: 0.5605 loss_bbox: 0.3618 loss_cls: 0.4424 2024/04/13 07:17:13 - mmengine - INFO - Epoch(train) [10][ 150/3111] lr: 2.0000e-05 eta: 4:14:07 time: 1.6579 data_time: 0.0701 memory: 13852 grad_norm: 0.7461 loss: 1.5651 loss_center: 0.6846 loss_bbox: 0.3531 loss_cls: 0.5274 2024/04/13 07:18:39 - mmengine - INFO - Epoch(train) [10][ 200/3111] lr: 2.0000e-05 eta: 4:12:46 time: 1.7308 data_time: 0.0730 memory: 17544 grad_norm: 0.7877 loss: 1.5687 loss_center: 0.7006 loss_bbox: 0.3253 loss_cls: 0.5427 2024/04/13 07:20:04 - mmengine - INFO - Epoch(train) [10][ 250/3111] lr: 2.0000e-05 eta: 4:11:23 time: 1.7006 data_time: 0.1638 memory: 14743 grad_norm: 0.8008 loss: 1.6548 loss_center: 0.7460 loss_bbox: 0.3225 loss_cls: 0.5863 2024/04/13 07:21:28 - mmengine - INFO - Epoch(train) [10][ 300/3111] lr: 2.0000e-05 eta: 4:10:00 time: 1.6754 data_time: 0.0670 memory: 14312 grad_norm: 0.7446 loss: 1.5425 loss_center: 0.6626 loss_bbox: 0.3862 loss_cls: 0.4937 2024/04/13 07:22:51 - mmengine - INFO - Epoch(train) [10][ 350/3111] lr: 2.0000e-05 eta: 4:08:37 time: 1.6468 data_time: 0.1030 memory: 13607 grad_norm: 0.7444 loss: 1.5336 loss_center: 0.6517 loss_bbox: 0.3770 loss_cls: 0.5049 2024/04/13 07:24:09 - mmengine - INFO - Epoch(train) [10][ 400/3111] lr: 2.0000e-05 eta: 4:07:13 time: 1.5629 data_time: 0.1032 memory: 16742 grad_norm: 0.7722 loss: 1.4540 loss_center: 0.5743 loss_bbox: 0.4234 loss_cls: 0.4564 2024/04/13 07:25:37 - mmengine - INFO - Epoch(train) [10][ 450/3111] lr: 2.0000e-05 eta: 4:05:51 time: 1.7600 data_time: 0.1664 memory: 15781 grad_norm: 0.7423 loss: 1.6450 loss_center: 0.6053 loss_bbox: 0.5444 loss_cls: 0.4953 2024/04/13 07:26:57 - mmengine - INFO - Epoch(train) [10][ 500/3111] lr: 2.0000e-05 eta: 4:04:27 time: 1.6135 data_time: 0.0704 memory: 14302 grad_norm: 0.7657 loss: 1.6267 loss_center: 0.7369 loss_bbox: 0.3400 loss_cls: 0.5498 2024/04/13 07:28:21 - mmengine - INFO - Epoch(train) [10][ 550/3111] lr: 2.0000e-05 eta: 4:03:04 time: 1.6690 data_time: 0.0595 memory: 15000 grad_norm: 0.7586 loss: 1.4056 loss_center: 0.5548 loss_bbox: 0.4578 loss_cls: 0.3930 2024/04/13 07:29:47 - mmengine - INFO - Epoch(train) [10][ 600/3111] lr: 2.0000e-05 eta: 4:01:42 time: 1.7204 data_time: 0.1033 memory: 13891 grad_norm: 0.8561 loss: 1.6101 loss_center: 0.6205 loss_bbox: 0.4846 loss_cls: 0.5050 2024/04/13 07:31:11 - mmengine - INFO - Epoch(train) [10][ 650/3111] lr: 2.0000e-05 eta: 4:00:20 time: 1.6750 data_time: 0.1335 memory: 14913 grad_norm: 0.7486 loss: 1.5592 loss_center: 0.6732 loss_bbox: 0.3365 loss_cls: 0.5495 2024/04/13 07:32:35 - mmengine - INFO - Epoch(train) [10][ 700/3111] lr: 2.0000e-05 eta: 3:58:57 time: 1.6802 data_time: 0.2280 memory: 16423 grad_norm: 0.7518 loss: 1.3973 loss_center: 0.5362 loss_bbox: 0.4048 loss_cls: 0.4563 2024/04/13 07:33:57 - mmengine - INFO - Epoch(train) [10][ 750/3111] lr: 2.0000e-05 eta: 3:57:34 time: 1.6536 data_time: 0.1109 memory: 13880 grad_norm: 0.7703 loss: 1.4902 loss_center: 0.6682 loss_bbox: 0.3125 loss_cls: 0.5096 2024/04/13 07:35:20 - mmengine - INFO - Epoch(train) [10][ 800/3111] lr: 2.0000e-05 eta: 3:56:10 time: 1.6511 data_time: 0.0999 memory: 16379 grad_norm: 0.7597 loss: 1.5280 loss_center: 0.6290 loss_bbox: 0.4251 loss_cls: 0.4739 2024/04/13 07:36:47 - mmengine - INFO - Epoch(train) [10][ 850/3111] lr: 2.0000e-05 eta: 3:54:49 time: 1.7470 data_time: 0.1382 memory: 17752 grad_norm: 0.8149 loss: 1.4369 loss_center: 0.5732 loss_bbox: 0.4109 loss_cls: 0.4528 2024/04/13 07:38:08 - mmengine - INFO - Epoch(train) [10][ 900/3111] lr: 2.0000e-05 eta: 3:53:25 time: 1.6184 data_time: 0.0580 memory: 14911 grad_norm: 0.7529 loss: 1.5207 loss_center: 0.6813 loss_bbox: 0.3357 loss_cls: 0.5037 2024/04/13 07:39:32 - mmengine - INFO - Epoch(train) [10][ 950/3111] lr: 2.0000e-05 eta: 3:52:02 time: 1.6706 data_time: 0.0601 memory: 17125 grad_norm: 0.7505 loss: 1.6573 loss_center: 0.7694 loss_bbox: 0.3319 loss_cls: 0.5559 2024/04/13 07:40:54 - mmengine - INFO - Epoch(train) [10][1000/3111] lr: 2.0000e-05 eta: 3:50:39 time: 1.6525 data_time: 0.0609 memory: 17495 grad_norm: 0.7851 loss: 1.4012 loss_center: 0.6057 loss_bbox: 0.3489 loss_cls: 0.4466 2024/04/13 07:40:56 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 07:42:20 - mmengine - INFO - Epoch(train) [10][1050/3111] lr: 2.0000e-05 eta: 3:49:17 time: 1.7096 data_time: 0.2255 memory: 15826 grad_norm: 0.8046 loss: 1.3990 loss_center: 0.5319 loss_bbox: 0.4322 loss_cls: 0.4349 2024/04/13 07:43:41 - mmengine - INFO - Epoch(train) [10][1100/3111] lr: 2.0000e-05 eta: 3:47:53 time: 1.6323 data_time: 0.0666 memory: 21240 grad_norm: 0.8118 loss: 1.8289 loss_center: 0.6716 loss_bbox: 0.6568 loss_cls: 0.5006 2024/04/13 07:45:02 - mmengine - INFO - Epoch(train) [10][1150/3111] lr: 2.0000e-05 eta: 3:46:29 time: 1.6036 data_time: 0.2780 memory: 12630 grad_norm: 0.7777 loss: 1.4148 loss_center: 0.5539 loss_bbox: 0.4165 loss_cls: 0.4443 2024/04/13 07:46:27 - mmengine - INFO - Epoch(train) [10][1200/3111] lr: 2.0000e-05 eta: 3:45:07 time: 1.7023 data_time: 0.1164 memory: 14765 grad_norm: 0.7745 loss: 1.4845 loss_center: 0.5832 loss_bbox: 0.4105 loss_cls: 0.4908 2024/04/13 07:47:53 - mmengine - INFO - Epoch(train) [10][1250/3111] lr: 2.0000e-05 eta: 3:43:45 time: 1.7183 data_time: 0.2400 memory: 16453 grad_norm: 0.7838 loss: 1.4970 loss_center: 0.6007 loss_bbox: 0.4380 loss_cls: 0.4584 2024/04/13 07:49:18 - mmengine - INFO - Epoch(train) [10][1300/3111] lr: 2.0000e-05 eta: 3:42:22 time: 1.7007 data_time: 0.0964 memory: 14465 grad_norm: 0.8720 loss: 1.5971 loss_center: 0.7257 loss_bbox: 0.3157 loss_cls: 0.5557 2024/04/13 07:50:42 - mmengine - INFO - Epoch(train) [10][1350/3111] lr: 2.0000e-05 eta: 3:40:59 time: 1.6865 data_time: 0.1686 memory: 13433 grad_norm: 0.7480 loss: 1.5050 loss_center: 0.6337 loss_bbox: 0.3686 loss_cls: 0.5027 2024/04/13 07:52:05 - mmengine - INFO - Epoch(train) [10][1400/3111] lr: 2.0000e-05 eta: 3:39:36 time: 1.6546 data_time: 0.1020 memory: 19030 grad_norm: 0.7755 loss: 1.4348 loss_center: 0.6104 loss_bbox: 0.3440 loss_cls: 0.4804 2024/04/13 07:53:27 - mmengine - INFO - Epoch(train) [10][1450/3111] lr: 2.0000e-05 eta: 3:38:13 time: 1.6529 data_time: 0.1301 memory: 16838 grad_norm: 0.7162 loss: 1.5696 loss_center: 0.6841 loss_bbox: 0.3589 loss_cls: 0.5267 2024/04/13 07:54:50 - mmengine - INFO - Epoch(train) [10][1500/3111] lr: 2.0000e-05 eta: 3:36:50 time: 1.6603 data_time: 0.1075 memory: 16097 grad_norm: 0.7969 loss: 1.4525 loss_center: 0.5857 loss_bbox: 0.4030 loss_cls: 0.4638 2024/04/13 07:56:13 - mmengine - INFO - Epoch(train) [10][1550/3111] lr: 2.0000e-05 eta: 3:35:27 time: 1.6469 data_time: 0.0548 memory: 17125 grad_norm: 0.7256 loss: 1.5576 loss_center: 0.6474 loss_bbox: 0.4260 loss_cls: 0.4843 2024/04/13 07:57:35 - mmengine - INFO - Epoch(train) [10][1600/3111] lr: 2.0000e-05 eta: 3:34:04 time: 1.6506 data_time: 0.1154 memory: 18529 grad_norm: 0.7488 loss: 1.3484 loss_center: 0.5436 loss_bbox: 0.3612 loss_cls: 0.4436 2024/04/13 07:58:59 - mmengine - INFO - Epoch(train) [10][1650/3111] lr: 2.0000e-05 eta: 3:32:41 time: 1.6651 data_time: 0.1493 memory: 15465 grad_norm: 0.7389 loss: 1.3521 loss_center: 0.5638 loss_bbox: 0.3669 loss_cls: 0.4214 2024/04/13 08:00:24 - mmengine - INFO - Epoch(train) [10][1700/3111] lr: 2.0000e-05 eta: 3:31:18 time: 1.7172 data_time: 0.1014 memory: 15722 grad_norm: 0.7365 loss: 1.5127 loss_center: 0.6652 loss_bbox: 0.3531 loss_cls: 0.4944 2024/04/13 08:01:50 - mmengine - INFO - Epoch(train) [10][1750/3111] lr: 2.0000e-05 eta: 3:29:56 time: 1.7112 data_time: 0.0870 memory: 14433 grad_norm: 0.7753 loss: 1.5042 loss_center: 0.6710 loss_bbox: 0.3365 loss_cls: 0.4968 2024/04/13 08:03:10 - mmengine - INFO - Epoch(train) [10][1800/3111] lr: 2.0000e-05 eta: 3:28:32 time: 1.6069 data_time: 0.1117 memory: 21379 grad_norm: 0.7817 loss: 1.3900 loss_center: 0.5904 loss_bbox: 0.3413 loss_cls: 0.4583 2024/04/13 08:04:34 - mmengine - INFO - Epoch(train) [10][1850/3111] lr: 2.0000e-05 eta: 3:27:09 time: 1.6654 data_time: 0.1232 memory: 13655 grad_norm: 0.8271 loss: 1.4519 loss_center: 0.6051 loss_bbox: 0.3768 loss_cls: 0.4700 2024/04/13 08:05:55 - mmengine - INFO - Epoch(train) [10][1900/3111] lr: 2.0000e-05 eta: 3:25:46 time: 1.6286 data_time: 0.1462 memory: 15917 grad_norm: 0.7291 loss: 1.4957 loss_center: 0.6091 loss_bbox: 0.4207 loss_cls: 0.4659 2024/04/13 08:07:18 - mmengine - INFO - Epoch(train) [10][1950/3111] lr: 2.0000e-05 eta: 3:24:23 time: 1.6605 data_time: 0.1064 memory: 14880 grad_norm: 0.8218 loss: 1.5816 loss_center: 0.6551 loss_bbox: 0.4195 loss_cls: 0.5071 2024/04/13 08:08:40 - mmengine - INFO - Epoch(train) [10][2000/3111] lr: 2.0000e-05 eta: 3:22:59 time: 1.6310 data_time: 0.2224 memory: 13730 grad_norm: 0.7456 loss: 1.3796 loss_center: 0.5625 loss_bbox: 0.4077 loss_cls: 0.4094 2024/04/13 08:08:41 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 08:10:05 - mmengine - INFO - Epoch(train) [10][2050/3111] lr: 2.0000e-05 eta: 3:21:37 time: 1.6964 data_time: 0.0661 memory: 13930 grad_norm: 0.7677 loss: 1.5855 loss_center: 0.6734 loss_bbox: 0.3800 loss_cls: 0.5320 2024/04/13 08:11:29 - mmengine - INFO - Epoch(train) [10][2100/3111] lr: 2.0000e-05 eta: 3:20:14 time: 1.6959 data_time: 0.0890 memory: 16311 grad_norm: 0.7830 loss: 1.4617 loss_center: 0.6445 loss_bbox: 0.3130 loss_cls: 0.5042 2024/04/13 08:12:53 - mmengine - INFO - Epoch(train) [10][2150/3111] lr: 2.0000e-05 eta: 3:18:51 time: 1.6743 data_time: 0.1075 memory: 17031 grad_norm: 0.8097 loss: 1.3609 loss_center: 0.5934 loss_bbox: 0.3470 loss_cls: 0.4204 2024/04/13 08:14:16 - mmengine - INFO - Epoch(train) [10][2200/3111] lr: 2.0000e-05 eta: 3:17:28 time: 1.6595 data_time: 0.1805 memory: 16102 grad_norm: 0.8877 loss: 1.4493 loss_center: 0.6167 loss_bbox: 0.3649 loss_cls: 0.4677 2024/04/13 08:15:42 - mmengine - INFO - Epoch(train) [10][2250/3111] lr: 2.0000e-05 eta: 3:16:06 time: 1.7176 data_time: 0.0801 memory: 16772 grad_norm: 0.7856 loss: 1.6681 loss_center: 0.6787 loss_bbox: 0.4499 loss_cls: 0.5395 2024/04/13 08:17:02 - mmengine - INFO - Epoch(train) [10][2300/3111] lr: 2.0000e-05 eta: 3:14:42 time: 1.6074 data_time: 0.0977 memory: 14034 grad_norm: 0.7225 loss: 1.6344 loss_center: 0.7503 loss_bbox: 0.3136 loss_cls: 0.5705 2024/04/13 08:18:24 - mmengine - INFO - Epoch(train) [10][2350/3111] lr: 2.0000e-05 eta: 3:13:19 time: 1.6359 data_time: 0.0695 memory: 17225 grad_norm: 0.7715 loss: 1.4418 loss_center: 0.6302 loss_bbox: 0.3371 loss_cls: 0.4746 2024/04/13 08:19:51 - mmengine - INFO - Epoch(train) [10][2400/3111] lr: 2.0000e-05 eta: 3:11:56 time: 1.7399 data_time: 0.0607 memory: 16754 grad_norm: 0.7560 loss: 1.8474 loss_center: 0.6905 loss_bbox: 0.6550 loss_cls: 0.5018 2024/04/13 08:21:11 - mmengine - INFO - Epoch(train) [10][2450/3111] lr: 2.0000e-05 eta: 3:10:33 time: 1.5945 data_time: 0.1070 memory: 14393 grad_norm: 0.7721 loss: 1.6393 loss_center: 0.7478 loss_bbox: 0.3217 loss_cls: 0.5698 2024/04/13 08:22:35 - mmengine - INFO - Epoch(train) [10][2500/3111] lr: 2.0000e-05 eta: 3:09:10 time: 1.6931 data_time: 0.2076 memory: 18426 grad_norm: 0.7345 loss: 1.4852 loss_center: 0.6388 loss_bbox: 0.3497 loss_cls: 0.4966 2024/04/13 08:23:58 - mmengine - INFO - Epoch(train) [10][2550/3111] lr: 2.0000e-05 eta: 3:07:47 time: 1.6538 data_time: 0.1499 memory: 15765 grad_norm: 1.1351 loss: 1.6619 loss_center: 0.7123 loss_bbox: 0.4078 loss_cls: 0.5419 2024/04/13 08:25:20 - mmengine - INFO - Epoch(train) [10][2600/3111] lr: 2.0000e-05 eta: 3:06:23 time: 1.6280 data_time: 0.1725 memory: 14635 grad_norm: 0.7397 loss: 1.5062 loss_center: 0.6241 loss_bbox: 0.3813 loss_cls: 0.5009 2024/04/13 08:26:40 - mmengine - INFO - Epoch(train) [10][2650/3111] lr: 2.0000e-05 eta: 3:05:00 time: 1.6079 data_time: 0.0739 memory: 15922 grad_norm: 0.8051 loss: 1.4893 loss_center: 0.6283 loss_bbox: 0.3739 loss_cls: 0.4871 2024/04/13 08:28:03 - mmengine - INFO - Epoch(train) [10][2700/3111] lr: 2.0000e-05 eta: 3:03:37 time: 1.6512 data_time: 0.1463 memory: 14048 grad_norm: 0.7614 loss: 1.4702 loss_center: 0.6055 loss_bbox: 0.3750 loss_cls: 0.4897 2024/04/13 08:29:29 - mmengine - INFO - Epoch(train) [10][2750/3111] lr: 2.0000e-05 eta: 3:02:14 time: 1.7209 data_time: 0.1793 memory: 18496 grad_norm: 0.7882 loss: 1.4338 loss_center: 0.6339 loss_bbox: 0.3465 loss_cls: 0.4534 2024/04/13 08:30:51 - mmengine - INFO - Epoch(train) [10][2800/3111] lr: 2.0000e-05 eta: 3:00:51 time: 1.6397 data_time: 0.1561 memory: 14834 grad_norm: 0.7470 loss: 1.4208 loss_center: 0.6298 loss_bbox: 0.3304 loss_cls: 0.4606 2024/04/13 08:32:13 - mmengine - INFO - Epoch(train) [10][2850/3111] lr: 2.0000e-05 eta: 2:59:28 time: 1.6464 data_time: 0.1041 memory: 19614 grad_norm: 0.7200 loss: 1.3900 loss_center: 0.5773 loss_bbox: 0.3734 loss_cls: 0.4392 2024/04/13 08:33:36 - mmengine - INFO - Epoch(train) [10][2900/3111] lr: 2.0000e-05 eta: 2:58:05 time: 1.6654 data_time: 0.0631 memory: 15297 grad_norm: 0.7872 loss: 1.5063 loss_center: 0.6562 loss_bbox: 0.3770 loss_cls: 0.4731 2024/04/13 08:34:59 - mmengine - INFO - Epoch(train) [10][2950/3111] lr: 2.0000e-05 eta: 2:56:42 time: 1.6493 data_time: 0.1607 memory: 17598 grad_norm: 0.7570 loss: 1.3608 loss_center: 0.5668 loss_bbox: 0.3761 loss_cls: 0.4179 2024/04/13 08:36:24 - mmengine - INFO - Epoch(train) [10][3000/3111] lr: 2.0000e-05 eta: 2:55:19 time: 1.6980 data_time: 0.0681 memory: 14270 grad_norm: 0.7942 loss: 1.7100 loss_center: 0.7165 loss_bbox: 0.4509 loss_cls: 0.5426 2024/04/13 08:36:25 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 08:37:47 - mmengine - INFO - Epoch(train) [10][3050/3111] lr: 2.0000e-05 eta: 2:53:56 time: 1.6743 data_time: 0.1232 memory: 16502 grad_norm: 0.7476 loss: 1.4909 loss_center: 0.6282 loss_bbox: 0.4035 loss_cls: 0.4592 2024/04/13 08:39:09 - mmengine - INFO - Epoch(train) [10][3100/3111] lr: 2.0000e-05 eta: 2:52:33 time: 1.6429 data_time: 0.0979 memory: 14696 grad_norm: 0.7626 loss: 1.5184 loss_center: 0.6191 loss_bbox: 0.4089 loss_cls: 0.4905 2024/04/13 08:39:30 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 08:39:30 - mmengine - INFO - Saving checkpoint at 10 epochs 2024/04/13 08:41:00 - mmengine - INFO - Epoch(train) [11][ 50/3111] lr: 2.0000e-05 eta: 2:50:52 time: 1.6238 data_time: 0.1285 memory: 17517 grad_norm: 0.7388 loss: 1.5861 loss_center: 0.7015 loss_bbox: 0.3712 loss_cls: 0.5134 2024/04/13 08:42:21 - mmengine - INFO - Epoch(train) [11][ 100/3111] lr: 2.0000e-05 eta: 2:49:28 time: 1.6306 data_time: 0.0937 memory: 16118 grad_norm: 0.7497 loss: 1.4876 loss_center: 0.6593 loss_bbox: 0.3343 loss_cls: 0.4939 2024/04/13 08:43:45 - mmengine - INFO - Epoch(train) [11][ 150/3111] lr: 2.0000e-05 eta: 2:48:05 time: 1.6791 data_time: 0.0714 memory: 17061 grad_norm: 0.8614 loss: 1.4800 loss_center: 0.6001 loss_bbox: 0.4217 loss_cls: 0.4582 2024/04/13 08:45:10 - mmengine - INFO - Epoch(train) [11][ 200/3111] lr: 2.0000e-05 eta: 2:46:43 time: 1.6943 data_time: 0.1376 memory: 16726 grad_norm: 0.7423 loss: 1.6180 loss_center: 0.6804 loss_bbox: 0.4257 loss_cls: 0.5119 2024/04/13 08:46:33 - mmengine - INFO - Epoch(train) [11][ 250/3111] lr: 2.0000e-05 eta: 2:45:20 time: 1.6656 data_time: 0.0846 memory: 16341 grad_norm: 0.8230 loss: 1.4832 loss_center: 0.6528 loss_bbox: 0.3653 loss_cls: 0.4652 2024/04/13 08:47:53 - mmengine - INFO - Epoch(train) [11][ 300/3111] lr: 2.0000e-05 eta: 2:43:56 time: 1.5860 data_time: 0.0827 memory: 15906 grad_norm: 0.7626 loss: 1.5848 loss_center: 0.6662 loss_bbox: 0.4316 loss_cls: 0.4870 2024/04/13 08:49:19 - mmengine - INFO - Epoch(train) [11][ 350/3111] lr: 2.0000e-05 eta: 2:42:33 time: 1.7283 data_time: 0.1024 memory: 19039 grad_norm: 0.7967 loss: 1.5031 loss_center: 0.5897 loss_bbox: 0.3915 loss_cls: 0.5219 2024/04/13 08:50:39 - mmengine - INFO - Epoch(train) [11][ 400/3111] lr: 2.0000e-05 eta: 2:41:10 time: 1.5973 data_time: 0.0920 memory: 12102 grad_norm: 0.7487 loss: 1.5289 loss_center: 0.6512 loss_bbox: 0.3735 loss_cls: 0.5042 2024/04/13 08:52:01 - mmengine - INFO - Epoch(train) [11][ 450/3111] lr: 2.0000e-05 eta: 2:39:46 time: 1.6428 data_time: 0.1126 memory: 15144 grad_norm: 0.8100 loss: 1.6014 loss_center: 0.7202 loss_bbox: 0.3268 loss_cls: 0.5545 2024/04/13 08:53:25 - mmengine - INFO - Epoch(train) [11][ 500/3111] lr: 2.0000e-05 eta: 2:38:24 time: 1.6724 data_time: 0.0572 memory: 12850 grad_norm: 0.7446 loss: 1.5362 loss_center: 0.6893 loss_bbox: 0.3221 loss_cls: 0.5248 2024/04/13 08:54:48 - mmengine - INFO - Epoch(train) [11][ 550/3111] lr: 2.0000e-05 eta: 2:37:01 time: 1.6669 data_time: 0.1057 memory: 18947 grad_norm: 0.7727 loss: 1.5729 loss_center: 0.6218 loss_bbox: 0.4485 loss_cls: 0.5026 2024/04/13 08:56:16 - mmengine - INFO - Epoch(train) [11][ 600/3111] lr: 2.0000e-05 eta: 2:35:38 time: 1.7668 data_time: 0.0665 memory: 16009 grad_norm: 0.7671 loss: 1.6732 loss_center: 0.6757 loss_bbox: 0.4682 loss_cls: 0.5293 2024/04/13 08:57:37 - mmengine - INFO - Epoch(train) [11][ 650/3111] lr: 2.0000e-05 eta: 2:34:15 time: 1.6031 data_time: 0.0688 memory: 13677 grad_norm: 0.8128 loss: 1.6393 loss_center: 0.7284 loss_bbox: 0.3670 loss_cls: 0.5440 2024/04/13 08:59:00 - mmengine - INFO - Epoch(train) [11][ 700/3111] lr: 2.0000e-05 eta: 2:32:52 time: 1.6771 data_time: 0.1744 memory: 17576 grad_norm: 0.8469 loss: 1.3955 loss_center: 0.6131 loss_bbox: 0.3380 loss_cls: 0.4444 2024/04/13 09:00:19 - mmengine - INFO - Epoch(train) [11][ 750/3111] lr: 2.0000e-05 eta: 2:31:28 time: 1.5773 data_time: 0.0789 memory: 15293 grad_norm: 0.7939 loss: 1.3619 loss_center: 0.5372 loss_bbox: 0.4265 loss_cls: 0.3982 2024/04/13 09:01:44 - mmengine - INFO - Epoch(train) [11][ 800/3111] lr: 2.0000e-05 eta: 2:30:05 time: 1.6913 data_time: 0.1392 memory: 19177 grad_norm: 0.8081 loss: 1.3927 loss_center: 0.5653 loss_bbox: 0.3729 loss_cls: 0.4545 2024/04/13 09:03:13 - mmengine - INFO - Epoch(train) [11][ 850/3111] lr: 2.0000e-05 eta: 2:28:43 time: 1.7839 data_time: 0.0676 memory: 16427 grad_norm: 0.7496 loss: 1.4126 loss_center: 0.6178 loss_bbox: 0.3251 loss_cls: 0.4696 2024/04/13 09:04:16 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 09:04:35 - mmengine - INFO - Epoch(train) [11][ 900/3111] lr: 2.0000e-05 eta: 2:27:20 time: 1.6402 data_time: 0.1324 memory: 17029 grad_norm: 0.7571 loss: 1.4336 loss_center: 0.6098 loss_bbox: 0.3672 loss_cls: 0.4566 2024/04/13 09:06:02 - mmengine - INFO - Epoch(train) [11][ 950/3111] lr: 2.0000e-05 eta: 2:25:58 time: 1.7399 data_time: 0.1775 memory: 16474 grad_norm: 0.7816 loss: 1.5600 loss_center: 0.6398 loss_bbox: 0.4059 loss_cls: 0.5143 2024/04/13 09:07:28 - mmengine - INFO - Epoch(train) [11][1000/3111] lr: 2.0000e-05 eta: 2:24:35 time: 1.7078 data_time: 0.1344 memory: 14204 grad_norm: 0.8871 loss: 1.3070 loss_center: 0.5195 loss_bbox: 0.3883 loss_cls: 0.3993 2024/04/13 09:08:50 - mmengine - INFO - Epoch(train) [11][1050/3111] lr: 2.0000e-05 eta: 2:23:12 time: 1.6418 data_time: 0.1354 memory: 14467 grad_norm: 0.7694 loss: 1.3139 loss_center: 0.5447 loss_bbox: 0.3544 loss_cls: 0.4148 2024/04/13 09:10:16 - mmengine - INFO - Epoch(train) [11][1100/3111] lr: 2.0000e-05 eta: 2:21:49 time: 1.7297 data_time: 0.1002 memory: 15788 grad_norm: 0.7489 loss: 1.4450 loss_center: 0.5814 loss_bbox: 0.3955 loss_cls: 0.4681 2024/04/13 09:11:34 - mmengine - INFO - Epoch(train) [11][1150/3111] lr: 2.0000e-05 eta: 2:20:25 time: 1.5597 data_time: 0.0789 memory: 16818 grad_norm: 0.7404 loss: 1.4017 loss_center: 0.6147 loss_bbox: 0.3383 loss_cls: 0.4486 2024/04/13 09:12:55 - mmengine - INFO - Epoch(train) [11][1200/3111] lr: 2.0000e-05 eta: 2:19:02 time: 1.6174 data_time: 0.1221 memory: 15366 grad_norm: 0.8243 loss: 1.4607 loss_center: 0.5916 loss_bbox: 0.3918 loss_cls: 0.4773 2024/04/13 09:14:19 - mmengine - INFO - Epoch(train) [11][1250/3111] lr: 2.0000e-05 eta: 2:17:39 time: 1.6744 data_time: 0.0604 memory: 16287 grad_norm: 0.7542 loss: 1.5712 loss_center: 0.6841 loss_bbox: 0.3662 loss_cls: 0.5209 2024/04/13 09:15:42 - mmengine - INFO - Epoch(train) [11][1300/3111] lr: 2.0000e-05 eta: 2:16:16 time: 1.6553 data_time: 0.0722 memory: 14911 grad_norm: 0.7460 loss: 1.4771 loss_center: 0.6324 loss_bbox: 0.3645 loss_cls: 0.4803 2024/04/13 09:17:04 - mmengine - INFO - Epoch(train) [11][1350/3111] lr: 2.0000e-05 eta: 2:14:53 time: 1.6436 data_time: 0.1311 memory: 18466 grad_norm: 0.8663 loss: 1.8227 loss_center: 0.6733 loss_bbox: 0.6449 loss_cls: 0.5046 2024/04/13 09:18:26 - mmengine - INFO - Epoch(train) [11][1400/3111] lr: 2.0000e-05 eta: 2:13:30 time: 1.6538 data_time: 0.1553 memory: 13992 grad_norm: 0.7241 loss: 1.6332 loss_center: 0.7523 loss_bbox: 0.3729 loss_cls: 0.5080 2024/04/13 09:19:47 - mmengine - INFO - Epoch(train) [11][1450/3111] lr: 2.0000e-05 eta: 2:12:06 time: 1.6186 data_time: 0.0632 memory: 15932 grad_norm: 1.0431 loss: 1.5379 loss_center: 0.6355 loss_bbox: 0.3817 loss_cls: 0.5207 2024/04/13 09:21:10 - mmengine - INFO - Epoch(train) [11][1500/3111] lr: 2.0000e-05 eta: 2:10:43 time: 1.6440 data_time: 0.1218 memory: 17268 grad_norm: 0.7583 loss: 1.5912 loss_center: 0.7409 loss_bbox: 0.3250 loss_cls: 0.5253 2024/04/13 09:22:31 - mmengine - INFO - Epoch(train) [11][1550/3111] lr: 2.0000e-05 eta: 2:09:20 time: 1.6326 data_time: 0.0869 memory: 16091 grad_norm: 0.7791 loss: 1.5663 loss_center: 0.7170 loss_bbox: 0.3328 loss_cls: 0.5164 2024/04/13 09:23:51 - mmengine - INFO - Epoch(train) [11][1600/3111] lr: 2.0000e-05 eta: 2:07:56 time: 1.5870 data_time: 0.0794 memory: 20047 grad_norm: 0.7684 loss: 1.6805 loss_center: 0.6480 loss_bbox: 0.5139 loss_cls: 0.5186 2024/04/13 09:25:09 - mmengine - INFO - Epoch(train) [11][1650/3111] lr: 2.0000e-05 eta: 2:06:33 time: 1.5789 data_time: 0.1127 memory: 14975 grad_norm: 0.8061 loss: 1.5656 loss_center: 0.6792 loss_bbox: 0.3646 loss_cls: 0.5218 2024/04/13 09:26:33 - mmengine - INFO - Epoch(train) [11][1700/3111] lr: 2.0000e-05 eta: 2:05:10 time: 1.6723 data_time: 0.0841 memory: 17334 grad_norm: 0.7347 loss: 1.5610 loss_center: 0.6703 loss_bbox: 0.3782 loss_cls: 0.5125 2024/04/13 09:27:55 - mmengine - INFO - Epoch(train) [11][1750/3111] lr: 2.0000e-05 eta: 2:03:47 time: 1.6443 data_time: 0.1415 memory: 14161 grad_norm: 0.7663 loss: 1.4132 loss_center: 0.5947 loss_bbox: 0.3757 loss_cls: 0.4428 2024/04/13 09:29:20 - mmengine - INFO - Epoch(train) [11][1800/3111] lr: 2.0000e-05 eta: 2:02:24 time: 1.6857 data_time: 0.1439 memory: 15204 grad_norm: 0.7709 loss: 1.4340 loss_center: 0.5649 loss_bbox: 0.3945 loss_cls: 0.4746 2024/04/13 09:30:41 - mmengine - INFO - Epoch(train) [11][1850/3111] lr: 2.0000e-05 eta: 2:01:00 time: 1.6241 data_time: 0.0775 memory: 16244 grad_norm: 0.7390 loss: 1.4133 loss_center: 0.5719 loss_bbox: 0.4003 loss_cls: 0.4411 2024/04/13 09:31:45 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 09:32:00 - mmengine - INFO - Epoch(train) [11][1900/3111] lr: 2.0000e-05 eta: 1:59:37 time: 1.5934 data_time: 0.1511 memory: 15820 grad_norm: 0.7189 loss: 1.4239 loss_center: 0.5648 loss_bbox: 0.4109 loss_cls: 0.4483 2024/04/13 09:33:23 - mmengine - INFO - Epoch(train) [11][1950/3111] lr: 2.0000e-05 eta: 1:58:14 time: 1.6451 data_time: 0.1620 memory: 15495 grad_norm: 0.7853 loss: 1.4906 loss_center: 0.6150 loss_bbox: 0.3705 loss_cls: 0.5051 2024/04/13 09:34:42 - mmengine - INFO - Epoch(train) [11][2000/3111] lr: 2.0000e-05 eta: 1:56:50 time: 1.5828 data_time: 0.1140 memory: 14440 grad_norm: 0.7729 loss: 1.5813 loss_center: 0.6715 loss_bbox: 0.3713 loss_cls: 0.5385 2024/04/13 09:36:06 - mmengine - INFO - Epoch(train) [11][2050/3111] lr: 2.0000e-05 eta: 1:55:27 time: 1.6919 data_time: 0.0709 memory: 14138 grad_norm: 0.7814 loss: 1.5578 loss_center: 0.6686 loss_bbox: 0.3850 loss_cls: 0.5041 2024/04/13 09:37:30 - mmengine - INFO - Epoch(train) [11][2100/3111] lr: 2.0000e-05 eta: 1:54:05 time: 1.6796 data_time: 0.1012 memory: 15879 grad_norm: 0.7563 loss: 1.4345 loss_center: 0.6402 loss_bbox: 0.3211 loss_cls: 0.4732 2024/04/13 09:38:52 - mmengine - INFO - Epoch(train) [11][2150/3111] lr: 2.0000e-05 eta: 1:52:41 time: 1.6323 data_time: 0.0893 memory: 16470 grad_norm: 0.7497 loss: 1.5182 loss_center: 0.6287 loss_bbox: 0.3979 loss_cls: 0.4916 2024/04/13 09:40:11 - mmengine - INFO - Epoch(train) [11][2200/3111] lr: 2.0000e-05 eta: 1:51:18 time: 1.5828 data_time: 0.0956 memory: 13942 grad_norm: 0.7613 loss: 1.4377 loss_center: 0.5667 loss_bbox: 0.4542 loss_cls: 0.4168 2024/04/13 09:41:36 - mmengine - INFO - Epoch(train) [11][2250/3111] lr: 2.0000e-05 eta: 1:49:55 time: 1.6858 data_time: 0.0770 memory: 18007 grad_norm: 0.8169 loss: 1.6801 loss_center: 0.7052 loss_bbox: 0.4379 loss_cls: 0.5371 2024/04/13 09:43:01 - mmengine - INFO - Epoch(train) [11][2300/3111] lr: 2.0000e-05 eta: 1:48:32 time: 1.7012 data_time: 0.1059 memory: 20732 grad_norm: 0.8909 loss: 1.6174 loss_center: 0.6863 loss_bbox: 0.3961 loss_cls: 0.5349 2024/04/13 09:44:25 - mmengine - INFO - Epoch(train) [11][2350/3111] lr: 2.0000e-05 eta: 1:47:09 time: 1.6852 data_time: 0.1205 memory: 16722 grad_norm: 0.7520 loss: 1.4797 loss_center: 0.6351 loss_bbox: 0.3832 loss_cls: 0.4614 2024/04/13 09:45:48 - mmengine - INFO - Epoch(train) [11][2400/3111] lr: 2.0000e-05 eta: 1:45:46 time: 1.6601 data_time: 0.0954 memory: 14706 grad_norm: 0.8310 loss: 1.5186 loss_center: 0.6600 loss_bbox: 0.3568 loss_cls: 0.5018 2024/04/13 09:47:13 - mmengine - INFO - Epoch(train) [11][2450/3111] lr: 2.0000e-05 eta: 1:44:23 time: 1.6939 data_time: 0.1112 memory: 16167 grad_norm: 0.7951 loss: 1.3129 loss_center: 0.5382 loss_bbox: 0.3523 loss_cls: 0.4224 2024/04/13 09:48:38 - mmengine - INFO - Epoch(train) [11][2500/3111] lr: 2.0000e-05 eta: 1:43:01 time: 1.7016 data_time: 0.1117 memory: 17192 grad_norm: 0.8360 loss: 1.2426 loss_center: 0.4754 loss_bbox: 0.4145 loss_cls: 0.3527 2024/04/13 09:49:59 - mmengine - INFO - Epoch(train) [11][2550/3111] lr: 2.0000e-05 eta: 1:41:37 time: 1.6352 data_time: 0.0740 memory: 15423 grad_norm: 0.7697 loss: 1.5891 loss_center: 0.7182 loss_bbox: 0.3233 loss_cls: 0.5476 2024/04/13 09:51:24 - mmengine - INFO - Epoch(train) [11][2600/3111] lr: 2.0000e-05 eta: 1:40:15 time: 1.6953 data_time: 0.1074 memory: 16480 grad_norm: 0.8200 loss: 1.5522 loss_center: 0.6347 loss_bbox: 0.3902 loss_cls: 0.5273 2024/04/13 09:52:51 - mmengine - INFO - Epoch(train) [11][2650/3111] lr: 2.0000e-05 eta: 1:38:52 time: 1.7344 data_time: 0.0794 memory: 16450 grad_norm: 0.8043 loss: 1.6339 loss_center: 0.7202 loss_bbox: 0.3615 loss_cls: 0.5522 2024/04/13 09:54:12 - mmengine - INFO - Epoch(train) [11][2700/3111] lr: 2.0000e-05 eta: 1:37:29 time: 1.6296 data_time: 0.0779 memory: 14906 grad_norm: 0.7983 loss: 1.6124 loss_center: 0.6462 loss_bbox: 0.4368 loss_cls: 0.5294 2024/04/13 09:55:35 - mmengine - INFO - Epoch(train) [11][2750/3111] lr: 2.0000e-05 eta: 1:36:06 time: 1.6441 data_time: 0.1219 memory: 14301 grad_norm: 0.7270 loss: 1.3832 loss_center: 0.6177 loss_bbox: 0.3192 loss_cls: 0.4463 2024/04/13 09:56:58 - mmengine - INFO - Epoch(train) [11][2800/3111] lr: 2.0000e-05 eta: 1:34:43 time: 1.6688 data_time: 0.1741 memory: 17244 grad_norm: 0.8222 loss: 1.7614 loss_center: 0.6967 loss_bbox: 0.5105 loss_cls: 0.5542 2024/04/13 09:58:18 - mmengine - INFO - Epoch(train) [11][2850/3111] lr: 2.0000e-05 eta: 1:33:19 time: 1.6035 data_time: 0.1034 memory: 13362 grad_norm: 0.7773 loss: 1.3924 loss_center: 0.5832 loss_bbox: 0.3714 loss_cls: 0.4379 2024/04/13 09:59:25 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 09:59:42 - mmengine - INFO - Epoch(train) [11][2900/3111] lr: 2.0000e-05 eta: 1:31:56 time: 1.6811 data_time: 0.1557 memory: 14763 grad_norm: 0.8720 loss: 1.5771 loss_center: 0.5849 loss_bbox: 0.5188 loss_cls: 0.4733 2024/04/13 10:01:07 - mmengine - INFO - Epoch(train) [11][2950/3111] lr: 2.0000e-05 eta: 1:30:33 time: 1.6840 data_time: 0.0746 memory: 17702 grad_norm: 0.7894 loss: 1.3722 loss_center: 0.5945 loss_bbox: 0.3614 loss_cls: 0.4164 2024/04/13 10:02:29 - mmengine - INFO - Epoch(train) [11][3000/3111] lr: 2.0000e-05 eta: 1:29:10 time: 1.6500 data_time: 0.1515 memory: 15277 grad_norm: 0.8753 loss: 1.5763 loss_center: 0.6163 loss_bbox: 0.4811 loss_cls: 0.4789 2024/04/13 10:03:50 - mmengine - INFO - Epoch(train) [11][3050/3111] lr: 2.0000e-05 eta: 1:27:47 time: 1.6259 data_time: 0.1420 memory: 15328 grad_norm: 0.7599 loss: 1.4686 loss_center: 0.6139 loss_bbox: 0.3660 loss_cls: 0.4887 2024/04/13 10:05:16 - mmengine - INFO - Epoch(train) [11][3100/3111] lr: 2.0000e-05 eta: 1:26:24 time: 1.7142 data_time: 0.0952 memory: 13506 grad_norm: 0.7986 loss: 1.6630 loss_center: 0.7332 loss_bbox: 0.3931 loss_cls: 0.5367 2024/04/13 10:05:33 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 10:05:33 - mmengine - INFO - Saving checkpoint at 11 epochs 2024/04/13 10:07:05 - mmengine - INFO - Epoch(train) [12][ 50/3111] lr: 2.0000e-06 eta: 1:24:43 time: 1.6614 data_time: 0.0737 memory: 16622 grad_norm: 0.7985 loss: 1.5016 loss_center: 0.6832 loss_bbox: 0.3187 loss_cls: 0.4997 2024/04/13 10:08:28 - mmengine - INFO - Epoch(train) [12][ 100/3111] lr: 2.0000e-06 eta: 1:23:20 time: 1.6586 data_time: 0.1108 memory: 17907 grad_norm: 0.7931 loss: 1.5171 loss_center: 0.6800 loss_bbox: 0.3389 loss_cls: 0.4982 2024/04/13 10:09:52 - mmengine - INFO - Epoch(train) [12][ 150/3111] lr: 2.0000e-06 eta: 1:21:57 time: 1.6819 data_time: 0.0677 memory: 16172 grad_norm: 0.7772 loss: 1.6191 loss_center: 0.7538 loss_bbox: 0.3320 loss_cls: 0.5333 2024/04/13 10:11:15 - mmengine - INFO - Epoch(train) [12][ 200/3111] lr: 2.0000e-06 eta: 1:20:34 time: 1.6610 data_time: 0.0997 memory: 14938 grad_norm: 0.8159 loss: 1.5164 loss_center: 0.6194 loss_bbox: 0.4057 loss_cls: 0.4912 2024/04/13 10:12:41 - mmengine - INFO - Epoch(train) [12][ 250/3111] lr: 2.0000e-06 eta: 1:19:11 time: 1.7103 data_time: 0.0646 memory: 15844 grad_norm: 0.7780 loss: 1.4621 loss_center: 0.6463 loss_bbox: 0.3395 loss_cls: 0.4763 2024/04/13 10:14:02 - mmengine - INFO - Epoch(train) [12][ 300/3111] lr: 2.0000e-06 eta: 1:17:48 time: 1.6163 data_time: 0.1228 memory: 16445 grad_norm: 0.8028 loss: 1.6035 loss_center: 0.6746 loss_bbox: 0.3812 loss_cls: 0.5477 2024/04/13 10:15:25 - mmengine - INFO - Epoch(train) [12][ 350/3111] lr: 2.0000e-06 eta: 1:16:25 time: 1.6593 data_time: 0.0820 memory: 18661 grad_norm: 0.8016 loss: 1.4209 loss_center: 0.6036 loss_bbox: 0.3606 loss_cls: 0.4567 2024/04/13 10:16:46 - mmengine - INFO - Epoch(train) [12][ 400/3111] lr: 2.0000e-06 eta: 1:15:02 time: 1.6386 data_time: 0.0616 memory: 16141 grad_norm: 0.7929 loss: 1.4675 loss_center: 0.6312 loss_bbox: 0.3621 loss_cls: 0.4743 2024/04/13 10:18:14 - mmengine - INFO - Epoch(train) [12][ 450/3111] lr: 2.0000e-06 eta: 1:13:39 time: 1.7414 data_time: 0.1572 memory: 20005 grad_norm: 0.7596 loss: 1.3137 loss_center: 0.5269 loss_bbox: 0.3800 loss_cls: 0.4067 2024/04/13 10:19:34 - mmengine - INFO - Epoch(train) [12][ 500/3111] lr: 2.0000e-06 eta: 1:12:16 time: 1.6150 data_time: 0.0738 memory: 19705 grad_norm: 0.7554 loss: 1.5378 loss_center: 0.6449 loss_bbox: 0.3717 loss_cls: 0.5213 2024/04/13 10:20:57 - mmengine - INFO - Epoch(train) [12][ 550/3111] lr: 2.0000e-06 eta: 1:10:53 time: 1.6512 data_time: 0.1456 memory: 17657 grad_norm: 0.8257 loss: 1.3687 loss_center: 0.6116 loss_bbox: 0.3060 loss_cls: 0.4512 2024/04/13 10:22:15 - mmengine - INFO - Epoch(train) [12][ 600/3111] lr: 2.0000e-06 eta: 1:09:29 time: 1.5699 data_time: 0.0901 memory: 13058 grad_norm: 0.7447 loss: 1.5399 loss_center: 0.7045 loss_bbox: 0.3091 loss_cls: 0.5263 2024/04/13 10:23:41 - mmengine - INFO - Epoch(train) [12][ 650/3111] lr: 2.0000e-06 eta: 1:08:06 time: 1.7049 data_time: 0.1540 memory: 16401 grad_norm: 0.8227 loss: 1.4656 loss_center: 0.6082 loss_bbox: 0.3981 loss_cls: 0.4592 2024/04/13 10:25:00 - mmengine - INFO - Epoch(train) [12][ 700/3111] lr: 2.0000e-06 eta: 1:06:43 time: 1.5916 data_time: 0.0678 memory: 18079 grad_norm: 0.7485 loss: 1.6342 loss_center: 0.7627 loss_bbox: 0.3493 loss_cls: 0.5222 2024/04/13 10:26:22 - mmengine - INFO - Epoch(train) [12][ 750/3111] lr: 2.0000e-06 eta: 1:05:20 time: 1.6331 data_time: 0.1242 memory: 14612 grad_norm: 0.7576 loss: 1.5297 loss_center: 0.6236 loss_bbox: 0.4420 loss_cls: 0.4640 2024/04/13 10:27:13 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 10:27:46 - mmengine - INFO - Epoch(train) [12][ 800/3111] lr: 2.0000e-06 eta: 1:03:57 time: 1.6779 data_time: 0.0790 memory: 14921 grad_norm: 0.7467 loss: 1.4181 loss_center: 0.5954 loss_bbox: 0.3601 loss_cls: 0.4627 2024/04/13 10:29:12 - mmengine - INFO - Epoch(train) [12][ 850/3111] lr: 2.0000e-06 eta: 1:02:34 time: 1.7274 data_time: 0.1350 memory: 15163 grad_norm: 0.8705 loss: 1.6476 loss_center: 0.7375 loss_bbox: 0.3399 loss_cls: 0.5702 2024/04/13 10:30:36 - mmengine - INFO - Epoch(train) [12][ 900/3111] lr: 2.0000e-06 eta: 1:01:11 time: 1.6698 data_time: 0.1854 memory: 16552 grad_norm: 0.7786 loss: 1.5379 loss_center: 0.7121 loss_bbox: 0.2946 loss_cls: 0.5312 2024/04/13 10:32:00 - mmengine - INFO - Epoch(train) [12][ 950/3111] lr: 2.0000e-06 eta: 0:59:48 time: 1.6795 data_time: 0.1435 memory: 16116 grad_norm: 0.8042 loss: 1.6058 loss_center: 0.7019 loss_bbox: 0.3588 loss_cls: 0.5451 2024/04/13 10:33:23 - mmengine - INFO - Epoch(train) [12][1000/3111] lr: 2.0000e-06 eta: 0:58:25 time: 1.6666 data_time: 0.0647 memory: 15372 grad_norm: 0.8145 loss: 1.6691 loss_center: 0.7297 loss_bbox: 0.3860 loss_cls: 0.5534 2024/04/13 10:34:49 - mmengine - INFO - Epoch(train) [12][1050/3111] lr: 2.0000e-06 eta: 0:57:02 time: 1.7279 data_time: 0.1326 memory: 20074 grad_norm: 1.0736 loss: 1.5825 loss_center: 0.7314 loss_bbox: 0.3122 loss_cls: 0.5389 2024/04/13 10:36:14 - mmengine - INFO - Epoch(train) [12][1100/3111] lr: 2.0000e-06 eta: 0:55:39 time: 1.6960 data_time: 0.1313 memory: 16566 grad_norm: 0.7611 loss: 1.6267 loss_center: 0.7254 loss_bbox: 0.3411 loss_cls: 0.5601 2024/04/13 10:37:37 - mmengine - INFO - Epoch(train) [12][1150/3111] lr: 2.0000e-06 eta: 0:54:16 time: 1.6460 data_time: 0.1206 memory: 19559 grad_norm: 0.8395 loss: 1.5799 loss_center: 0.6314 loss_bbox: 0.4435 loss_cls: 0.5050 2024/04/13 10:39:06 - mmengine - INFO - Epoch(train) [12][1200/3111] lr: 2.0000e-06 eta: 0:52:54 time: 1.7820 data_time: 0.0788 memory: 15699 grad_norm: 0.7504 loss: 1.3059 loss_center: 0.5252 loss_bbox: 0.3793 loss_cls: 0.4014 2024/04/13 10:40:33 - mmengine - INFO - Epoch(train) [12][1250/3111] lr: 2.0000e-06 eta: 0:51:31 time: 1.7568 data_time: 0.0566 memory: 21040 grad_norm: 1.2176 loss: 1.5252 loss_center: 0.6579 loss_bbox: 0.3420 loss_cls: 0.5253 2024/04/13 10:41:56 - mmengine - INFO - Epoch(train) [12][1300/3111] lr: 2.0000e-06 eta: 0:50:08 time: 1.6584 data_time: 0.0752 memory: 16000 grad_norm: 0.7657 loss: 1.5397 loss_center: 0.6387 loss_bbox: 0.3945 loss_cls: 0.5066 2024/04/13 10:43:24 - mmengine - INFO - Epoch(train) [12][1350/3111] lr: 2.0000e-06 eta: 0:48:45 time: 1.7484 data_time: 0.1085 memory: 17774 grad_norm: 0.7704 loss: 1.4936 loss_center: 0.6445 loss_bbox: 0.3462 loss_cls: 0.5030 2024/04/13 10:44:50 - mmengine - INFO - Epoch(train) [12][1400/3111] lr: 2.0000e-06 eta: 0:47:22 time: 1.7218 data_time: 0.1586 memory: 17187 grad_norm: 0.7752 loss: 1.5604 loss_center: 0.6978 loss_bbox: 0.3233 loss_cls: 0.5394 2024/04/13 10:46:09 - mmengine - INFO - Epoch(train) [12][1450/3111] lr: 2.0000e-06 eta: 0:45:59 time: 1.5839 data_time: 0.0730 memory: 18669 grad_norm: 0.7386 loss: 1.4936 loss_center: 0.6251 loss_bbox: 0.3821 loss_cls: 0.4864 2024/04/13 10:47:34 - mmengine - INFO - Epoch(train) [12][1500/3111] lr: 2.0000e-06 eta: 0:44:36 time: 1.7018 data_time: 0.1162 memory: 17319 grad_norm: 0.8803 loss: 1.7033 loss_center: 0.7296 loss_bbox: 0.3960 loss_cls: 0.5777 2024/04/13 10:48:55 - mmengine - INFO - Epoch(train) [12][1550/3111] lr: 2.0000e-06 eta: 0:43:13 time: 1.6230 data_time: 0.1258 memory: 14874 grad_norm: 0.8102 loss: 1.5818 loss_center: 0.7052 loss_bbox: 0.3605 loss_cls: 0.5161 2024/04/13 10:50:18 - mmengine - INFO - Epoch(train) [12][1600/3111] lr: 2.0000e-06 eta: 0:41:50 time: 1.6470 data_time: 0.1526 memory: 12498 grad_norm: 0.7789 loss: 1.4925 loss_center: 0.6632 loss_bbox: 0.3317 loss_cls: 0.4976 2024/04/13 10:51:40 - mmengine - INFO - Epoch(train) [12][1650/3111] lr: 2.0000e-06 eta: 0:40:27 time: 1.6420 data_time: 0.1221 memory: 17153 grad_norm: 0.8267 loss: 1.6656 loss_center: 0.5915 loss_bbox: 0.6162 loss_cls: 0.4578 2024/04/13 10:53:07 - mmengine - INFO - Epoch(train) [12][1700/3111] lr: 2.0000e-06 eta: 0:39:04 time: 1.7406 data_time: 0.1348 memory: 15484 grad_norm: 0.7926 loss: 1.6727 loss_center: 0.7215 loss_bbox: 0.4028 loss_cls: 0.5484 2024/04/13 10:54:31 - mmengine - INFO - Epoch(train) [12][1750/3111] lr: 2.0000e-06 eta: 0:37:41 time: 1.6893 data_time: 0.0720 memory: 13834 grad_norm: 0.7533 loss: 1.7293 loss_center: 0.6986 loss_bbox: 0.5010 loss_cls: 0.5297 2024/04/13 10:55:20 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 10:55:54 - mmengine - INFO - Epoch(train) [12][1800/3111] lr: 2.0000e-06 eta: 0:36:18 time: 1.6551 data_time: 0.1193 memory: 17813 grad_norm: 0.9765 loss: 1.5581 loss_center: 0.6258 loss_bbox: 0.4191 loss_cls: 0.5131 2024/04/13 10:57:16 - mmengine - INFO - Epoch(train) [12][1850/3111] lr: 2.0000e-06 eta: 0:34:54 time: 1.6293 data_time: 0.1041 memory: 13609 grad_norm: 0.8561 loss: 1.5051 loss_center: 0.6558 loss_bbox: 0.3514 loss_cls: 0.4979 2024/04/13 10:58:34 - mmengine - INFO - Epoch(train) [12][1900/3111] lr: 2.0000e-06 eta: 0:33:31 time: 1.5706 data_time: 0.1320 memory: 12832 grad_norm: 0.7977 loss: 1.3553 loss_center: 0.5440 loss_bbox: 0.3965 loss_cls: 0.4147 2024/04/13 11:00:01 - mmengine - INFO - Epoch(train) [12][1950/3111] lr: 2.0000e-06 eta: 0:32:08 time: 1.7269 data_time: 0.2367 memory: 16785 grad_norm: 0.7786 loss: 1.5100 loss_center: 0.6479 loss_bbox: 0.3644 loss_cls: 0.4977 2024/04/13 11:01:24 - mmengine - INFO - Epoch(train) [12][2000/3111] lr: 2.0000e-06 eta: 0:30:45 time: 1.6761 data_time: 0.0568 memory: 16364 grad_norm: 0.9265 loss: 1.5284 loss_center: 0.7042 loss_bbox: 0.3007 loss_cls: 0.5235 2024/04/13 11:02:48 - mmengine - INFO - Epoch(train) [12][2050/3111] lr: 2.0000e-06 eta: 0:29:22 time: 1.6737 data_time: 0.0956 memory: 19117 grad_norm: 0.7756 loss: 1.5392 loss_center: 0.6513 loss_bbox: 0.3831 loss_cls: 0.5048 2024/04/13 11:04:13 - mmengine - INFO - Epoch(train) [12][2100/3111] lr: 2.0000e-06 eta: 0:27:59 time: 1.6933 data_time: 0.1439 memory: 14903 grad_norm: 0.7677 loss: 1.4686 loss_center: 0.6512 loss_bbox: 0.3487 loss_cls: 0.4687 2024/04/13 11:05:38 - mmengine - INFO - Epoch(train) [12][2150/3111] lr: 2.0000e-06 eta: 0:26:36 time: 1.6988 data_time: 0.1507 memory: 17568 grad_norm: 0.7667 loss: 1.4783 loss_center: 0.5791 loss_bbox: 0.4294 loss_cls: 0.4699 2024/04/13 11:07:02 - mmengine - INFO - Epoch(train) [12][2200/3111] lr: 2.0000e-06 eta: 0:25:13 time: 1.6837 data_time: 0.0673 memory: 16318 grad_norm: 0.8115 loss: 1.5060 loss_center: 0.6838 loss_bbox: 0.3304 loss_cls: 0.4917 2024/04/13 11:08:23 - mmengine - INFO - Epoch(train) [12][2250/3111] lr: 2.0000e-06 eta: 0:23:50 time: 1.6242 data_time: 0.0639 memory: 21949 grad_norm: 0.7118 loss: 1.4547 loss_center: 0.6258 loss_bbox: 0.3489 loss_cls: 0.4800 2024/04/13 11:09:44 - mmengine - INFO - Epoch(train) [12][2300/3111] lr: 2.0000e-06 eta: 0:22:27 time: 1.6168 data_time: 0.1494 memory: 14766 grad_norm: 0.7073 loss: 1.3334 loss_center: 0.5988 loss_bbox: 0.3181 loss_cls: 0.4164 2024/04/13 11:11:13 - mmengine - INFO - Epoch(train) [12][2350/3111] lr: 2.0000e-06 eta: 0:21:04 time: 1.7825 data_time: 0.1014 memory: 16249 grad_norm: 0.7544 loss: 1.5134 loss_center: 0.6473 loss_bbox: 0.3511 loss_cls: 0.5150 2024/04/13 11:12:39 - mmengine - INFO - Epoch(train) [12][2400/3111] lr: 2.0000e-06 eta: 0:19:41 time: 1.7198 data_time: 0.1178 memory: 15497 grad_norm: 0.7720 loss: 1.5734 loss_center: 0.6954 loss_bbox: 0.3616 loss_cls: 0.5164 2024/04/13 11:14:03 - mmengine - INFO - Epoch(train) [12][2450/3111] lr: 2.0000e-06 eta: 0:18:18 time: 1.6699 data_time: 0.1275 memory: 16315 grad_norm: 0.7723 loss: 1.5148 loss_center: 0.6545 loss_bbox: 0.3656 loss_cls: 0.4947 2024/04/13 11:15:30 - mmengine - INFO - Epoch(train) [12][2500/3111] lr: 2.0000e-06 eta: 0:16:55 time: 1.7479 data_time: 0.1545 memory: 17267 grad_norm: 0.8176 loss: 1.4651 loss_center: 0.6024 loss_bbox: 0.3807 loss_cls: 0.4820 2024/04/13 11:16:55 - mmengine - INFO - Epoch(train) [12][2550/3111] lr: 2.0000e-06 eta: 0:15:32 time: 1.6982 data_time: 0.0714 memory: 21297 grad_norm: 0.8620 loss: 1.7408 loss_center: 0.7935 loss_bbox: 0.3649 loss_cls: 0.5824 2024/04/13 11:18:20 - mmengine - INFO - Epoch(train) [12][2600/3111] lr: 2.0000e-06 eta: 0:14:09 time: 1.6964 data_time: 0.1076 memory: 17263 grad_norm: 0.8764 loss: 1.4443 loss_center: 0.6081 loss_bbox: 0.3622 loss_cls: 0.4739 2024/04/13 11:19:38 - mmengine - INFO - Epoch(train) [12][2650/3111] lr: 2.0000e-06 eta: 0:12:46 time: 1.5730 data_time: 0.0608 memory: 17300 grad_norm: 0.7348 loss: 1.5572 loss_center: 0.6749 loss_bbox: 0.3525 loss_cls: 0.5298 2024/04/13 11:21:00 - mmengine - INFO - Epoch(train) [12][2700/3111] lr: 2.0000e-06 eta: 0:11:22 time: 1.6390 data_time: 0.0755 memory: 14395 grad_norm: 0.7650 loss: 1.4628 loss_center: 0.6247 loss_bbox: 0.3689 loss_cls: 0.4692 2024/04/13 11:22:26 - mmengine - INFO - Epoch(train) [12][2750/3111] lr: 2.0000e-06 eta: 0:09:59 time: 1.7099 data_time: 0.1124 memory: 15534 grad_norm: 0.8313 loss: 1.5265 loss_center: 0.7055 loss_bbox: 0.3067 loss_cls: 0.5142 2024/04/13 11:23:14 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 11:23:49 - mmengine - INFO - Epoch(train) [12][2800/3111] lr: 2.0000e-06 eta: 0:08:36 time: 1.6555 data_time: 0.1604 memory: 14493 grad_norm: 0.7890 loss: 1.6056 loss_center: 0.7024 loss_bbox: 0.3768 loss_cls: 0.5264 2024/04/13 11:25:14 - mmengine - INFO - Epoch(train) [12][2850/3111] lr: 2.0000e-06 eta: 0:07:13 time: 1.7077 data_time: 0.1439 memory: 14949 grad_norm: 0.7935 loss: 1.4855 loss_center: 0.6058 loss_bbox: 0.4062 loss_cls: 0.4735 2024/04/13 11:26:36 - mmengine - INFO - Epoch(train) [12][2900/3111] lr: 2.0000e-06 eta: 0:05:50 time: 1.6462 data_time: 0.1252 memory: 14773 grad_norm: 0.7782 loss: 1.3717 loss_center: 0.5908 loss_bbox: 0.3336 loss_cls: 0.4473 2024/04/13 11:28:00 - mmengine - INFO - Epoch(train) [12][2950/3111] lr: 2.0000e-06 eta: 0:04:27 time: 1.6679 data_time: 0.1301 memory: 14183 grad_norm: 0.8430 loss: 1.5139 loss_center: 0.5544 loss_bbox: 0.5177 loss_cls: 0.4417 2024/04/13 11:29:23 - mmengine - INFO - Epoch(train) [12][3000/3111] lr: 2.0000e-06 eta: 0:03:04 time: 1.6613 data_time: 0.0684 memory: 15753 grad_norm: 1.2172 loss: 1.5228 loss_center: 0.6431 loss_bbox: 0.4165 loss_cls: 0.4632 2024/04/13 11:30:47 - mmengine - INFO - Epoch(train) [12][3050/3111] lr: 2.0000e-06 eta: 0:01:41 time: 1.6867 data_time: 0.0962 memory: 16080 grad_norm: 0.8593 loss: 1.6598 loss_center: 0.6735 loss_bbox: 0.4210 loss_cls: 0.5653 2024/04/13 11:32:13 - mmengine - INFO - Epoch(train) [12][3100/3111] lr: 2.0000e-06 eta: 0:00:18 time: 1.7124 data_time: 0.1642 memory: 15992 grad_norm: 0.8130 loss: 1.2539 loss_center: 0.5177 loss_bbox: 0.3389 loss_cls: 0.3974 2024/04/13 11:32:30 - mmengine - INFO - Exp name: cont-det3d_8xb1_embodiedscan-3d-284class-9dof_20240412_181420 2024/04/13 11:32:30 - mmengine - INFO - Saving checkpoint at 12 epochs 2024/04/13 11:43:00 - mmengine - INFO - Epoch(val) [12][ 50/103] eta: 0:10:57 time: 12.4117 data_time: 0.1733 memory: 33149 2024/04/13 11:53:12 - mmengine - INFO - Epoch(val) [12][100/103] eta: 0:00:36 time: 12.2455 data_time: 0.1152 memory: 37691 2024/04/13 12:21:05 - mmengine - INFO - +---------------------+---------+---------+---------+---------+ | classes | AP_0.25 | AR_0.25 | AP_0.50 | AR_0.50 | +---------------------+---------+---------+---------+---------+ | alarm | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | backpack | 0.3899 | 0.8112 | 0.2108 | 0.5923 | | bag | 0.0123 | 0.5831 | 0.0020 | 0.2276 | | bar | 0.0000 | 0.0052 | 0.0000 | 0.0000 | | barricade | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | basin | 0.0001 | 0.1905 | 0.0000 | 0.0000 | | basket | 0.0325 | 0.7660 | 0.0285 | 0.5426 | | bathtub | 0.8154 | 0.9169 | 0.7665 | 0.8286 | | bed | 0.8716 | 0.9899 | 0.5873 | 0.7827 | | bench | 0.5250 | 1.0000 | 0.5250 | 0.9914 | | bin | 0.5083 | 0.7918 | 0.3685 | 0.6386 | | blackboard | 0.2239 | 0.8245 | 0.0684 | 0.2680 | | blanket | 0.1829 | 0.7683 | 0.0089 | 0.1489 | | board | 0.0011 | 0.9833 | 0.0000 | 0.0000 | | book | 0.0739 | 0.3092 | 0.0151 | 0.0755 | | bottle | 0.0112 | 0.2362 | 0.0000 | 0.0076 | | bowl | 0.0003 | 0.1548 | 0.0000 | 0.0194 | | box | 0.0327 | 0.4653 | 0.0074 | 0.1738 | | brush | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | bucket | 0.0002 | 0.2564 | 0.0000 | 0.0385 | | cabinet | 0.3111 | 0.9216 | 0.1386 | 0.5768 | | carpet | 0.0000 | 0.1667 | 0.0000 | 0.0000 | | cart | 0.0084 | 1.0000 | 0.0058 | 0.8261 | | case | 0.4435 | 0.9625 | 0.2876 | 0.8844 | | chair | 0.7150 | 0.8294 | 0.5358 | 0.6463 | | clock | 0.0391 | 0.2892 | 0.0020 | 0.0723 | | clothes | 0.0660 | 0.5257 | 0.0311 | 0.2198 | | computer | 0.1911 | 0.6648 | 0.1016 | 0.3563 | | container | 0.0055 | 0.7247 | 0.0008 | 0.2865 | | copier | 0.2894 | 0.4000 | 0.0242 | 0.3750 | | couch | 0.5779 | 0.9906 | 0.5191 | 0.7923 | | counter | 0.1385 | 0.3580 | 0.0647 | 0.1289 | | cup | 0.0063 | 0.1608 | 0.0001 | 0.0325 | | curtain | 0.3743 | 0.7608 | 0.0372 | 0.2692 | | decoration | 0.0035 | 0.3470 | 0.0011 | 0.1425 | | desk | 0.6458 | 0.9951 | 0.5197 | 0.8615 | | dispenser | 0.6218 | 0.7863 | 0.1962 | 0.4758 | | door | 0.3875 | 0.8795 | 0.0564 | 0.2622 | | doorframe | 0.4989 | 0.8957 | 0.0629 | 0.4068 | | dresser | 0.1462 | 0.9491 | 0.1425 | 0.8372 | | excercise equipment | 0.0420 | 1.0000 | 0.0045 | 0.6200 | | fan | 0.6298 | 0.6977 | 0.0039 | 0.0698 | | faucet | 0.0001 | 0.0693 | 0.0000 | 0.0000 | | fire extinguisher | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | frame | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | guitar | 0.0443 | 0.6933 | 0.0359 | 0.5467 | | hair dryer | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | hat | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | holder | 0.0000 | 0.0400 | 0.0000 | 0.0000 | | jacket | 0.4424 | 0.7869 | 0.0587 | 0.1944 | | lamp | 0.6275 | 0.8652 | 0.3745 | 0.5502 | | laptop | 0.1518 | 0.3971 | 0.0464 | 0.3141 | | ledge | 0.0274 | 1.0000 | 0.0000 | 0.0400 | | light | 0.2592 | 0.6613 | 0.0033 | 0.0919 | | machine | 0.1356 | 0.9069 | 0.0151 | 0.1152 | | mat | 0.0000 | 0.0120 | 0.0000 | 0.0040 | | microwave | 0.1152 | 0.5929 | 0.0536 | 0.3459 | | mirror | 0.0415 | 0.5718 | 0.0001 | 0.0498 | | monitor | 0.4770 | 0.7197 | 0.0919 | 0.4385 | | paper | 0.0000 | 0.0019 | 0.0000 | 0.0000 | | paper cutter | 0.0878 | 0.9583 | 0.0000 | 0.0000 | | picture | 0.0693 | 0.2637 | 0.0050 | 0.0213 | | pillar | 0.0178 | 0.9070 | 0.0000 | 0.0000 | | pillow | 0.5304 | 0.7603 | 0.2086 | 0.4186 | | pipe | 0.0019 | 0.0829 | 0.0000 | 0.0080 | | plant | 0.2138 | 0.5538 | 0.0458 | 0.2321 | | plate | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | plug | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | plunger | 0.0131 | 0.4626 | 0.0003 | 0.0408 | | poster | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | pot | 0.0000 | 0.0444 | 0.0000 | 0.0000 | | printer | 0.3990 | 0.6871 | 0.0794 | 0.4354 | | purse | 0.0000 | 0.1007 | 0.0000 | 0.0000 | | rack | 0.0027 | 0.8271 | 0.0010 | 0.2632 | | radiator | 0.3796 | 0.7860 | 0.0416 | 0.3253 | | range hood | 0.6311 | 0.7815 | 0.0000 | 0.0000 | | refrigerator | 0.6708 | 0.9009 | 0.3774 | 0.8571 | | shelf | 0.6414 | 0.9031 | 0.3176 | 0.5983 | | shoe | 0.0072 | 0.0248 | 0.0000 | 0.0019 | | shower | 0.0017 | 0.1497 | 0.0015 | 0.1070 | | sign | 0.0016 | 0.2915 | 0.0000 | 0.0237 | | sink | 0.7809 | 0.9159 | 0.4560 | 0.6108 | | soap dispenser | 0.4635 | 0.5789 | 0.2218 | 0.3649 | | socket | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | stall | 0.1596 | 0.9444 | 0.0319 | 0.2778 | | stand | 0.7109 | 0.9641 | 0.6780 | 0.8938 | | stool | 0.3988 | 0.9074 | 0.2519 | 0.7370 | | stopcock | 0.0457 | 0.2294 | 0.0002 | 0.0105 | | stove | 0.4429 | 0.9019 | 0.4332 | 0.7664 | | structure | 0.0001 | 0.1500 | 0.0000 | 0.0800 | | switch | 0.0000 | 0.0012 | 0.0000 | 0.0000 | | table | 0.6411 | 0.9546 | 0.5849 | 0.8711 | | telephone | 0.0039 | 0.0789 | 0.0000 | 0.0034 | | tissue box | 0.0084 | 0.3785 | 0.0002 | 0.1319 | | toaster | 0.0053 | 0.3357 | 0.0000 | 0.0000 | | toilet | 0.9818 | 0.9957 | 0.8909 | 0.9066 | | toilet paper | 0.0984 | 0.3592 | 0.0005 | 0.0351 | | towel | 0.2478 | 0.6462 | 0.1042 | 0.3037 | | toy | 0.0008 | 0.1910 | 0.0000 | 0.0000 | | tube | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | tv | 0.5048 | 0.8747 | 0.1115 | 0.5195 | | vanity | 0.4468 | 0.8632 | 0.3857 | 0.6937 | | wardrobe | 0.0097 | 1.0000 | 0.0017 | 0.4681 | | water cooler | 0.0000 | 0.0600 | 0.0000 | 0.0400 | | window | 0.3933 | 0.9179 | 0.0463 | 0.2645 | | windowsill | 0.0023 | 0.9730 | 0.0000 | 0.0000 | | ball | 0.2364 | 0.7750 | 0.1137 | 0.4700 | | broom | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | mailbox | 0.0162 | 1.0000 | 0.0001 | 0.0400 | | teapot | 0.0073 | 0.5455 | 0.0000 | 0.0227 | | dish rack | 0.0158 | 0.3404 | 0.0000 | 0.0000 | | toothbrush | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | dvd | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | dishwasher | 0.0016 | 0.5455 | 0.0000 | 0.0000 | | fruit | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | keyboard | 0.0211 | 0.0691 | 0.0000 | 0.0063 | | mouse | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | notebook | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | map | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | coffee maker | 0.0001 | 0.1056 | 0.0000 | 0.0000 | | scale | 0.0041 | 0.0667 | 0.0003 | 0.0148 | | eraser | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | toothpaste | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | rod | 0.0002 | 0.0586 | 0.0000 | 0.0000 | | pen | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | scissors | 0.0000 | 0.0000 | 0.0000 | 0.0000 | +---------------------+---------+---------+---------+---------+ | Overall | 0.1783 | 0.4753 | 0.0904 | 0.2304 | +---------------------+---------+---------+---------+---------+ 2024/04/13 12:21:05 - mmengine - INFO - +--------------+---------+---------+---------+---------+ | head_classes | AP_0.25 | AR_0.25 | AP_0.50 | AR_0.50 | +--------------+---------+---------+---------+---------+ | chair | 0.7150 | 0.8294 | 0.5358 | 0.6463 | | picture | 0.0693 | 0.2637 | 0.0050 | 0.0213 | | door | 0.3875 | 0.8795 | 0.0564 | 0.2622 | | pillow | 0.5304 | 0.7603 | 0.2086 | 0.4186 | | cabinet | 0.3111 | 0.9216 | 0.1386 | 0.5768 | | table | 0.6411 | 0.9546 | 0.5849 | 0.8711 | | book | 0.0739 | 0.3092 | 0.0151 | 0.0755 | | window | 0.3933 | 0.9179 | 0.0463 | 0.2645 | | box | 0.0327 | 0.4653 | 0.0074 | 0.1738 | | doorframe | 0.4989 | 0.8957 | 0.0629 | 0.4068 | | shelf | 0.6414 | 0.9031 | 0.3176 | 0.5983 | | light | 0.2592 | 0.6613 | 0.0033 | 0.0919 | | plant | 0.2138 | 0.5538 | 0.0458 | 0.2321 | | paper | 0.0000 | 0.0019 | 0.0000 | 0.0000 | | bin | 0.5083 | 0.7918 | 0.3685 | 0.6386 | | curtain | 0.3743 | 0.7608 | 0.0372 | 0.2692 | | bottle | 0.0112 | 0.2362 | 0.0000 | 0.0076 | | lamp | 0.6275 | 0.8652 | 0.3745 | 0.5502 | | couch | 0.5779 | 0.9906 | 0.5191 | 0.7923 | | towel | 0.2478 | 0.6462 | 0.1042 | 0.3037 | | sink | 0.7809 | 0.9159 | 0.4560 | 0.6108 | | socket | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | clothes | 0.0660 | 0.5257 | 0.0311 | 0.2198 | | desk | 0.6458 | 0.9951 | 0.5197 | 0.8615 | | stand | 0.7109 | 0.9641 | 0.6780 | 0.8938 | | monitor | 0.4770 | 0.7197 | 0.0919 | 0.4385 | | stool | 0.3988 | 0.9074 | 0.2519 | 0.7370 | | mirror | 0.0415 | 0.5718 | 0.0001 | 0.0498 | | case | 0.4435 | 0.9625 | 0.2876 | 0.8844 | | decoration | 0.0035 | 0.3470 | 0.0011 | 0.1425 | | bag | 0.0123 | 0.5831 | 0.0020 | 0.2276 | | bed | 0.8716 | 0.9899 | 0.5873 | 0.7827 | | cup | 0.0063 | 0.1608 | 0.0001 | 0.0325 | | switch | 0.0000 | 0.0012 | 0.0000 | 0.0000 | | shoe | 0.0072 | 0.0248 | 0.0000 | 0.0019 | | toilet | 0.9818 | 0.9957 | 0.8909 | 0.9066 | | counter | 0.1385 | 0.3580 | 0.0647 | 0.1289 | | tv | 0.5048 | 0.8747 | 0.1115 | 0.5195 | | backpack | 0.3899 | 0.8112 | 0.2108 | 0.5923 | | carpet | 0.0000 | 0.1667 | 0.0000 | 0.0000 | | basket | 0.0325 | 0.7660 | 0.0285 | 0.5426 | | blanket | 0.1829 | 0.7683 | 0.0089 | 0.1489 | | blackboard | 0.2239 | 0.8245 | 0.0684 | 0.2680 | | radiator | 0.3796 | 0.7860 | 0.0416 | 0.3253 | | toilet paper | 0.0984 | 0.3592 | 0.0005 | 0.0351 | | bench | 0.5250 | 1.0000 | 0.5250 | 0.9914 | | keyboard | 0.0211 | 0.0691 | 0.0000 | 0.0063 | | board | 0.0011 | 0.9833 | 0.0000 | 0.0000 | | plate | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | refrigerator | 0.6708 | 0.9009 | 0.3774 | 0.8571 | | frame | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | wardrobe | 0.0097 | 1.0000 | 0.0017 | 0.4681 | | telephone | 0.0039 | 0.0789 | 0.0000 | 0.0034 | | computer | 0.1911 | 0.6648 | 0.1016 | 0.3563 | | windowsill | 0.0023 | 0.9730 | 0.0000 | 0.0000 | | bathtub | 0.8154 | 0.9169 | 0.7665 | 0.8286 | | toy | 0.0008 | 0.1910 | 0.0000 | 0.0000 | | rack | 0.0027 | 0.8271 | 0.0010 | 0.2632 | | clock | 0.0391 | 0.2892 | 0.0020 | 0.0723 | | dresser | 0.1462 | 0.9491 | 0.1425 | 0.8372 | | faucet | 0.0001 | 0.0693 | 0.0000 | 0.0000 | | bucket | 0.0002 | 0.2564 | 0.0000 | 0.0385 | | bowl | 0.0003 | 0.1548 | 0.0000 | 0.0194 | | dispenser | 0.6218 | 0.7863 | 0.1962 | 0.4758 | | mouse | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | microwave | 0.1152 | 0.5929 | 0.0536 | 0.3459 | | container | 0.0055 | 0.7247 | 0.0008 | 0.2865 | | stove | 0.4429 | 0.9019 | 0.4332 | 0.7664 | | fan | 0.6298 | 0.6977 | 0.0039 | 0.0698 | | pot | 0.0000 | 0.0444 | 0.0000 | 0.0000 | | shower | 0.0017 | 0.1497 | 0.0015 | 0.1070 | | mat | 0.0000 | 0.0120 | 0.0000 | 0.0040 | | laptop | 0.1518 | 0.3971 | 0.0464 | 0.3141 | | tissue box | 0.0084 | 0.3785 | 0.0002 | 0.1319 | | pillar | 0.0178 | 0.9070 | 0.0000 | 0.0000 | | printer | 0.3990 | 0.6871 | 0.0794 | 0.4354 | +--------------+---------+---------+---------+---------+ | Overall | 0.2544 | 0.5867 | 0.1381 | 0.3188 | +--------------+---------+---------+---------+---------+ 2024/04/13 12:21:05 - mmengine - INFO - +---------------------+---------+---------+---------+---------+ | common_classes | AP_0.25 | AR_0.25 | AP_0.50 | AR_0.50 | +---------------------+---------+---------+---------+---------+ | poster | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | jacket | 0.4424 | 0.7869 | 0.0587 | 0.1944 | | pipe | 0.0019 | 0.0829 | 0.0000 | 0.0080 | | sign | 0.0016 | 0.2915 | 0.0000 | 0.0237 | | vanity | 0.4468 | 0.8632 | 0.3857 | 0.6937 | | soap dispenser | 0.4635 | 0.5789 | 0.2218 | 0.3649 | | rod | 0.0002 | 0.0586 | 0.0000 | 0.0000 | | stopcock | 0.0457 | 0.2294 | 0.0002 | 0.0105 | | bar | 0.0000 | 0.0052 | 0.0000 | 0.0000 | | coffee maker | 0.0001 | 0.1056 | 0.0000 | 0.0000 | | range hood | 0.6311 | 0.7815 | 0.0000 | 0.0000 | | plug | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | alarm | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | purse | 0.0000 | 0.1007 | 0.0000 | 0.0000 | | brush | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | pen | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | ball | 0.2364 | 0.7750 | 0.1137 | 0.4700 | | basin | 0.0001 | 0.1905 | 0.0000 | 0.0000 | | tube | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | stall | 0.1596 | 0.9444 | 0.0319 | 0.2778 | | copier | 0.2894 | 0.4000 | 0.0242 | 0.3750 | | notebook | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | dishwasher | 0.0016 | 0.5455 | 0.0000 | 0.0000 | | teapot | 0.0073 | 0.5455 | 0.0000 | 0.0227 | | hat | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | fire extinguisher | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | scale | 0.0041 | 0.0667 | 0.0003 | 0.0148 | | ledge | 0.0274 | 1.0000 | 0.0000 | 0.0400 | | machine | 0.1356 | 0.9069 | 0.0151 | 0.1152 | | guitar | 0.0443 | 0.6933 | 0.0359 | 0.5467 | | excercise equipment | 0.0420 | 1.0000 | 0.0045 | 0.6200 | | cart | 0.0084 | 1.0000 | 0.0058 | 0.8261 | | paper cutter | 0.0878 | 0.9583 | 0.0000 | 0.0000 | | fruit | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | dish rack | 0.0158 | 0.3404 | 0.0000 | 0.0000 | | hair dryer | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | holder | 0.0000 | 0.0400 | 0.0000 | 0.0000 | +---------------------+---------+---------+---------+---------+ | Overall | 0.0836 | 0.3592 | 0.0243 | 0.1244 | +---------------------+---------+---------+---------+---------+ 2024/04/13 12:21:05 - mmengine - INFO - +--------------+---------+---------+---------+---------+ | tail_classes | AP_0.25 | AR_0.25 | AP_0.50 | AR_0.50 | +--------------+---------+---------+---------+---------+ | mailbox | 0.0162 | 1.0000 | 0.0001 | 0.0400 | | toaster | 0.0053 | 0.3357 | 0.0000 | 0.0000 | | water cooler | 0.0000 | 0.0600 | 0.0000 | 0.0400 | | toothbrush | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | broom | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | plunger | 0.0131 | 0.4626 | 0.0003 | 0.0408 | | toothpaste | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | eraser | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | barricade | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | structure | 0.0001 | 0.1500 | 0.0000 | 0.0800 | | map | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | scissors | 0.0000 | 0.0000 | 0.0000 | 0.0000 | | dvd | 0.0000 | 0.0000 | 0.0000 | 0.0000 | +--------------+---------+---------+---------+---------+ | Overall | 0.0027 | 0.1545 | 0.0000 | 0.0154 | +--------------+---------+---------+---------+---------+ 2024/04/13 12:21:19 - mmengine - INFO - Epoch(val) [12][103/103] alarm_AP_0.25: 0.0000 backpack_AP_0.25: 0.3899 bag_AP_0.25: 0.0123 bar_AP_0.25: 0.0000 barricade_AP_0.25: 0.0000 basin_AP_0.25: 0.0001 basket_AP_0.25: 0.0325 bathtub_AP_0.25: 0.8154 bed_AP_0.25: 0.8716 bench_AP_0.25: 0.5250 bin_AP_0.25: 0.5083 blackboard_AP_0.25: 0.2239 blanket_AP_0.25: 0.1829 board_AP_0.25: 0.0011 book_AP_0.25: 0.0739 bottle_AP_0.25: 0.0112 bowl_AP_0.25: 0.0003 box_AP_0.25: 0.0327 brush_AP_0.25: 0.0000 bucket_AP_0.25: 0.0002 cabinet_AP_0.25: 0.3111 carpet_AP_0.25: 0.0000 cart_AP_0.25: 0.0084 case_AP_0.25: 0.4435 chair_AP_0.25: 0.7150 clock_AP_0.25: 0.0391 clothes_AP_0.25: 0.0660 computer_AP_0.25: 0.1911 container_AP_0.25: 0.0055 copier_AP_0.25: 0.2894 couch_AP_0.25: 0.5779 counter_AP_0.25: 0.1385 cup_AP_0.25: 0.0063 curtain_AP_0.25: 0.3743 decoration_AP_0.25: 0.0035 desk_AP_0.25: 0.6458 dispenser_AP_0.25: 0.6218 door_AP_0.25: 0.3875 doorframe_AP_0.25: 0.4989 dresser_AP_0.25: 0.1462 excercise equipment_AP_0.25: 0.0420 fan_AP_0.25: 0.6298 faucet_AP_0.25: 0.0001 fire extinguisher_AP_0.25: 0.0000 frame_AP_0.25: 0.0000 guitar_AP_0.25: 0.0443 hair dryer_AP_0.25: 0.0000 hat_AP_0.25: 0.0000 holder_AP_0.25: 0.0000 jacket_AP_0.25: 0.4424 lamp_AP_0.25: 0.6275 laptop_AP_0.25: 0.1518 ledge_AP_0.25: 0.0274 light_AP_0.25: 0.2592 machine_AP_0.25: 0.1356 mat_AP_0.25: 0.0000 microwave_AP_0.25: 0.1152 mirror_AP_0.25: 0.0415 monitor_AP_0.25: 0.4770 paper_AP_0.25: 0.0000 paper cutter_AP_0.25: 0.0878 picture_AP_0.25: 0.0693 pillar_AP_0.25: 0.0178 pillow_AP_0.25: 0.5304 pipe_AP_0.25: 0.0019 plant_AP_0.25: 0.2138 plate_AP_0.25: 0.0000 plug_AP_0.25: 0.0000 plunger_AP_0.25: 0.0131 poster_AP_0.25: 0.0000 pot_AP_0.25: 0.0000 printer_AP_0.25: 0.3990 purse_AP_0.25: 0.0000 rack_AP_0.25: 0.0027 radiator_AP_0.25: 0.3796 range hood_AP_0.25: 0.6311 refrigerator_AP_0.25: 0.6708 shelf_AP_0.25: 0.6414 shoe_AP_0.25: 0.0072 shower_AP_0.25: 0.0017 sign_AP_0.25: 0.0016 sink_AP_0.25: 0.7809 soap dispenser_AP_0.25: 0.4635 socket_AP_0.25: 0.0000 stall_AP_0.25: 0.1596 stand_AP_0.25: 0.7109 stool_AP_0.25: 0.3988 stopcock_AP_0.25: 0.0457 stove_AP_0.25: 0.4429 structure_AP_0.25: 0.0001 switch_AP_0.25: 0.0000 table_AP_0.25: 0.6411 telephone_AP_0.25: 0.0039 tissue box_AP_0.25: 0.0084 toaster_AP_0.25: 0.0053 toilet_AP_0.25: 0.9818 toilet paper_AP_0.25: 0.0984 towel_AP_0.25: 0.2478 toy_AP_0.25: 0.0008 tube_AP_0.25: 0.0000 tv_AP_0.25: 0.5048 vanity_AP_0.25: 0.4468 wardrobe_AP_0.25: 0.0097 water cooler_AP_0.25: 0.0000 window_AP_0.25: 0.3933 windowsill_AP_0.25: 0.0023 ball_AP_0.25: 0.2364 broom_AP_0.25: 0.0000 mailbox_AP_0.25: 0.0162 teapot_AP_0.25: 0.0073 dish rack_AP_0.25: 0.0158 toothbrush_AP_0.25: 0.0000 dvd_AP_0.25: 0.0000 dishwasher_AP_0.25: 0.0016 fruit_AP_0.25: 0.0000 keyboard_AP_0.25: 0.0211 mouse_AP_0.25: 0.0000 notebook_AP_0.25: 0.0000 map_AP_0.25: 0.0000 coffee maker_AP_0.25: 0.0001 scale_AP_0.25: 0.0041 eraser_AP_0.25: 0.0000 toothpaste_AP_0.25: 0.0000 rod_AP_0.25: 0.0002 pen_AP_0.25: 0.0000 scissors_AP_0.25: 0.0000 mAP_0.25: 0.1783 alarm_rec_0.25: 0.0000 backpack_rec_0.25: 0.8112 bag_rec_0.25: 0.5831 bar_rec_0.25: 0.0052 barricade_rec_0.25: 0.0000 basin_rec_0.25: 0.1905 basket_rec_0.25: 0.7660 bathtub_rec_0.25: 0.9169 bed_rec_0.25: 0.9899 bench_rec_0.25: 1.0000 bin_rec_0.25: 0.7918 blackboard_rec_0.25: 0.8245 blanket_rec_0.25: 0.7683 board_rec_0.25: 0.9833 book_rec_0.25: 0.3092 bottle_rec_0.25: 0.2362 bowl_rec_0.25: 0.1548 box_rec_0.25: 0.4653 brush_rec_0.25: 0.0000 bucket_rec_0.25: 0.2564 cabinet_rec_0.25: 0.9216 carpet_rec_0.25: 0.1667 cart_rec_0.25: 1.0000 case_rec_0.25: 0.9625 chair_rec_0.25: 0.8294 clock_rec_0.25: 0.2892 clothes_rec_0.25: 0.5257 computer_rec_0.25: 0.6648 container_rec_0.25: 0.7247 copier_rec_0.25: 0.4000 couch_rec_0.25: 0.9906 counter_rec_0.25: 0.3580 cup_rec_0.25: 0.1608 curtain_rec_0.25: 0.7608 decoration_rec_0.25: 0.3470 desk_rec_0.25: 0.9951 dispenser_rec_0.25: 0.7863 door_rec_0.25: 0.8795 doorframe_rec_0.25: 0.8957 dresser_rec_0.25: 0.9491 excercise equipment_rec_0.25: 1.0000 fan_rec_0.25: 0.6977 faucet_rec_0.25: 0.0693 fire extinguisher_rec_0.25: 0.0000 frame_rec_0.25: 0.0000 guitar_rec_0.25: 0.6933 hair dryer_rec_0.25: 0.0000 hat_rec_0.25: 0.0000 holder_rec_0.25: 0.0400 jacket_rec_0.25: 0.7869 lamp_rec_0.25: 0.8652 laptop_rec_0.25: 0.3971 ledge_rec_0.25: 1.0000 light_rec_0.25: 0.6613 machine_rec_0.25: 0.9069 mat_rec_0.25: 0.0120 microwave_rec_0.25: 0.5929 mirror_rec_0.25: 0.5718 monitor_rec_0.25: 0.7197 paper_rec_0.25: 0.0019 paper cutter_rec_0.25: 0.9583 picture_rec_0.25: 0.2637 pillar_rec_0.25: 0.9070 pillow_rec_0.25: 0.7603 pipe_rec_0.25: 0.0829 plant_rec_0.25: 0.5538 plate_rec_0.25: 0.0000 plug_rec_0.25: 0.0000 plunger_rec_0.25: 0.4626 poster_rec_0.25: 0.0000 pot_rec_0.25: 0.0444 printer_rec_0.25: 0.6871 purse_rec_0.25: 0.1007 rack_rec_0.25: 0.8271 radiator_rec_0.25: 0.7860 range hood_rec_0.25: 0.7815 refrigerator_rec_0.25: 0.9009 shelf_rec_0.25: 0.9031 shoe_rec_0.25: 0.0248 shower_rec_0.25: 0.1497 sign_rec_0.25: 0.2915 sink_rec_0.25: 0.9159 soap dispenser_rec_0.25: 0.5789 socket_rec_0.25: 0.0000 stall_rec_0.25: 0.9444 stand_rec_0.25: 0.9641 stool_rec_0.25: 0.9074 stopcock_rec_0.25: 0.2294 stove_rec_0.25: 0.9019 structure_rec_0.25: 0.1500 switch_rec_0.25: 0.0012 table_rec_0.25: 0.9546 telephone_rec_0.25: 0.0789 tissue box_rec_0.25: 0.3785 toaster_rec_0.25: 0.3357 toilet_rec_0.25: 0.9957 toilet paper_rec_0.25: 0.3592 towel_rec_0.25: 0.6462 toy_rec_0.25: 0.1910 tube_rec_0.25: 0.0000 tv_rec_0.25: 0.8747 vanity_rec_0.25: 0.8632 wardrobe_rec_0.25: 1.0000 water cooler_rec_0.25: 0.0600 window_rec_0.25: 0.9179 windowsill_rec_0.25: 0.9730 ball_rec_0.25: 0.7750 broom_rec_0.25: 0.0000 mailbox_rec_0.25: 1.0000 teapot_rec_0.25: 0.5455 dish rack_rec_0.25: 0.3404 toothbrush_rec_0.25: 0.0000 dvd_rec_0.25: 0.0000 dishwasher_rec_0.25: 0.5455 fruit_rec_0.25: 0.0000 keyboard_rec_0.25: 0.0691 mouse_rec_0.25: 0.0000 notebook_rec_0.25: 0.0000 map_rec_0.25: 0.0000 coffee maker_rec_0.25: 0.1056 scale_rec_0.25: 0.0667 eraser_rec_0.25: 0.0000 toothpaste_rec_0.25: 0.0000 rod_rec_0.25: 0.0586 pen_rec_0.25: 0.0000 scissors_rec_0.25: 0.0000 mAR_0.25: 0.4753 alarm_AP_0.50: 0.0000 backpack_AP_0.50: 0.2108 bag_AP_0.50: 0.0020 bar_AP_0.50: 0.0000 barricade_AP_0.50: 0.0000 basin_AP_0.50: 0.0000 basket_AP_0.50: 0.0285 bathtub_AP_0.50: 0.7665 bed_AP_0.50: 0.5873 bench_AP_0.50: 0.5250 bin_AP_0.50: 0.3685 blackboard_AP_0.50: 0.0684 blanket_AP_0.50: 0.0089 board_AP_0.50: 0.0000 book_AP_0.50: 0.0151 bottle_AP_0.50: 0.0000 bowl_AP_0.50: 0.0000 box_AP_0.50: 0.0074 brush_AP_0.50: 0.0000 bucket_AP_0.50: 0.0000 cabinet_AP_0.50: 0.1386 carpet_AP_0.50: 0.0000 cart_AP_0.50: 0.0058 case_AP_0.50: 0.2876 chair_AP_0.50: 0.5358 clock_AP_0.50: 0.0020 clothes_AP_0.50: 0.0311 computer_AP_0.50: 0.1016 container_AP_0.50: 0.0008 copier_AP_0.50: 0.0242 couch_AP_0.50: 0.5191 counter_AP_0.50: 0.0647 cup_AP_0.50: 0.0001 curtain_AP_0.50: 0.0372 decoration_AP_0.50: 0.0011 desk_AP_0.50: 0.5197 dispenser_AP_0.50: 0.1962 door_AP_0.50: 0.0564 doorframe_AP_0.50: 0.0629 dresser_AP_0.50: 0.1425 excercise equipment_AP_0.50: 0.0045 fan_AP_0.50: 0.0039 faucet_AP_0.50: 0.0000 fire extinguisher_AP_0.50: 0.0000 frame_AP_0.50: 0.0000 guitar_AP_0.50: 0.0359 hair dryer_AP_0.50: 0.0000 hat_AP_0.50: 0.0000 holder_AP_0.50: 0.0000 jacket_AP_0.50: 0.0587 lamp_AP_0.50: 0.3745 laptop_AP_0.50: 0.0464 ledge_AP_0.50: 0.0000 light_AP_0.50: 0.0033 machine_AP_0.50: 0.0151 mat_AP_0.50: 0.0000 microwave_AP_0.50: 0.0536 mirror_AP_0.50: 0.0001 monitor_AP_0.50: 0.0919 paper_AP_0.50: 0.0000 paper cutter_AP_0.50: 0.0000 picture_AP_0.50: 0.0050 pillar_AP_0.50: 0.0000 pillow_AP_0.50: 0.2086 pipe_AP_0.50: 0.0000 plant_AP_0.50: 0.0458 plate_AP_0.50: 0.0000 plug_AP_0.50: 0.0000 plunger_AP_0.50: 0.0003 poster_AP_0.50: 0.0000 pot_AP_0.50: 0.0000 printer_AP_0.50: 0.0794 purse_AP_0.50: 0.0000 rack_AP_0.50: 0.0010 radiator_AP_0.50: 0.0416 range hood_AP_0.50: 0.0000 refrigerator_AP_0.50: 0.3774 shelf_AP_0.50: 0.3176 shoe_AP_0.50: 0.0000 shower_AP_0.50: 0.0015 sign_AP_0.50: 0.0000 sink_AP_0.50: 0.4560 soap dispenser_AP_0.50: 0.2218 socket_AP_0.50: 0.0000 stall_AP_0.50: 0.0319 stand_AP_0.50: 0.6780 stool_AP_0.50: 0.2519 stopcock_AP_0.50: 0.0002 stove_AP_0.50: 0.4332 structure_AP_0.50: 0.0000 switch_AP_0.50: 0.0000 table_AP_0.50: 0.5849 telephone_AP_0.50: 0.0000 tissue box_AP_0.50: 0.0002 toaster_AP_0.50: 0.0000 toilet_AP_0.50: 0.8909 toilet paper_AP_0.50: 0.0005 towel_AP_0.50: 0.1042 toy_AP_0.50: 0.0000 tube_AP_0.50: 0.0000 tv_AP_0.50: 0.1115 vanity_AP_0.50: 0.3857 wardrobe_AP_0.50: 0.0017 water cooler_AP_0.50: 0.0000 window_AP_0.50: 0.0463 windowsill_AP_0.50: 0.0000 ball_AP_0.50: 0.1137 broom_AP_0.50: 0.0000 mailbox_AP_0.50: 0.0001 teapot_AP_0.50: 0.0000 dish rack_AP_0.50: 0.0000 toothbrush_AP_0.50: 0.0000 dvd_AP_0.50: 0.0000 dishwasher_AP_0.50: 0.0000 fruit_AP_0.50: 0.0000 keyboard_AP_0.50: 0.0000 mouse_AP_0.50: 0.0000 notebook_AP_0.50: 0.0000 map_AP_0.50: 0.0000 coffee maker_AP_0.50: 0.0000 scale_AP_0.50: 0.0003 eraser_AP_0.50: 0.0000 toothpaste_AP_0.50: 0.0000 rod_AP_0.50: 0.0000 pen_AP_0.50: 0.0000 scissors_AP_0.50: 0.0000 mAP_0.50: 0.0904 alarm_rec_0.50: 0.0000 backpack_rec_0.50: 0.5923 bag_rec_0.50: 0.2276 bar_rec_0.50: 0.0000 barricade_rec_0.50: 0.0000 basin_rec_0.50: 0.0000 basket_rec_0.50: 0.5426 bathtub_rec_0.50: 0.8286 bed_rec_0.50: 0.7827 bench_rec_0.50: 0.9914 bin_rec_0.50: 0.6386 blackboard_rec_0.50: 0.2680 blanket_rec_0.50: 0.1489 board_rec_0.50: 0.0000 book_rec_0.50: 0.0755 bottle_rec_0.50: 0.0076 bowl_rec_0.50: 0.0194 box_rec_0.50: 0.1738 brush_rec_0.50: 0.0000 bucket_rec_0.50: 0.0385 cabinet_rec_0.50: 0.5768 carpet_rec_0.50: 0.0000 cart_rec_0.50: 0.8261 case_rec_0.50: 0.8844 chair_rec_0.50: 0.6463 clock_rec_0.50: 0.0723 clothes_rec_0.50: 0.2198 computer_rec_0.50: 0.3563 container_rec_0.50: 0.2865 copier_rec_0.50: 0.3750 couch_rec_0.50: 0.7923 counter_rec_0.50: 0.1289 cup_rec_0.50: 0.0325 curtain_rec_0.50: 0.2692 decoration_rec_0.50: 0.1425 desk_rec_0.50: 0.8615 dispenser_rec_0.50: 0.4758 door_rec_0.50: 0.2622 doorframe_rec_0.50: 0.4068 dresser_rec_0.50: 0.8372 excercise equipment_rec_0.50: 0.6200 fan_rec_0.50: 0.0698 faucet_rec_0.50: 0.0000 fire extinguisher_rec_0.50: 0.0000 frame_rec_0.50: 0.0000 guitar_rec_0.50: 0.5467 hair dryer_rec_0.50: 0.0000 hat_rec_0.50: 0.0000 holder_rec_0.50: 0.0000 jacket_rec_0.50: 0.1944 lamp_rec_0.50: 0.5502 laptop_rec_0.50: 0.3141 ledge_rec_0.50: 0.0400 light_rec_0.50: 0.0919 machine_rec_0.50: 0.1152 mat_rec_0.50: 0.0040 microwave_rec_0.50: 0.3459 mirror_rec_0.50: 0.0498 monitor_rec_0.50: 0.4385 paper_rec_0.50: 0.0000 paper cutter_rec_0.50: 0.0000 picture_rec_0.50: 0.0213 pillar_rec_0.50: 0.0000 pillow_rec_0.50: 0.4186 pipe_rec_0.50: 0.0080 plant_rec_0.50: 0.2321 plate_rec_0.50: 0.0000 plug_rec_0.50: 0.0000 plunger_rec_0.50: 0.0408 poster_rec_0.50: 0.0000 pot_rec_0.50: 0.0000 printer_rec_0.50: 0.4354 purse_rec_0.50: 0.0000 rack_rec_0.50: 0.2632 radiator_rec_0.50: 0.3253 range hood_rec_0.50: 0.0000 refrigerator_rec_0.50: 0.8571 shelf_rec_0.50: 0.5983 shoe_rec_0.50: 0.0019 shower_rec_0.50: 0.1070 sign_rec_0.50: 0.0237 sink_rec_0.50: 0.6108 soap dispenser_rec_0.50: 0.3649 socket_rec_0.50: 0.0000 stall_rec_0.50: 0.2778 stand_rec_0.50: 0.8938 stool_rec_0.50: 0.7370 stopcock_rec_0.50: 0.0105 stove_rec_0.50: 0.7664 structure_rec_0.50: 0.0800 switch_rec_0.50: 0.0000 table_rec_0.50: 0.8711 telephone_rec_0.50: 0.0034 tissue box_rec_0.50: 0.1319 toaster_rec_0.50: 0.0000 toilet_rec_0.50: 0.9066 toilet paper_rec_0.50: 0.0351 towel_rec_0.50: 0.3037 toy_rec_0.50: 0.0000 tube_rec_0.50: 0.0000 tv_rec_0.50: 0.5195 vanity_rec_0.50: 0.6937 wardrobe_rec_0.50: 0.4681 water cooler_rec_0.50: 0.0400 window_rec_0.50: 0.2645 windowsill_rec_0.50: 0.0000 ball_rec_0.50: 0.4700 broom_rec_0.50: 0.0000 mailbox_rec_0.50: 0.0400 teapot_rec_0.50: 0.0227 dish rack_rec_0.50: 0.0000 toothbrush_rec_0.50: 0.0000 dvd_rec_0.50: 0.0000 dishwasher_rec_0.50: 0.0000 fruit_rec_0.50: 0.0000 keyboard_rec_0.50: 0.0063 mouse_rec_0.50: 0.0000 notebook_rec_0.50: 0.0000 map_rec_0.50: 0.0000 coffee maker_rec_0.50: 0.0000 scale_rec_0.50: 0.0148 eraser_rec_0.50: 0.0000 toothpaste_rec_0.50: 0.0000 rod_rec_0.50: 0.0000 pen_rec_0.50: 0.0000 scissors_rec_0.50: 0.0000 mAR_0.50: 0.2304 data_time: 0.1441 time: 12.3011