2024/04/12 13:09:45 - 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: 756312338 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: 756312338 Distributed launcher: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2024/04/12 13:09:46 - 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 point_cloud_range = [ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ] prior_generator = dict( type='AlignedAnchor3DRangeGenerator', ranges=[ [ -3.2, -3.2, -1.28, 3.2, 3.2, 1.28, ], ], rotations=[ 0.0, ]) model = dict( type='DenseFusionOccPredictor', use_valid_mask=False, use_xyz_feat=True, point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ], 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), backbone=dict( type='mmdet.ResNet', depth=50, 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'), neck=dict( type='mmdet.FPN', in_channels=[ 256, 512, 1024, 2048, ], out_channels=256, num_outs=4), backbone_3d=dict(type='MinkResNet', in_channels=3, depth=34), neck_3d=dict( type='IndoorImVoxelNeck', in_channels=768, out_channels=128, n_blocks=[ 1, 1, 1, ]), bbox_head=dict( type='ImVoxelOccHead', volume_h=[ 20, 10, 5, ], volume_w=[ 20, 10, 5, ], volume_z=[ 8, 4, 2, ], num_classes=81, in_channels=[ 128, 128, 128, ], use_semantic=True), prior_generator=dict( type='AlignedAnchor3DRangeGenerator', ranges=[ [ -3.2, -3.2, -1.28, 3.2, 3.2, 1.28, ], ], rotations=[ 0.0, ]), n_voxels=[ 40, 40, 16, ], coord_type='DEPTH') dataset_type = 'EmbodiedScanDataset' data_root = 'data' class_names = ( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ) metainfo = dict( classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), occ_classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), box_type_3d='euler-depth') backend_args = None train_pipeline = [ dict( type='LoadAnnotations3D', with_occupancy=True, with_visible_occupancy_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'), dict( type='PointsRangeFilter', point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ]), dict(type='PointSample', num_points=100000), dict(type='ConstructMultiViewMasks'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_occupancy', ]), ] test_pipeline = [ dict( type='LoadAnnotations3D', with_occupancy=True, with_visible_occupancy_masks=True), dict( type='MultiViewPipeline', n_images=20, 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'), dict( type='PointsRangeFilter', point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ]), dict(type='PointSample', num_points=100000), dict(type='ConstructMultiViewMasks'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_occupancy', ]), ] train_dataloader = dict( batch_size=1, num_workers=1, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='EmbodiedScanDataset', data_root='data', ann_file='embodiedscan_infos_train.pkl', pipeline=[ dict( type='LoadAnnotations3D', with_occupancy=True, with_visible_occupancy_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'), dict( type='PointsRangeFilter', point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ]), dict(type='PointSample', num_points=100000), dict(type='ConstructMultiViewMasks'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_occupancy', ]), ], test_mode=False, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), occ_classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), box_type_3d='euler-depth'))) 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_occupancy=True, with_visible_occupancy_masks=True), dict( type='MultiViewPipeline', n_images=20, 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'), dict( type='PointsRangeFilter', point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ]), dict(type='PointSample', num_points=100000), dict(type='ConstructMultiViewMasks'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_occupancy', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), occ_classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), box_type_3d='euler-depth'))) 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_occupancy=True, with_visible_occupancy_masks=True), dict( type='MultiViewPipeline', n_images=20, 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'), dict( type='PointsRangeFilter', point_cloud_range=[ -3.2, -3.2, -0.78, 3.2, 3.2, 1.78, ]), dict(type='PointSample', num_points=100000), dict(type='ConstructMultiViewMasks'), dict( type='Pack3DDetInputs', keys=[ 'img', 'points', 'gt_bboxes_3d', 'gt_labels_3d', 'gt_occupancy', ]), ], test_mode=True, filter_empty_gt=True, box_type_3d='Euler-Depth', metainfo=dict( classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), occ_classes=( 'floor', 'wall', 'chair', 'cabinet', 'door', 'table', 'couch', 'shelf', 'window', 'bed', 'curtain', 'desk', 'doorframe', 'plant', 'stairs', 'pillow', 'wardrobe', 'picture', 'bathtub', 'box', 'counter', 'bench', 'stand', 'rail', 'sink', 'clothes', 'mirror', 'toilet', 'refrigerator', 'lamp', 'book', 'dresser', 'stool', 'fireplace', 'tv', 'blanket', 'commode', 'washing machine', 'monitor', 'window frame', 'radiator', 'mat', 'shower', 'rack', 'towel', 'ottoman', 'column', 'blinds', 'stove', 'bar', 'pillar', 'bin', 'heater', 'clothes dryer', 'backpack', 'blackboard', 'decoration', 'roof', 'bag', 'steps', 'windowsill', 'cushion', 'carpet', 'copier', 'board', 'countertop', 'basket', 'mailbox', 'kitchen island', 'washbasin', 'bicycle', 'drawer', 'oven', 'piano', 'excercise equipment', 'beam', 'partition', 'printer', 'microwave', 'frame', ), box_type_3d='euler-depth'))) val_evaluator = dict(type='OccupancyMetric') test_evaluator = dict(type='OccupancyMetric') train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=24, val_interval=4) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='AdamW', lr=0.0001, weight_decay=0.01), clip_grad=dict(max_norm=35.0, norm_type=2)) param_scheduler = dict( type='MultiStepLR', begin=0, end=24, by_epoch=True, milestones=[ 16, 22, ], gamma=0.1) custom_hooks = [ dict(type='EmptyCacheHook', after_iter=True), ] find_unused_parameters = True launcher = 'slurm' work_dir = '/mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-occupancy-benchmark' 2024/04/12 13:09:46 - 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 13:09:58 - 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 13:09:58 - 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 13:09:59 - 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 13:09:59 - mmengine - WARNING - euler-depth is not a meta file, simply parsed as meta information 2024/04/12 13:11:43 - 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 13:11:43 - 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 13:11:43 - 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 13:11:43 - 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 13:11:43 - 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 13:12:07 - mmengine - WARNING - The prefix is not set in metric class OccupancyMetric. 2024/04/12 13:12:09 - 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 13:12:09 - mmengine - INFO - load model from: torchvision://resnet50 2024/04/12 13:12:09 - mmengine - INFO - Loads checkpoint by torchvision backend from path: torchvision://resnet50 2024/04/12 13:12:09 - mmengine - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: fc.weight, fc.bias Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 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 DenseFusionOccPredictor backbone_3d.norm1.bias - torch.Size([1, 64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.0.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.0.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.0.downsample.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.1.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.1.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.2.norm1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer1.2.norm2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.0.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.0.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.0.downsample.1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.1.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.1.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.2.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.2.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.3.norm1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer2.3.norm2.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.0.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.0.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.0.downsample.1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.1.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.1.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.2.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.2.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.3.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.3.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.4.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.4.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.5.norm1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer3.5.norm2.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.0.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.0.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.0.downsample.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.1.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.1.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.2.norm1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 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 DenseFusionOccPredictor backbone_3d.layer4.2.norm2.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.lateral_convs.0.conv.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.lateral_convs.1.conv.weight - torch.Size([256, 512, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.lateral_convs.2.conv.weight - torch.Size([256, 1024, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.lateral_convs.3.conv.weight - torch.Size([256, 2048, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck.fpn_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.conv1.weight - torch.Size([768, 768, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.norm1.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.norm1.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.conv2.weight - torch.Size([768, 768, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.norm2.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_0.0.norm2.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_0.0.weight - torch.Size([128, 768, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_0.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_0.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.conv1.weight - torch.Size([1536, 768, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.norm1.weight - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.norm1.bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.conv2.weight - torch.Size([1536, 1536, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.norm2.weight - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.norm2.bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.downsample.0.weight - torch.Size([1536, 768, 1, 1, 1]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.downsample.1.weight - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_1.0.downsample.1.bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.0.weight - torch.Size([1536, 768, 2, 2, 2]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.1.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.1.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.3.weight - torch.Size([768, 768, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.4.weight - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_1.4.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_1.0.weight - torch.Size([128, 1536, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_1.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_1.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.conv1.weight - torch.Size([3072, 1536, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.norm1.weight - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.norm1.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.conv2.weight - torch.Size([3072, 3072, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.norm2.weight - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.norm2.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.downsample.0.weight - torch.Size([3072, 1536, 1, 1, 1]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.downsample.1.weight - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.down_layer_2.0.downsample.1.bias - torch.Size([3072]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.0.weight - torch.Size([3072, 1536, 2, 2, 2]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.1.weight - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.1.bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.3.weight - torch.Size([1536, 1536, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.4.weight - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.up_block_2.4.bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_2.0.weight - torch.Size([128, 3072, 3, 3, 3]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_2.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor neck_3d.out_block_2.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor bbox_head.occ.0.weight - torch.Size([81, 128, 1, 1, 1]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor bbox_head.occ.1.weight - torch.Size([81, 128, 1, 1, 1]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor bbox_head.occ.2.weight - torch.Size([81, 128, 1, 1, 1]): The value is the same before and after calling `init_weights` of DenseFusionOccPredictor 2024/04/12 13:12:09 - 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 13:12:09 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2024/04/12 13:12:09 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/wangtai/EmbodiedScan/work_dirs/mv-occupancy-benchmark. 2024/04/12 13:13:40 - mmengine - INFO - Epoch(train) [1][ 50/389] lr: 1.0000e-04 eta: 4:40:14 time: 1.8108 data_time: 0.1897 memory: 20059 grad_norm: 18.4739 loss: 16.4166 loss_occ_0: 9.2646 loss_occ_1: 4.6804 loss_occ_2: 2.4715 2024/04/12 13:14:57 - mmengine - INFO - Epoch(train) [1][100/389] lr: 1.0000e-04 eta: 4:18:34 time: 1.5489 data_time: 0.2182 memory: 20149 grad_norm: 9.5826 loss: 13.0774 loss_occ_0: 7.3296 loss_occ_1: 3.7333 loss_occ_2: 2.0145 2024/04/12 13:16:21 - mmengine - INFO - Epoch(train) [1][150/389] lr: 1.0000e-04 eta: 4:16:32 time: 1.6674 data_time: 0.1125 memory: 20138 grad_norm: 8.6381 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:17:40 - mmengine - INFO - Epoch(train) [1][200/389] lr: 1.0000e-04 eta: 4:11:29 time: 1.5795 data_time: 0.1123 memory: 20068 grad_norm: 8.9284 loss: 11.9316 loss_occ_0: 6.5924 loss_occ_1: 3.4486 loss_occ_2: 1.8906 2024/04/12 13:19:01 - mmengine - INFO - Epoch(train) [1][250/389] lr: 1.0000e-04 eta: 4:09:20 time: 1.6261 data_time: 0.1731 memory: 20043 grad_norm: 7.7221 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:20:23 - mmengine - INFO - Epoch(train) [1][300/389] lr: 1.0000e-04 eta: 4:07:54 time: 1.6440 data_time: 0.1787 memory: 20202 grad_norm: 7.7840 loss: 14.9789 loss_occ_0: 7.9934 loss_occ_1: 4.1958 loss_occ_2: 2.7897 2024/04/12 13:21:43 - mmengine - INFO - Epoch(train) [1][350/389] lr: 1.0000e-04 eta: 4:05:28 time: 1.5968 data_time: 0.0797 memory: 19958 grad_norm: 7.3681 loss: 10.5247 loss_occ_0: 5.7521 loss_occ_1: 3.0496 loss_occ_2: 1.7230 2024/04/12 13:22:42 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 13:22:42 - mmengine - INFO - Saving checkpoint at 1 epochs 2024/04/12 13:24:49 - mmengine - INFO - Epoch(train) [2][ 50/389] lr: 1.0000e-04 eta: 4:01:23 time: 1.6383 data_time: 0.3899 memory: 20056 grad_norm: 7.4885 loss: 9.7656 loss_occ_0: 5.3455 loss_occ_1: 2.8496 loss_occ_2: 1.5705 2024/04/12 13:26:09 - mmengine - INFO - Epoch(train) [2][100/389] lr: 1.0000e-04 eta: 3:59:41 time: 1.6058 data_time: 0.2821 memory: 20016 grad_norm: 7.2766 loss: 10.0234 loss_occ_0: 5.5658 loss_occ_1: 2.8638 loss_occ_2: 1.5938 2024/04/12 13:27:32 - mmengine - INFO - Epoch(train) [2][150/389] lr: 1.0000e-04 eta: 3:58:48 time: 1.6606 data_time: 0.3149 memory: 20204 grad_norm: 7.1825 loss: 9.4437 loss_occ_0: 5.1797 loss_occ_1: 2.7374 loss_occ_2: 1.5266 2024/04/12 13:28:56 - mmengine - INFO - Epoch(train) [2][200/389] lr: 1.0000e-04 eta: 3:58:07 time: 1.6824 data_time: 0.2300 memory: 20128 grad_norm: 7.2912 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:30:14 - mmengine - INFO - Epoch(train) [2][250/389] lr: 1.0000e-04 eta: 3:55:46 time: 1.5465 data_time: 0.1403 memory: 20070 grad_norm: 7.7082 loss: 8.6438 loss_occ_0: 4.4994 loss_occ_1: 2.5820 loss_occ_2: 1.5625 2024/04/12 13:31:35 - mmengine - INFO - Epoch(train) [2][300/389] lr: 1.0000e-04 eta: 3:54:22 time: 1.6225 data_time: 0.2746 memory: 20043 grad_norm: 7.2127 loss: 9.5306 loss_occ_0: 5.2609 loss_occ_1: 2.7486 loss_occ_2: 1.5210 2024/04/12 13:33:00 - mmengine - INFO - Epoch(train) [2][350/389] lr: 1.0000e-04 eta: 3:53:45 time: 1.7027 data_time: 0.1010 memory: 20058 grad_norm: 7.1318 loss: 16.2266 loss_occ_0: 8.9912 loss_occ_1: 4.6766 loss_occ_2: 2.5588 2024/04/12 13:34:01 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 13:34:01 - mmengine - INFO - Saving checkpoint at 2 epochs 2024/04/12 13:36:05 - mmengine - INFO - Epoch(train) [3][ 50/389] lr: 1.0000e-04 eta: 3:50:53 time: 1.6341 data_time: 0.3976 memory: 20060 grad_norm: 7.3310 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:37:26 - mmengine - INFO - Epoch(train) [3][100/389] lr: 1.0000e-04 eta: 3:49:23 time: 1.6107 data_time: 0.1407 memory: 20040 grad_norm: 7.1991 loss: 7.7460 loss_occ_0: 4.1551 loss_occ_1: 2.2921 loss_occ_2: 1.2988 2024/04/12 13:38:42 - mmengine - INFO - Epoch(train) [3][150/389] lr: 1.0000e-04 eta: 3:47:14 time: 1.5217 data_time: 0.0999 memory: 20115 grad_norm: 6.8399 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:40:04 - mmengine - INFO - Epoch(train) [3][200/389] lr: 1.0000e-04 eta: 3:45:59 time: 1.6359 data_time: 0.2219 memory: 20142 grad_norm: 6.7233 loss: 8.2624 loss_occ_0: 4.3733 loss_occ_1: 2.4346 loss_occ_2: 1.4545 2024/04/12 13:40:38 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 13:41:24 - mmengine - INFO - Epoch(train) [3][250/389] lr: 1.0000e-04 eta: 3:44:30 time: 1.6029 data_time: 0.1823 memory: 20192 grad_norm: 7.1233 loss: 15.8090 loss_occ_0: 8.5046 loss_occ_1: 4.4054 loss_occ_2: 2.8991 2024/04/12 13:42:45 - mmengine - INFO - Epoch(train) [3][300/389] lr: 1.0000e-04 eta: 3:43:10 time: 1.6230 data_time: 0.1901 memory: 20013 grad_norm: 7.0729 loss: 8.0335 loss_occ_0: 4.2526 loss_occ_1: 2.3784 loss_occ_2: 1.4025 2024/04/12 13:44:08 - mmengine - INFO - Epoch(train) [3][350/389] lr: 1.0000e-04 eta: 3:42:00 time: 1.6534 data_time: 0.1531 memory: 20094 grad_norm: 7.2136 loss: 7.6001 loss_occ_0: 4.0268 loss_occ_1: 2.2991 loss_occ_2: 1.2741 2024/04/12 13:45:14 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 13:45:14 - mmengine - INFO - Saving checkpoint at 3 epochs 2024/04/12 13:47:14 - mmengine - INFO - Epoch(train) [4][ 50/389] lr: 1.0000e-04 eta: 3:39:30 time: 1.5505 data_time: 0.2307 memory: 20195 grad_norm: 7.1032 loss: 8.0912 loss_occ_0: 4.3372 loss_occ_1: 2.3755 loss_occ_2: 1.3786 2024/04/12 13:48:37 - mmengine - INFO - Epoch(train) [4][100/389] lr: 1.0000e-04 eta: 3:38:25 time: 1.6729 data_time: 0.0627 memory: 20031 grad_norm: 7.3529 loss: 7.6379 loss_occ_0: 4.1054 loss_occ_1: 2.1992 loss_occ_2: 1.3332 2024/04/12 13:49:58 - mmengine - INFO - Epoch(train) [4][150/389] lr: 1.0000e-04 eta: 3:37:02 time: 1.6176 data_time: 0.2493 memory: 20158 grad_norm: 6.8077 loss: 14.5474 loss_occ_0: 8.0252 loss_occ_1: 4.2133 loss_occ_2: 2.3089 2024/04/12 13:51:20 - mmengine - INFO - Epoch(train) [4][200/389] lr: 1.0000e-04 eta: 3:35:46 time: 1.6407 data_time: 0.3388 memory: 20117 grad_norm: 7.4732 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 13:52:41 - mmengine - INFO - Epoch(train) [4][250/389] lr: 1.0000e-04 eta: 3:34:22 time: 1.6137 data_time: 0.2213 memory: 20026 grad_norm: 7.4542 loss: 14.9976 loss_occ_0: 7.9664 loss_occ_1: 4.2416 loss_occ_2: 2.7897 2024/04/12 13:54:01 - mmengine - INFO - Epoch(train) [4][300/389] lr: 1.0000e-04 eta: 3:32:56 time: 1.6088 data_time: 0.1200 memory: 20085 grad_norm: 7.2463 loss: 7.5202 loss_occ_0: 3.9540 loss_occ_1: 2.2274 loss_occ_2: 1.3388 2024/04/12 13:55:27 - mmengine - INFO - Epoch(train) [4][350/389] lr: 1.0000e-04 eta: 3:31:57 time: 1.7085 data_time: 0.1994 memory: 19970 grad_norm: 6.8434 loss: 7.8384 loss_occ_0: 4.2736 loss_occ_1: 2.2797 loss_occ_2: 1.2851 2024/04/12 13:56:25 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 13:56:25 - mmengine - INFO - Saving checkpoint at 4 epochs 2024/04/12 13:57:58 - mmengine - INFO - Epoch(val) [4][ 50/103] eta: 0:00:52 time: 0.9835 data_time: 0.8753 memory: 20205 2024/04/12 14:00:54 - mmengine - INFO - Epoch(val) [4][100/103] eta: 0:00:06 time: 3.5365 data_time: 3.4286 memory: 16131 2024/04/12 14:01:53 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.70000 | | floor | 0.64736 | | wall | 0.46703 | | chair | 0.41666 | | cabinet | 0.19692 | | door | 0.15132 | | table | 0.31880 | | couch | 0.27062 | | shelf | 0.30701 | | window | 0.17859 | | bed | 0.32988 | | curtain | 0.30633 | | desk | 0.22181 | | doorframe | 0.15124 | | plant | 0.24996 | | stairs | 0.30144 | | pillow | 0.20428 | | wardrobe | 0.00000 | | picture | 0.17156 | | bathtub | 0.38658 | | box | 0.05686 | | counter | 0.19525 | | bench | 0.07891 | | stand | 0.08522 | | rail | 0.02784 | | sink | 0.30488 | | clothes | 0.06376 | | mirror | 0.05796 | | toilet | 0.46170 | | refrigerator | 0.01031 | | lamp | 0.19832 | | book | 0.00063 | | dresser | 0.00000 | | stool | 0.03168 | | fireplace | 0.00000 | | tv | 0.05854 | | blanket | 0.15726 | | commode | 0.00000 | | washing machine | 0.00197 | | monitor | 0.26410 | | window frame | 0.00315 | | radiator | 0.12334 | | mat | 0.00000 | | shower | 0.00000 | | rack | 0.00000 | | towel | 0.09604 | | ottoman | 0.05217 | | column | 0.00000 | | blinds | 0.00000 | | stove | 0.02628 | | bar | 0.00000 | | pillar | 0.00000 | | bin | 0.16014 | | heater | 0.00000 | | clothes dryer | 0.00000 | | backpack | 0.06441 | | blackboard | 0.08935 | | decoration | 0.00114 | | roof | 0.00000 | | bag | 0.00266 | | steps | 0.00000 | | windowsill | 0.06623 | | cushion | 0.00304 | | carpet | 0.00000 | | copier | 0.02757 | | board | 0.00090 | | countertop | 0.00863 | | basket | 0.00289 | | mailbox | 0.00000 | | kitchen island | 0.00000 | | washbasin | 0.00875 | | bicycle | 0.00000 | | drawer | 0.00000 | | oven | 0.00000 | | piano | 0.00000 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.00000 | | microwave | 0.07922 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.10924 | +---------------------+---------+ 2024/04/12 14:01:53 - mmengine - INFO - Epoch(val) [4][103/103] empty: 0.7000 floor: 0.6474 wall: 0.4670 chair: 0.4167 cabinet: 0.1969 door: 0.1513 table: 0.3188 couch: 0.2706 shelf: 0.3070 window: 0.1786 bed: 0.3299 curtain: 0.3063 desk: 0.2218 doorframe: 0.1512 plant: 0.2500 stairs: 0.3014 pillow: 0.2043 wardrobe: 0.0000 picture: 0.1716 bathtub: 0.3866 box: 0.0569 counter: 0.1952 bench: 0.0789 stand: 0.0852 rail: 0.0278 sink: 0.3049 clothes: 0.0638 mirror: 0.0580 toilet: 0.4617 refrigerator: 0.0103 lamp: 0.1983 book: 0.0006 dresser: 0.0000 stool: 0.0317 fireplace: 0.0000 tv: 0.0585 blanket: 0.1573 commode: 0.0000 washing machine: 0.0020 monitor: 0.2641 window frame: 0.0031 radiator: 0.1233 mat: 0.0000 shower: 0.0000 rack: 0.0000 towel: 0.0960 ottoman: 0.0522 column: 0.0000 blinds: 0.0000 stove: 0.0263 bar: 0.0000 pillar: 0.0000 bin: 0.1601 heater: 0.0000 clothes dryer: 0.0000 backpack: 0.0644 blackboard: 0.0893 decoration: 0.0011 roof: 0.0000 bag: 0.0027 steps: 0.0000 windowsill: 0.0662 cushion: 0.0030 carpet: 0.0000 copier: 0.0276 board: 0.0009 countertop: 0.0086 basket: 0.0029 mailbox: 0.0000 kitchen island: 0.0000 washbasin: 0.0087 bicycle: 0.0000 drawer: 0.0000 oven: 0.0000 piano: 0.0000 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.0000 microwave: 0.0792 frame: 0.0000 data_time: 2.2086 time: 2.3168 2024/04/12 14:03:15 - mmengine - INFO - Epoch(train) [5][ 50/389] lr: 1.0000e-04 eta: 3:29:13 time: 1.6444 data_time: 0.0811 memory: 20136 grad_norm: 6.8448 loss: 6.9954 loss_occ_0: 3.6475 loss_occ_1: 2.0998 loss_occ_2: 1.2481 2024/04/12 14:04:34 - mmengine - INFO - Epoch(train) [5][100/389] lr: 1.0000e-04 eta: 3:27:42 time: 1.5817 data_time: 0.1235 memory: 20116 grad_norm: 7.2106 loss: 7.6484 loss_occ_0: 3.7499 loss_occ_1: 2.1132 loss_occ_2: 1.7853 2024/04/12 14:06:00 - mmengine - INFO - Epoch(train) [5][150/389] lr: 1.0000e-04 eta: 3:26:40 time: 1.7102 data_time: 0.0946 memory: 20091 grad_norm: 7.0700 loss: 7.0149 loss_occ_0: 3.7078 loss_occ_1: 2.1340 loss_occ_2: 1.1731 2024/04/12 14:07:19 - mmengine - INFO - Epoch(train) [5][200/389] lr: 1.0000e-04 eta: 3:25:11 time: 1.5880 data_time: 0.1520 memory: 19984 grad_norm: 7.0709 loss: 7.8363 loss_occ_0: 3.8050 loss_occ_1: 2.1724 loss_occ_2: 1.8589 2024/04/12 14:08:41 - mmengine - INFO - Epoch(train) [5][250/389] lr: 1.0000e-04 eta: 3:23:52 time: 1.6370 data_time: 0.2288 memory: 20024 grad_norm: 6.9607 loss: 6.9970 loss_occ_0: 3.8001 loss_occ_1: 2.0012 loss_occ_2: 1.1958 2024/04/12 14:10:06 - mmengine - INFO - Epoch(train) [5][300/389] lr: 1.0000e-04 eta: 3:22:44 time: 1.6874 data_time: 0.2447 memory: 20060 grad_norm: 7.0847 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:11:23 - mmengine - INFO - Epoch(train) [5][350/389] lr: 1.0000e-04 eta: 3:21:06 time: 1.5394 data_time: 0.2830 memory: 20090 grad_norm: 7.5416 loss: 7.4542 loss_occ_0: 3.9881 loss_occ_1: 2.2259 loss_occ_2: 1.2402 2024/04/12 14:12:24 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:12:24 - mmengine - INFO - Saving checkpoint at 5 epochs 2024/04/12 14:14:35 - mmengine - INFO - Epoch(train) [6][ 50/389] lr: 1.0000e-04 eta: 3:18:37 time: 1.6417 data_time: 0.5395 memory: 20213 grad_norm: 7.0472 loss: 14.2884 loss_occ_0: 7.6158 loss_occ_1: 3.9925 loss_occ_2: 2.6800 2024/04/12 14:14:43 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:15:56 - mmengine - INFO - Epoch(train) [6][100/389] lr: 1.0000e-04 eta: 3:17:17 time: 1.6260 data_time: 0.1066 memory: 20041 grad_norm: 6.8600 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:17:16 - mmengine - INFO - Epoch(train) [6][150/389] lr: 1.0000e-04 eta: 3:15:51 time: 1.5996 data_time: 0.1035 memory: 20011 grad_norm: 6.7801 loss: 7.0607 loss_occ_0: 3.4386 loss_occ_1: 1.9373 loss_occ_2: 1.6848 2024/04/12 14:18:42 - mmengine - INFO - Epoch(train) [6][200/389] lr: 1.0000e-04 eta: 3:14:45 time: 1.7129 data_time: 0.1118 memory: 20107 grad_norm: 7.4871 loss: 6.2726 loss_occ_0: 3.3546 loss_occ_1: 1.8149 loss_occ_2: 1.1032 2024/04/12 14:20:03 - mmengine - INFO - Epoch(train) [6][250/389] lr: 1.0000e-04 eta: 3:13:25 time: 1.6279 data_time: 0.2079 memory: 20103 grad_norm: 6.9492 loss: 6.5557 loss_occ_0: 3.5134 loss_occ_1: 1.8789 loss_occ_2: 1.1633 2024/04/12 14:21:17 - mmengine - INFO - Epoch(train) [6][300/389] lr: 1.0000e-04 eta: 3:11:41 time: 1.4849 data_time: 0.1404 memory: 20191 grad_norm: 7.1820 loss: 7.0785 loss_occ_0: 3.7917 loss_occ_1: 2.0266 loss_occ_2: 1.2602 2024/04/12 14:22:42 - mmengine - INFO - Epoch(train) [6][350/389] lr: 1.0000e-04 eta: 3:10:31 time: 1.6908 data_time: 0.2757 memory: 20031 grad_norm: 7.0001 loss: 7.1168 loss_occ_0: 3.7356 loss_occ_1: 2.1213 loss_occ_2: 1.2600 2024/04/12 14:23:44 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:23:44 - mmengine - INFO - Saving checkpoint at 6 epochs 2024/04/12 14:25:54 - mmengine - INFO - Epoch(train) [7][ 50/389] lr: 1.0000e-04 eta: 3:08:10 time: 1.6752 data_time: 0.4129 memory: 20219 grad_norm: 6.8461 loss: 6.8314 loss_occ_0: 3.6312 loss_occ_1: 1.9849 loss_occ_2: 1.2154 2024/04/12 14:27:17 - mmengine - INFO - Epoch(train) [7][100/389] lr: 1.0000e-04 eta: 3:06:54 time: 1.6629 data_time: 0.3675 memory: 20046 grad_norm: 7.0172 loss: 7.4134 loss_occ_0: 4.0142 loss_occ_1: 2.1375 loss_occ_2: 1.2616 2024/04/12 14:28:35 - mmengine - INFO - Epoch(train) [7][150/389] lr: 1.0000e-04 eta: 3:05:25 time: 1.5646 data_time: 0.1012 memory: 20065 grad_norm: 7.0087 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:29:56 - mmengine - INFO - Epoch(train) [7][200/389] lr: 1.0000e-04 eta: 3:04:04 time: 1.6238 data_time: 0.0855 memory: 20151 grad_norm: 6.8774 loss: 6.8583 loss_occ_0: 3.3537 loss_occ_1: 1.8456 loss_occ_2: 1.6590 2024/04/12 14:31:14 - mmengine - INFO - Epoch(train) [7][250/389] lr: 1.0000e-04 eta: 3:02:34 time: 1.5564 data_time: 0.1294 memory: 20086 grad_norm: 6.7240 loss: 6.8215 loss_occ_0: 3.6977 loss_occ_1: 1.9437 loss_occ_2: 1.1801 2024/04/12 14:32:37 - mmengine - INFO - Epoch(train) [7][300/389] lr: 1.0000e-04 eta: 3:01:19 time: 1.6709 data_time: 0.1606 memory: 20156 grad_norm: 6.9206 loss: 6.1261 loss_occ_0: 3.2522 loss_occ_1: 1.7702 loss_occ_2: 1.1037 2024/04/12 14:33:58 - mmengine - INFO - Epoch(train) [7][350/389] lr: 1.0000e-04 eta: 2:59:56 time: 1.6130 data_time: 0.0899 memory: 20026 grad_norm: 7.3725 loss: 6.5568 loss_occ_0: 3.5072 loss_occ_1: 1.9548 loss_occ_2: 1.0948 2024/04/12 14:35:00 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:35:00 - mmengine - INFO - Saving checkpoint at 7 epochs 2024/04/12 14:37:10 - mmengine - INFO - Epoch(train) [8][ 50/389] lr: 1.0000e-04 eta: 2:57:43 time: 1.7557 data_time: 0.1884 memory: 20039 grad_norm: 7.0115 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:38:33 - mmengine - INFO - Epoch(train) [8][100/389] lr: 1.0000e-04 eta: 2:56:27 time: 1.6636 data_time: 0.2789 memory: 20103 grad_norm: 6.9930 loss: 5.6703 loss_occ_0: 3.0053 loss_occ_1: 1.6588 loss_occ_2: 1.0062 2024/04/12 14:39:55 - mmengine - INFO - Epoch(train) [8][150/389] lr: 1.0000e-04 eta: 2:55:05 time: 1.6243 data_time: 0.1556 memory: 20043 grad_norm: 7.0651 loss: 9.9398 loss_occ_0: 7.0935 loss_occ_1: 1.7884 loss_occ_2: 1.0579 2024/04/12 14:41:18 - mmengine - INFO - Epoch(train) [8][200/389] lr: 1.0000e-04 eta: 2:53:49 time: 1.6760 data_time: 0.1990 memory: 20003 grad_norm: 6.9113 loss: 6.4294 loss_occ_0: 3.3512 loss_occ_1: 1.9141 loss_occ_2: 1.1640 2024/04/12 14:42:38 - mmengine - INFO - Epoch(train) [8][250/389] lr: 1.0000e-04 eta: 2:52:24 time: 1.5917 data_time: 0.1234 memory: 20043 grad_norm: 6.7887 loss: 6.4588 loss_occ_0: 3.4017 loss_occ_1: 1.8929 loss_occ_2: 1.1642 2024/04/12 14:43:22 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:43:57 - mmengine - INFO - Epoch(train) [8][300/389] lr: 1.0000e-04 eta: 2:50:58 time: 1.5803 data_time: 0.0938 memory: 20033 grad_norm: 6.5927 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:45:15 - mmengine - INFO - Epoch(train) [8][350/389] lr: 1.0000e-04 eta: 2:49:31 time: 1.5630 data_time: 0.1269 memory: 20022 grad_norm: 6.9120 loss: 6.8614 loss_occ_0: 3.3558 loss_occ_1: 1.8504 loss_occ_2: 1.6553 2024/04/12 14:46:16 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 14:46:16 - mmengine - INFO - Saving checkpoint at 8 epochs 2024/04/12 14:47:52 - mmengine - INFO - Epoch(val) [8][ 50/103] eta: 0:00:51 time: 0.9701 data_time: 0.8681 memory: 19935 2024/04/12 14:50:47 - mmengine - INFO - Epoch(val) [8][100/103] eta: 0:00:06 time: 3.5043 data_time: 3.3862 memory: 16130 2024/04/12 14:51:29 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.72405 | | floor | 0.68581 | | wall | 0.49983 | | chair | 0.45137 | | cabinet | 0.22670 | | door | 0.23457 | | table | 0.35504 | | couch | 0.28958 | | shelf | 0.35643 | | window | 0.22519 | | bed | 0.36733 | | curtain | 0.39871 | | desk | 0.16784 | | doorframe | 0.18593 | | plant | 0.34181 | | stairs | 0.26845 | | pillow | 0.26172 | | wardrobe | 0.01469 | | picture | 0.22165 | | bathtub | 0.51321 | | box | 0.09876 | | counter | 0.21688 | | bench | 0.10951 | | stand | 0.09996 | | rail | 0.11435 | | sink | 0.34691 | | clothes | 0.16555 | | mirror | 0.10197 | | toilet | 0.52440 | | refrigerator | 0.05316 | | lamp | 0.25720 | | book | 0.11700 | | dresser | 0.04823 | | stool | 0.05528 | | fireplace | 0.00000 | | tv | 0.13874 | | blanket | 0.16209 | | commode | 0.00968 | | washing machine | 0.02995 | | monitor | 0.43189 | | window frame | 0.00554 | | radiator | 0.31197 | | mat | 0.00106 | | shower | 0.00000 | | rack | 0.00000 | | towel | 0.16135 | | ottoman | 0.08746 | | column | 0.01245 | | blinds | 0.00000 | | stove | 0.02740 | | bar | 0.01879 | | pillar | 0.00000 | | bin | 0.27036 | | heater | 0.05944 | | clothes dryer | 0.00000 | | backpack | 0.20031 | | blackboard | 0.25939 | | decoration | 0.02569 | | roof | 0.00000 | | bag | 0.03489 | | steps | 0.03544 | | windowsill | 0.11919 | | cushion | 0.03239 | | carpet | 0.00000 | | copier | 0.04461 | | board | 0.00212 | | countertop | 0.03273 | | basket | 0.01641 | | mailbox | 0.00000 | | kitchen island | 0.00000 | | washbasin | 0.00000 | | bicycle | 0.00000 | | drawer | 0.00347 | | oven | 0.04545 | | piano | 0.00503 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.00352 | | microwave | 0.10108 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.14554 | +---------------------+---------+ 2024/04/12 14:51:29 - mmengine - INFO - Epoch(val) [8][103/103] empty: 0.7241 floor: 0.6858 wall: 0.4998 chair: 0.4514 cabinet: 0.2267 door: 0.2346 table: 0.3550 couch: 0.2896 shelf: 0.3564 window: 0.2252 bed: 0.3673 curtain: 0.3987 desk: 0.1678 doorframe: 0.1859 plant: 0.3418 stairs: 0.2684 pillow: 0.2617 wardrobe: 0.0147 picture: 0.2217 bathtub: 0.5132 box: 0.0988 counter: 0.2169 bench: 0.1095 stand: 0.1000 rail: 0.1144 sink: 0.3469 clothes: 0.1656 mirror: 0.1020 toilet: 0.5244 refrigerator: 0.0532 lamp: 0.2572 book: 0.1170 dresser: 0.0482 stool: 0.0553 fireplace: 0.0000 tv: 0.1387 blanket: 0.1621 commode: 0.0097 washing machine: 0.0300 monitor: 0.4319 window frame: 0.0055 radiator: 0.3120 mat: 0.0011 shower: 0.0000 rack: 0.0000 towel: 0.1613 ottoman: 0.0875 column: 0.0125 blinds: 0.0000 stove: 0.0274 bar: 0.0188 pillar: 0.0000 bin: 0.2704 heater: 0.0594 clothes dryer: 0.0000 backpack: 0.2003 blackboard: 0.2594 decoration: 0.0257 roof: 0.0000 bag: 0.0349 steps: 0.0354 windowsill: 0.1192 cushion: 0.0324 carpet: 0.0000 copier: 0.0446 board: 0.0021 countertop: 0.0327 basket: 0.0164 mailbox: 0.0000 kitchen island: 0.0000 washbasin: 0.0000 bicycle: 0.0000 drawer: 0.0035 oven: 0.0455 piano: 0.0050 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.0035 microwave: 0.1011 frame: 0.0000 data_time: 2.2041 time: 2.3144 2024/04/12 14:52:52 - mmengine - INFO - Epoch(train) [9][ 50/389] lr: 1.0000e-04 eta: 2:47:06 time: 1.6748 data_time: 0.2565 memory: 20187 grad_norm: 6.8145 loss: 5.9158 loss_occ_0: 3.1125 loss_occ_1: 1.7008 loss_occ_2: 1.1025 2024/04/12 14:54:23 - mmengine - INFO - Epoch(train) [9][100/389] lr: 1.0000e-04 eta: 2:46:03 time: 1.8114 data_time: 0.0651 memory: 20067 grad_norm: 6.5587 loss: 5.7793 loss_occ_0: 2.9893 loss_occ_1: 1.7157 loss_occ_2: 1.0742 2024/04/12 14:55:42 - mmengine - INFO - Epoch(train) [9][150/389] lr: 1.0000e-04 eta: 2:44:38 time: 1.5867 data_time: 0.1011 memory: 19958 grad_norm: 6.9115 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 14:57:00 - mmengine - INFO - Epoch(train) [9][200/389] lr: 1.0000e-04 eta: 2:43:11 time: 1.5615 data_time: 0.1582 memory: 20087 grad_norm: 7.0786 loss: 6.4228 loss_occ_0: 3.5443 loss_occ_1: 1.8162 loss_occ_2: 1.0624 2024/04/12 14:58:26 - mmengine - INFO - Epoch(train) [9][250/389] lr: 1.0000e-04 eta: 2:41:56 time: 1.7048 data_time: 0.2946 memory: 20017 grad_norm: 7.2085 loss: 13.4718 loss_occ_0: 7.3764 loss_occ_1: 3.9582 loss_occ_2: 2.1372 2024/04/12 14:59:51 - mmengine - INFO - Epoch(train) [9][300/389] lr: 1.0000e-04 eta: 2:40:43 time: 1.7135 data_time: 0.0760 memory: 20039 grad_norm: 6.9936 loss: 18.9163 loss_occ_0: 10.7643 loss_occ_1: 5.6280 loss_occ_2: 2.5240 2024/04/12 15:01:12 - mmengine - INFO - Epoch(train) [9][350/389] lr: 1.0000e-04 eta: 2:39:20 time: 1.6190 data_time: 0.1772 memory: 20144 grad_norm: 7.4968 loss: 5.8022 loss_occ_0: 2.9720 loss_occ_1: 1.7438 loss_occ_2: 1.0864 2024/04/12 15:02:15 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:02:15 - mmengine - INFO - Saving checkpoint at 9 epochs 2024/04/12 15:04:24 - mmengine - INFO - Epoch(train) [10][ 50/389] lr: 1.0000e-04 eta: 2:36:58 time: 1.6604 data_time: 0.1640 memory: 20093 grad_norm: 7.0712 loss: 5.6923 loss_occ_0: 2.9816 loss_occ_1: 1.6291 loss_occ_2: 1.0816 2024/04/12 15:05:47 - mmengine - INFO - Epoch(train) [10][100/389] lr: 1.0000e-04 eta: 2:35:38 time: 1.6538 data_time: 0.2598 memory: 19923 grad_norm: 6.7596 loss: 6.4933 loss_occ_0: 3.5495 loss_occ_1: 1.8343 loss_occ_2: 1.1095 2024/04/12 15:07:06 - mmengine - INFO - Epoch(train) [10][150/389] lr: 1.0000e-04 eta: 2:34:13 time: 1.5787 data_time: 0.3165 memory: 20094 grad_norm: 7.1029 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 15:08:29 - mmengine - INFO - Epoch(train) [10][200/389] lr: 1.0000e-04 eta: 2:32:55 time: 1.6662 data_time: 0.2744 memory: 20095 grad_norm: 6.7363 loss: 5.1851 loss_occ_0: 2.6576 loss_occ_1: 1.5425 loss_occ_2: 0.9851 2024/04/12 15:09:45 - mmengine - INFO - Epoch(train) [10][250/389] lr: 1.0000e-04 eta: 2:31:25 time: 1.5131 data_time: 0.0864 memory: 20280 grad_norm: 7.2085 loss: 5.8445 loss_occ_0: 3.0291 loss_occ_1: 1.7495 loss_occ_2: 1.0659 2024/04/12 15:11:04 - mmengine - INFO - Epoch(train) [10][300/389] lr: 1.0000e-04 eta: 2:30:01 time: 1.5922 data_time: 0.2617 memory: 20106 grad_norm: 6.8499 loss: 6.2101 loss_occ_0: 3.3365 loss_occ_1: 1.7888 loss_occ_2: 1.0848 2024/04/12 15:12:31 - mmengine - INFO - Epoch(train) [10][350/389] lr: 1.0000e-04 eta: 2:28:47 time: 1.7321 data_time: 0.1553 memory: 20010 grad_norm: 7.0631 loss: 5.7744 loss_occ_0: 3.0776 loss_occ_1: 1.6978 loss_occ_2: 0.9990 2024/04/12 15:13:33 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:13:33 - mmengine - INFO - Saving checkpoint at 10 epochs 2024/04/12 15:15:43 - mmengine - INFO - Epoch(train) [11][ 50/389] lr: 1.0000e-04 eta: 2:26:28 time: 1.7506 data_time: 0.2628 memory: 20126 grad_norm: 6.7944 loss: 6.1996 loss_occ_0: 3.2451 loss_occ_1: 1.8431 loss_occ_2: 1.1114 2024/04/12 15:17:05 - mmengine - INFO - Epoch(train) [11][100/389] lr: 1.0000e-04 eta: 2:25:07 time: 1.6338 data_time: 0.2749 memory: 20095 grad_norm: 6.3531 loss: 5.1772 loss_occ_0: 2.7536 loss_occ_1: 1.4958 loss_occ_2: 0.9279 2024/04/12 15:17:19 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:18:23 - mmengine - INFO - Epoch(train) [11][150/389] lr: 1.0000e-04 eta: 2:23:41 time: 1.5630 data_time: 0.2168 memory: 20109 grad_norm: 7.3121 loss: 5.4033 loss_occ_0: 2.7832 loss_occ_1: 1.5978 loss_occ_2: 1.0223 2024/04/12 15:19:45 - mmengine - INFO - Epoch(train) [11][200/389] lr: 1.0000e-04 eta: 2:22:21 time: 1.6427 data_time: 0.3704 memory: 19963 grad_norm: 6.8226 loss: 5.6307 loss_occ_0: 2.9867 loss_occ_1: 1.6781 loss_occ_2: 0.9659 2024/04/12 15:21:04 - mmengine - INFO - Epoch(train) [11][250/389] lr: 1.0000e-04 eta: 2:20:56 time: 1.5721 data_time: 0.0804 memory: 20044 grad_norm: 6.8813 loss: 5.3789 loss_occ_0: 2.8944 loss_occ_1: 1.5518 loss_occ_2: 0.9327 2024/04/12 15:22:19 - mmengine - INFO - Epoch(train) [11][300/389] lr: 1.0000e-04 eta: 2:19:28 time: 1.5126 data_time: 0.1164 memory: 20045 grad_norm: 7.3468 loss: 5.8009 loss_occ_0: 3.0865 loss_occ_1: 1.6905 loss_occ_2: 1.0239 2024/04/12 15:23:45 - mmengine - INFO - Epoch(train) [11][350/389] lr: 1.0000e-04 eta: 2:18:11 time: 1.7105 data_time: 0.1742 memory: 20117 grad_norm: 7.1727 loss: 13.1890 loss_occ_0: 6.9963 loss_occ_1: 3.6808 loss_occ_2: 2.5119 2024/04/12 15:24:45 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:24:45 - mmengine - INFO - Saving checkpoint at 11 epochs 2024/04/12 15:26:59 - mmengine - INFO - Epoch(train) [12][ 50/389] lr: 1.0000e-04 eta: 2:15:50 time: 1.7365 data_time: 0.3529 memory: 20092 grad_norm: 6.4457 loss: 6.0389 loss_occ_0: 3.1951 loss_occ_1: 1.7685 loss_occ_2: 1.0753 2024/04/12 15:28:24 - mmengine - INFO - Epoch(train) [12][100/389] lr: 1.0000e-04 eta: 2:14:32 time: 1.6966 data_time: 0.1813 memory: 20103 grad_norm: 6.7998 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 15:29:46 - mmengine - INFO - Epoch(train) [12][150/389] lr: 1.0000e-04 eta: 2:13:11 time: 1.6415 data_time: 0.3090 memory: 20048 grad_norm: 7.0036 loss: 5.1251 loss_occ_0: 2.6838 loss_occ_1: 1.5043 loss_occ_2: 0.9369 2024/04/12 15:30:59 - mmengine - INFO - Epoch(train) [12][200/389] lr: 1.0000e-04 eta: 2:11:41 time: 1.4612 data_time: 0.1581 memory: 20098 grad_norm: 6.3945 loss: 4.9890 loss_occ_0: 2.5889 loss_occ_1: 1.4861 loss_occ_2: 0.9140 2024/04/12 15:32:28 - mmengine - INFO - Epoch(train) [12][250/389] lr: 1.0000e-04 eta: 2:10:28 time: 1.7801 data_time: 0.1263 memory: 20081 grad_norm: 6.9610 loss: 5.0990 loss_occ_0: 2.6018 loss_occ_1: 1.5549 loss_occ_2: 0.9423 2024/04/12 15:33:46 - mmengine - INFO - Epoch(train) [12][300/389] lr: 1.0000e-04 eta: 2:09:03 time: 1.5653 data_time: 0.2471 memory: 19879 grad_norm: 7.2219 loss: 5.9532 loss_occ_0: 3.1690 loss_occ_1: 1.7325 loss_occ_2: 1.0516 2024/04/12 15:38:09 - mmengine - INFO - Epoch(train) [12][350/389] lr: 1.0000e-04 eta: 2:10:46 time: 5.2578 data_time: 0.0816 memory: 20029 grad_norm: 7.3209 loss: 5.1482 loss_occ_0: 2.6100 loss_occ_1: 1.5961 loss_occ_2: 0.9421 2024/04/12 15:39:13 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:39:13 - mmengine - INFO - Saving checkpoint at 12 epochs 2024/04/12 15:40:45 - mmengine - INFO - Epoch(val) [12][ 50/103] eta: 0:00:51 time: 0.9735 data_time: 0.8674 memory: 20076 2024/04/12 15:43:41 - mmengine - INFO - Epoch(val) [12][100/103] eta: 0:00:06 time: 3.5275 data_time: 3.4217 memory: 16130 2024/04/12 15:44:22 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.72580 | | floor | 0.67316 | | wall | 0.48201 | | chair | 0.48727 | | cabinet | 0.24062 | | door | 0.20406 | | table | 0.38580 | | couch | 0.39734 | | shelf | 0.37267 | | window | 0.24244 | | bed | 0.41435 | | curtain | 0.39344 | | desk | 0.20292 | | doorframe | 0.18486 | | plant | 0.31944 | | stairs | 0.33170 | | pillow | 0.31951 | | wardrobe | 0.05788 | | picture | 0.20360 | | bathtub | 0.55863 | | box | 0.10806 | | counter | 0.21863 | | bench | 0.14531 | | stand | 0.16119 | | rail | 0.11281 | | sink | 0.37406 | | clothes | 0.16959 | | mirror | 0.13619 | | toilet | 0.59258 | | refrigerator | 0.11741 | | lamp | 0.27835 | | book | 0.20379 | | dresser | 0.04363 | | stool | 0.08475 | | fireplace | 0.00062 | | tv | 0.15824 | | blanket | 0.19762 | | commode | 0.01175 | | washing machine | 0.13261 | | monitor | 0.46213 | | window frame | 0.01255 | | radiator | 0.35128 | | mat | 0.00566 | | shower | 0.00844 | | rack | 0.00066 | | towel | 0.15789 | | ottoman | 0.06540 | | column | 0.01850 | | blinds | 0.01190 | | stove | 0.09522 | | bar | 0.03624 | | pillar | 0.01152 | | bin | 0.30127 | | heater | 0.11831 | | clothes dryer | 0.00940 | | backpack | 0.19084 | | blackboard | 0.32144 | | decoration | 0.03038 | | roof | 0.00000 | | bag | 0.05560 | | steps | 0.06704 | | windowsill | 0.10689 | | cushion | 0.00829 | | carpet | 0.00000 | | copier | 0.06389 | | board | 0.00144 | | countertop | 0.01856 | | basket | 0.02217 | | mailbox | 0.00000 | | kitchen island | 0.00000 | | washbasin | 0.02299 | | bicycle | 0.04420 | | drawer | 0.02443 | | oven | 0.07836 | | piano | 0.00402 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.16713 | | microwave | 0.09798 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.16589 | +---------------------+---------+ 2024/04/12 15:44:22 - mmengine - INFO - Epoch(val) [12][103/103] empty: 0.7258 floor: 0.6732 wall: 0.4820 chair: 0.4873 cabinet: 0.2406 door: 0.2041 table: 0.3858 couch: 0.3973 shelf: 0.3727 window: 0.2424 bed: 0.4143 curtain: 0.3934 desk: 0.2029 doorframe: 0.1849 plant: 0.3194 stairs: 0.3317 pillow: 0.3195 wardrobe: 0.0579 picture: 0.2036 bathtub: 0.5586 box: 0.1081 counter: 0.2186 bench: 0.1453 stand: 0.1612 rail: 0.1128 sink: 0.3741 clothes: 0.1696 mirror: 0.1362 toilet: 0.5926 refrigerator: 0.1174 lamp: 0.2784 book: 0.2038 dresser: 0.0436 stool: 0.0847 fireplace: 0.0006 tv: 0.1582 blanket: 0.1976 commode: 0.0118 washing machine: 0.1326 monitor: 0.4621 window frame: 0.0126 radiator: 0.3513 mat: 0.0057 shower: 0.0084 rack: 0.0007 towel: 0.1579 ottoman: 0.0654 column: 0.0185 blinds: 0.0119 stove: 0.0952 bar: 0.0362 pillar: 0.0115 bin: 0.3013 heater: 0.1183 clothes dryer: 0.0094 backpack: 0.1908 blackboard: 0.3214 decoration: 0.0304 roof: 0.0000 bag: 0.0556 steps: 0.0670 windowsill: 0.1069 cushion: 0.0083 carpet: 0.0000 copier: 0.0639 board: 0.0014 countertop: 0.0186 basket: 0.0222 mailbox: 0.0000 kitchen island: 0.0000 washbasin: 0.0230 bicycle: 0.0442 drawer: 0.0244 oven: 0.0784 piano: 0.0040 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.1671 microwave: 0.0980 frame: 0.0000 data_time: 2.2225 time: 2.3286 2024/04/12 15:45:46 - mmengine - INFO - Epoch(train) [13][ 50/389] lr: 1.0000e-04 eta: 2:08:16 time: 1.6675 data_time: 0.1110 memory: 20068 grad_norm: 6.5919 loss: 4.7606 loss_occ_0: 2.4558 loss_occ_1: 1.4322 loss_occ_2: 0.8726 2024/04/12 15:47:13 - mmengine - INFO - Epoch(train) [13][100/389] lr: 1.0000e-04 eta: 2:06:57 time: 1.7484 data_time: 0.3084 memory: 20062 grad_norm: 6.6185 loss: 12.7320 loss_occ_0: 6.8575 loss_occ_1: 3.4876 loss_occ_2: 2.3869 2024/04/12 15:48:32 - mmengine - INFO - Epoch(train) [13][150/389] lr: 1.0000e-04 eta: 2:05:29 time: 1.5755 data_time: 0.2311 memory: 20120 grad_norm: 6.7517 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 15:49:58 - mmengine - INFO - Epoch(train) [13][200/389] lr: 1.0000e-04 eta: 2:04:08 time: 1.7238 data_time: 0.4488 memory: 19955 grad_norm: 6.9503 loss: 4.8958 loss_occ_0: 2.5506 loss_occ_1: 1.4458 loss_occ_2: 0.8994 2024/04/12 15:51:20 - mmengine - INFO - Epoch(train) [13][250/389] lr: 1.0000e-04 eta: 2:02:44 time: 1.6440 data_time: 0.4411 memory: 20049 grad_norm: 6.6201 loss: 5.0257 loss_occ_0: 2.6626 loss_occ_1: 1.4761 loss_occ_2: 0.8871 2024/04/12 15:52:38 - mmengine - INFO - Epoch(train) [13][300/389] lr: 1.0000e-04 eta: 2:01:16 time: 1.5578 data_time: 0.2535 memory: 20031 grad_norm: 6.8610 loss: 5.3174 loss_occ_0: 2.7231 loss_occ_1: 1.5895 loss_occ_2: 1.0048 2024/04/12 15:53:29 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:53:58 - mmengine - INFO - Epoch(train) [13][350/389] lr: 1.0000e-04 eta: 1:59:50 time: 1.6058 data_time: 0.0767 memory: 20106 grad_norm: 7.5303 loss: 5.3510 loss_occ_0: 2.8461 loss_occ_1: 1.5839 loss_occ_2: 0.9210 2024/04/12 15:55:01 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 15:55:01 - mmengine - INFO - Saving checkpoint at 13 epochs 2024/04/12 15:57:10 - mmengine - INFO - Epoch(train) [14][ 50/389] lr: 1.0000e-04 eta: 1:57:22 time: 1.7083 data_time: 0.0832 memory: 20202 grad_norm: 6.7449 loss: 5.1025 loss_occ_0: 2.7162 loss_occ_1: 1.4923 loss_occ_2: 0.8940 2024/04/12 15:58:30 - mmengine - INFO - Epoch(train) [14][100/389] lr: 1.0000e-04 eta: 1:55:56 time: 1.6038 data_time: 0.1151 memory: 20174 grad_norm: 7.2084 loss: 5.0918 loss_occ_0: 2.7222 loss_occ_1: 1.4646 loss_occ_2: 0.9050 2024/04/12 15:59:49 - mmengine - INFO - Epoch(train) [14][150/389] lr: 1.0000e-04 eta: 1:54:29 time: 1.5783 data_time: 0.3162 memory: 19956 grad_norm: 7.2932 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 16:01:09 - mmengine - INFO - Epoch(train) [14][200/389] lr: 1.0000e-04 eta: 1:53:03 time: 1.5865 data_time: 0.1031 memory: 19977 grad_norm: 7.3344 loss: 5.7793 loss_occ_0: 2.8456 loss_occ_1: 1.5337 loss_occ_2: 1.3999 2024/04/12 16:02:29 - mmengine - INFO - Epoch(train) [14][250/389] lr: 1.0000e-04 eta: 1:51:38 time: 1.6103 data_time: 0.1586 memory: 20194 grad_norm: 6.8772 loss: 4.8247 loss_occ_0: 2.5298 loss_occ_1: 1.4114 loss_occ_2: 0.8835 2024/04/12 16:03:48 - mmengine - INFO - Epoch(train) [14][300/389] lr: 1.0000e-04 eta: 1:50:12 time: 1.5795 data_time: 0.0953 memory: 20173 grad_norm: 6.7143 loss: 4.7341 loss_occ_0: 2.5099 loss_occ_1: 1.3487 loss_occ_2: 0.8756 2024/04/12 16:05:13 - mmengine - INFO - Epoch(train) [14][350/389] lr: 1.0000e-04 eta: 1:48:50 time: 1.6907 data_time: 0.1663 memory: 20047 grad_norm: 7.4195 loss: 5.6090 loss_occ_0: 2.9601 loss_occ_1: 1.6680 loss_occ_2: 0.9808 2024/04/12 16:06:15 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:06:15 - mmengine - INFO - Saving checkpoint at 14 epochs 2024/04/12 16:08:19 - mmengine - INFO - Epoch(train) [15][ 50/389] lr: 1.0000e-04 eta: 1:46:16 time: 1.5422 data_time: 0.1857 memory: 20093 grad_norm: 6.4554 loss: 11.5650 loss_occ_0: 6.3815 loss_occ_1: 3.3607 loss_occ_2: 1.8228 2024/04/12 16:09:43 - mmengine - INFO - Epoch(train) [15][100/389] lr: 1.0000e-04 eta: 1:44:54 time: 1.6791 data_time: 0.2071 memory: 20027 grad_norm: 7.4369 loss: 4.7198 loss_occ_0: 2.4336 loss_occ_1: 1.4032 loss_occ_2: 0.8830 2024/04/12 16:11:03 - mmengine - INFO - Epoch(train) [15][150/389] lr: 1.0000e-04 eta: 1:43:29 time: 1.6062 data_time: 0.3802 memory: 20279 grad_norm: 6.4454 loss: 5.2872 loss_occ_0: 2.8419 loss_occ_1: 1.5090 loss_occ_2: 0.9363 2024/04/12 16:12:23 - mmengine - INFO - Epoch(train) [15][200/389] lr: 1.0000e-04 eta: 1:42:04 time: 1.5897 data_time: 0.1759 memory: 20057 grad_norm: 6.5047 loss: 4.8612 loss_occ_0: 2.5847 loss_occ_1: 1.4320 loss_occ_2: 0.8445 2024/04/12 16:13:44 - mmengine - INFO - Epoch(train) [15][250/389] lr: 1.0000e-04 eta: 1:40:40 time: 1.6291 data_time: 0.3309 memory: 20078 grad_norm: 8.6027 loss: 5.2474 loss_occ_0: 2.7887 loss_occ_1: 1.4926 loss_occ_2: 0.9661 2024/04/12 16:15:02 - mmengine - INFO - Epoch(train) [15][300/389] lr: 1.0000e-04 eta: 1:39:13 time: 1.5578 data_time: 0.4118 memory: 20129 grad_norm: 6.8634 loss: 4.6945 loss_occ_0: 2.4559 loss_occ_1: 1.3937 loss_occ_2: 0.8449 2024/04/12 16:16:25 - mmengine - INFO - Epoch(train) [15][350/389] lr: 1.0000e-04 eta: 1:37:50 time: 1.6549 data_time: 0.0835 memory: 20084 grad_norm: 6.9695 loss: 4.7695 loss_occ_0: 2.4992 loss_occ_1: 1.4420 loss_occ_2: 0.8282 2024/04/12 16:17:32 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:17:32 - mmengine - INFO - Saving checkpoint at 15 epochs 2024/04/12 16:19:39 - mmengine - INFO - Epoch(train) [16][ 50/389] lr: 1.0000e-04 eta: 1:35:23 time: 1.6014 data_time: 0.2583 memory: 20089 grad_norm: 6.5931 loss: 5.0560 loss_occ_0: 2.4500 loss_occ_1: 1.3120 loss_occ_2: 1.2940 2024/04/12 16:21:05 - mmengine - INFO - Epoch(train) [16][100/389] lr: 1.0000e-04 eta: 1:34:01 time: 1.7106 data_time: 0.1552 memory: 20028 grad_norm: 6.7603 loss: 5.1488 loss_occ_0: 2.7320 loss_occ_1: 1.4813 loss_occ_2: 0.9355 2024/04/12 16:22:22 - mmengine - INFO - Epoch(train) [16][150/389] lr: 1.0000e-04 eta: 1:32:35 time: 1.5536 data_time: 0.1727 memory: 20058 grad_norm: 7.3182 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 16:22:46 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:23:41 - mmengine - INFO - Epoch(train) [16][200/389] lr: 1.0000e-04 eta: 1:31:10 time: 1.5806 data_time: 0.1571 memory: 20114 grad_norm: 6.9469 loss: 12.6640 loss_occ_0: 7.1062 loss_occ_1: 3.6417 loss_occ_2: 1.9162 2024/04/12 16:25:00 - mmengine - INFO - Epoch(train) [16][250/389] lr: 1.0000e-04 eta: 1:29:45 time: 1.5644 data_time: 0.2072 memory: 20234 grad_norm: 6.4205 loss: 5.0267 loss_occ_0: 2.6029 loss_occ_1: 1.4988 loss_occ_2: 0.9250 2024/04/12 16:26:23 - mmengine - INFO - Epoch(train) [16][300/389] lr: 1.0000e-04 eta: 1:28:22 time: 1.6611 data_time: 0.1213 memory: 20067 grad_norm: 6.4526 loss: 4.6187 loss_occ_0: 2.4276 loss_occ_1: 1.3485 loss_occ_2: 0.8426 2024/04/12 16:27:43 - mmengine - INFO - Epoch(train) [16][350/389] lr: 1.0000e-04 eta: 1:26:58 time: 1.6171 data_time: 0.2009 memory: 20021 grad_norm: 6.7097 loss: 11.8500 loss_occ_0: 6.4976 loss_occ_1: 3.4797 loss_occ_2: 1.8727 2024/04/12 16:28:50 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:28:50 - mmengine - INFO - Saving checkpoint at 16 epochs 2024/04/12 16:30:23 - mmengine - INFO - Epoch(val) [16][ 50/103] eta: 0:00:50 time: 0.9615 data_time: 0.8542 memory: 20025 2024/04/12 16:33:19 - mmengine - INFO - Epoch(val) [16][100/103] eta: 0:00:06 time: 3.5185 data_time: 3.4130 memory: 16130 2024/04/12 16:34:01 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.73213 | | floor | 0.69702 | | wall | 0.51497 | | chair | 0.49067 | | cabinet | 0.25249 | | door | 0.27650 | | table | 0.38981 | | couch | 0.39419 | | shelf | 0.40535 | | window | 0.27270 | | bed | 0.44915 | | curtain | 0.45647 | | desk | 0.13761 | | doorframe | 0.21342 | | plant | 0.35987 | | stairs | 0.36999 | | pillow | 0.33189 | | wardrobe | 0.05881 | | picture | 0.22383 | | bathtub | 0.51049 | | box | 0.12353 | | counter | 0.24290 | | bench | 0.15637 | | stand | 0.16571 | | rail | 0.17090 | | sink | 0.41691 | | clothes | 0.18607 | | mirror | 0.16343 | | toilet | 0.57251 | | refrigerator | 0.08869 | | lamp | 0.28568 | | book | 0.13477 | | dresser | 0.06638 | | stool | 0.10814 | | fireplace | 0.01523 | | tv | 0.23217 | | blanket | 0.21297 | | commode | 0.07206 | | washing machine | 0.13777 | | monitor | 0.50246 | | window frame | 0.01375 | | radiator | 0.39402 | | mat | 0.03039 | | shower | 0.01406 | | rack | 0.00199 | | towel | 0.19974 | | ottoman | 0.12191 | | column | 0.04201 | | blinds | 0.00000 | | stove | 0.16316 | | bar | 0.12393 | | pillar | 0.00586 | | bin | 0.34652 | | heater | 0.13739 | | clothes dryer | 0.03279 | | backpack | 0.21506 | | blackboard | 0.35644 | | decoration | 0.02434 | | roof | 0.00000 | | bag | 0.05040 | | steps | 0.09351 | | windowsill | 0.17284 | | cushion | 0.00855 | | carpet | 0.00128 | | copier | 0.28501 | | board | 0.00993 | | countertop | 0.02946 | | basket | 0.05735 | | mailbox | 0.00000 | | kitchen island | 0.02814 | | washbasin | 0.01302 | | bicycle | 0.10363 | | drawer | 0.00284 | | oven | 0.07717 | | piano | 0.05279 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.21383 | | microwave | 0.14596 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.18717 | +---------------------+---------+ 2024/04/12 16:34:01 - mmengine - INFO - Epoch(val) [16][103/103] empty: 0.7321 floor: 0.6970 wall: 0.5150 chair: 0.4907 cabinet: 0.2525 door: 0.2765 table: 0.3898 couch: 0.3942 shelf: 0.4053 window: 0.2727 bed: 0.4491 curtain: 0.4565 desk: 0.1376 doorframe: 0.2134 plant: 0.3599 stairs: 0.3700 pillow: 0.3319 wardrobe: 0.0588 picture: 0.2238 bathtub: 0.5105 box: 0.1235 counter: 0.2429 bench: 0.1564 stand: 0.1657 rail: 0.1709 sink: 0.4169 clothes: 0.1861 mirror: 0.1634 toilet: 0.5725 refrigerator: 0.0887 lamp: 0.2857 book: 0.1348 dresser: 0.0664 stool: 0.1081 fireplace: 0.0152 tv: 0.2322 blanket: 0.2130 commode: 0.0721 washing machine: 0.1378 monitor: 0.5025 window frame: 0.0138 radiator: 0.3940 mat: 0.0304 shower: 0.0141 rack: 0.0020 towel: 0.1997 ottoman: 0.1219 column: 0.0420 blinds: 0.0000 stove: 0.1632 bar: 0.1239 pillar: 0.0059 bin: 0.3465 heater: 0.1374 clothes dryer: 0.0328 backpack: 0.2151 blackboard: 0.3564 decoration: 0.0243 roof: 0.0000 bag: 0.0504 steps: 0.0935 windowsill: 0.1728 cushion: 0.0085 carpet: 0.0013 copier: 0.2850 board: 0.0099 countertop: 0.0295 basket: 0.0573 mailbox: 0.0000 kitchen island: 0.0281 washbasin: 0.0130 bicycle: 0.1036 drawer: 0.0028 oven: 0.0772 piano: 0.0528 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.2138 microwave: 0.1460 frame: 0.0000 data_time: 2.2132 time: 2.3197 2024/04/12 16:35:23 - mmengine - INFO - Epoch(train) [17][ 50/389] lr: 1.0000e-05 eta: 1:24:32 time: 1.6432 data_time: 0.1825 memory: 20304 grad_norm: 6.1446 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 16:36:43 - mmengine - INFO - Epoch(train) [17][100/389] lr: 1.0000e-05 eta: 1:23:07 time: 1.6004 data_time: 0.0968 memory: 20142 grad_norm: 6.4958 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 16:38:01 - mmengine - INFO - Epoch(train) [17][150/389] lr: 1.0000e-05 eta: 1:21:42 time: 1.5627 data_time: 0.1245 memory: 20021 grad_norm: 6.0727 loss: 4.7118 loss_occ_0: 2.4881 loss_occ_1: 1.3784 loss_occ_2: 0.8453 2024/04/12 16:39:27 - mmengine - INFO - Epoch(train) [17][200/389] lr: 1.0000e-05 eta: 1:20:21 time: 1.7231 data_time: 0.2054 memory: 19984 grad_norm: 6.2356 loss: 4.3503 loss_occ_0: 2.3973 loss_occ_1: 1.2200 loss_occ_2: 0.7329 2024/04/12 16:40:51 - mmengine - INFO - Epoch(train) [17][250/389] lr: 1.0000e-05 eta: 1:18:59 time: 1.6775 data_time: 0.1119 memory: 20129 grad_norm: 5.8443 loss: 4.6865 loss_occ_0: 2.4860 loss_occ_1: 1.3540 loss_occ_2: 0.8464 2024/04/12 16:42:13 - mmengine - INFO - Epoch(train) [17][300/389] lr: 1.0000e-05 eta: 1:17:36 time: 1.6376 data_time: 0.1478 memory: 20067 grad_norm: 5.9552 loss: 4.0902 loss_occ_0: 2.1243 loss_occ_1: 1.1985 loss_occ_2: 0.7674 2024/04/12 16:43:30 - mmengine - INFO - Epoch(train) [17][350/389] lr: 1.0000e-05 eta: 1:16:10 time: 1.5318 data_time: 0.1667 memory: 20098 grad_norm: 5.8010 loss: 4.3028 loss_occ_0: 2.2848 loss_occ_1: 1.2601 loss_occ_2: 0.7579 2024/04/12 16:44:33 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:44:33 - mmengine - INFO - Saving checkpoint at 17 epochs 2024/04/12 16:46:37 - mmengine - INFO - Epoch(train) [18][ 50/389] lr: 1.0000e-05 eta: 1:13:42 time: 1.6156 data_time: 0.1402 memory: 20222 grad_norm: 6.2155 loss: 3.9175 loss_occ_0: 2.0953 loss_occ_1: 1.1208 loss_occ_2: 0.7014 2024/04/12 16:48:01 - mmengine - INFO - Epoch(train) [18][100/389] lr: 1.0000e-05 eta: 1:12:20 time: 1.6802 data_time: 0.0746 memory: 20052 grad_norm: 6.1719 loss: 4.0496 loss_occ_0: 2.1146 loss_occ_1: 1.1787 loss_occ_2: 0.7563 2024/04/12 16:49:20 - mmengine - INFO - Epoch(train) [18][150/389] lr: 1.0000e-05 eta: 1:10:56 time: 1.5856 data_time: 0.1089 memory: 20098 grad_norm: 5.9442 loss: 4.0227 loss_occ_0: 2.1609 loss_occ_1: 1.1644 loss_occ_2: 0.6975 2024/04/12 16:50:48 - mmengine - INFO - Epoch(train) [18][200/389] lr: 1.0000e-05 eta: 1:09:35 time: 1.7574 data_time: 0.1319 memory: 20063 grad_norm: 6.0904 loss: 4.5872 loss_occ_0: 2.1748 loss_occ_1: 1.1909 loss_occ_2: 1.2215 2024/04/12 16:52:08 - mmengine - INFO - Epoch(train) [18][250/389] lr: 1.0000e-05 eta: 1:08:11 time: 1.5994 data_time: 0.3074 memory: 20034 grad_norm: 5.7812 loss: 3.9857 loss_occ_0: 2.1001 loss_occ_1: 1.1706 loss_occ_2: 0.7150 2024/04/12 16:53:31 - mmengine - INFO - Epoch(train) [18][300/389] lr: 1.0000e-05 eta: 1:06:49 time: 1.6663 data_time: 0.2578 memory: 20211 grad_norm: 6.1810 loss: 4.5674 loss_occ_0: 2.0594 loss_occ_1: 1.2504 loss_occ_2: 1.2575 2024/04/12 16:54:56 - mmengine - INFO - Epoch(train) [18][350/389] lr: 1.0000e-05 eta: 1:05:26 time: 1.6913 data_time: 0.3391 memory: 20190 grad_norm: 6.1951 loss: 4.2810 loss_occ_0: 2.2484 loss_occ_1: 1.2647 loss_occ_2: 0.7679 2024/04/12 16:55:58 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:56:00 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 16:56:00 - mmengine - INFO - Saving checkpoint at 18 epochs 2024/04/12 16:58:14 - mmengine - INFO - Epoch(train) [19][ 50/389] lr: 1.0000e-05 eta: 1:03:00 time: 1.7307 data_time: 0.1861 memory: 20177 grad_norm: 5.9070 loss: 3.8213 loss_occ_0: 2.0245 loss_occ_1: 1.1163 loss_occ_2: 0.6806 2024/04/12 16:59:37 - mmengine - INFO - Epoch(train) [19][100/389] lr: 1.0000e-05 eta: 1:01:38 time: 1.6638 data_time: 0.1628 memory: 20101 grad_norm: 5.9267 loss: 3.9708 loss_occ_0: 2.0999 loss_occ_1: 1.1741 loss_occ_2: 0.6968 2024/04/12 17:00:59 - mmengine - INFO - Epoch(train) [19][150/389] lr: 1.0000e-05 eta: 1:00:15 time: 1.6426 data_time: 0.1813 memory: 20030 grad_norm: 6.1277 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 17:02:22 - mmengine - INFO - Epoch(train) [19][200/389] lr: 1.0000e-05 eta: 0:58:52 time: 1.6600 data_time: 0.0811 memory: 20067 grad_norm: 5.9482 loss: 3.9103 loss_occ_0: 2.0190 loss_occ_1: 1.1774 loss_occ_2: 0.7139 2024/04/12 17:03:44 - mmengine - INFO - Epoch(train) [19][250/389] lr: 1.0000e-05 eta: 0:57:29 time: 1.6313 data_time: 0.0670 memory: 20040 grad_norm: 5.8946 loss: 3.9536 loss_occ_0: 2.0943 loss_occ_1: 1.1701 loss_occ_2: 0.6892 2024/04/12 17:05:03 - mmengine - INFO - Epoch(train) [19][300/389] lr: 1.0000e-05 eta: 0:56:05 time: 1.5795 data_time: 0.1035 memory: 20106 grad_norm: 6.1725 loss: 4.1614 loss_occ_0: 2.2471 loss_occ_1: 1.2022 loss_occ_2: 0.7121 2024/04/12 17:06:23 - mmengine - INFO - Epoch(train) [19][350/389] lr: 1.0000e-05 eta: 0:54:42 time: 1.5955 data_time: 0.1047 memory: 19974 grad_norm: 6.1456 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 17:07:28 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:07:28 - mmengine - INFO - Saving checkpoint at 19 epochs 2024/04/12 17:09:37 - mmengine - INFO - Epoch(train) [20][ 50/389] lr: 1.0000e-05 eta: 0:52:15 time: 1.6595 data_time: 0.1648 memory: 20007 grad_norm: 5.8923 loss: 10.9320 loss_occ_0: 6.0827 loss_occ_1: 3.1409 loss_occ_2: 1.7084 2024/04/12 17:10:58 - mmengine - INFO - Epoch(train) [20][100/389] lr: 1.0000e-05 eta: 0:50:52 time: 1.6230 data_time: 0.0715 memory: 20093 grad_norm: 6.5165 loss: 4.1210 loss_occ_0: 2.1112 loss_occ_1: 1.2458 loss_occ_2: 0.7641 2024/04/12 17:12:15 - mmengine - INFO - Epoch(train) [20][150/389] lr: 1.0000e-05 eta: 0:49:27 time: 1.5337 data_time: 0.1381 memory: 20225 grad_norm: 6.3336 loss: 4.3270 loss_occ_0: 2.2842 loss_occ_1: 1.2889 loss_occ_2: 0.7540 2024/04/12 17:13:40 - mmengine - INFO - Epoch(train) [20][200/389] lr: 1.0000e-05 eta: 0:48:05 time: 1.6903 data_time: 0.2526 memory: 20079 grad_norm: 6.1971 loss: 4.4100 loss_occ_0: 2.3595 loss_occ_1: 1.2658 loss_occ_2: 0.7847 2024/04/12 17:15:00 - mmengine - INFO - Epoch(train) [20][250/389] lr: 1.0000e-05 eta: 0:46:42 time: 1.6048 data_time: 0.3128 memory: 20115 grad_norm: 5.7228 loss: 3.8940 loss_occ_0: 2.0056 loss_occ_1: 1.1582 loss_occ_2: 0.7302 2024/04/12 17:16:21 - mmengine - INFO - Epoch(train) [20][300/389] lr: 1.0000e-05 eta: 0:45:19 time: 1.6256 data_time: 0.0837 memory: 19983 grad_norm: 6.4606 loss: 9.9701 loss_occ_0: 6.0485 loss_occ_1: 3.1283 loss_occ_2: 0.7933 2024/04/12 17:17:43 - mmengine - INFO - Epoch(train) [20][350/389] lr: 1.0000e-05 eta: 0:43:56 time: 1.6453 data_time: 0.1321 memory: 19995 grad_norm: 6.0928 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 17:18:46 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:18:46 - mmengine - INFO - Saving checkpoint at 20 epochs 2024/04/12 17:20:20 - mmengine - INFO - Epoch(val) [20][ 50/103] eta: 0:00:50 time: 0.9548 data_time: 0.8493 memory: 19966 2024/04/12 17:23:15 - mmengine - INFO - Epoch(val) [20][100/103] eta: 0:00:06 time: 3.4983 data_time: 3.3918 memory: 16130 2024/04/12 17:23:56 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.74374 | | floor | 0.71369 | | wall | 0.53650 | | chair | 0.53947 | | cabinet | 0.28896 | | door | 0.30292 | | table | 0.41399 | | couch | 0.45407 | | shelf | 0.42382 | | window | 0.27317 | | bed | 0.49758 | | curtain | 0.48893 | | desk | 0.31096 | | doorframe | 0.22136 | | plant | 0.36922 | | stairs | 0.34375 | | pillow | 0.36019 | | wardrobe | 0.09416 | | picture | 0.25220 | | bathtub | 0.58412 | | box | 0.18394 | | counter | 0.26257 | | bench | 0.16913 | | stand | 0.20886 | | rail | 0.20207 | | sink | 0.42714 | | clothes | 0.22719 | | mirror | 0.15670 | | toilet | 0.63358 | | refrigerator | 0.15021 | | lamp | 0.33999 | | book | 0.23783 | | dresser | 0.07091 | | stool | 0.12787 | | fireplace | 0.03520 | | tv | 0.25481 | | blanket | 0.23265 | | commode | 0.03187 | | washing machine | 0.26667 | | monitor | 0.51293 | | window frame | 0.01343 | | radiator | 0.38885 | | mat | 0.01067 | | shower | 0.01318 | | rack | 0.00175 | | towel | 0.24216 | | ottoman | 0.14175 | | column | 0.04184 | | blinds | 0.02159 | | stove | 0.20058 | | bar | 0.21178 | | pillar | 0.03173 | | bin | 0.38807 | | heater | 0.18112 | | clothes dryer | 0.03358 | | backpack | 0.23543 | | blackboard | 0.35149 | | decoration | 0.04080 | | roof | 0.00000 | | bag | 0.08260 | | steps | 0.11321 | | windowsill | 0.17636 | | cushion | 0.02676 | | carpet | 0.05762 | | copier | 0.32416 | | board | 0.01077 | | countertop | 0.03140 | | basket | 0.06941 | | mailbox | 0.00000 | | kitchen island | 0.02556 | | washbasin | 0.00556 | | bicycle | 0.07968 | | drawer | 0.02068 | | oven | 0.13706 | | piano | 0.07364 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.31348 | | microwave | 0.16891 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.21249 | +---------------------+---------+ 2024/04/12 17:23:56 - mmengine - INFO - Epoch(val) [20][103/103] empty: 0.7437 floor: 0.7137 wall: 0.5365 chair: 0.5395 cabinet: 0.2890 door: 0.3029 table: 0.4140 couch: 0.4541 shelf: 0.4238 window: 0.2732 bed: 0.4976 curtain: 0.4889 desk: 0.3110 doorframe: 0.2214 plant: 0.3692 stairs: 0.3438 pillow: 0.3602 wardrobe: 0.0942 picture: 0.2522 bathtub: 0.5841 box: 0.1839 counter: 0.2626 bench: 0.1691 stand: 0.2089 rail: 0.2021 sink: 0.4271 clothes: 0.2272 mirror: 0.1567 toilet: 0.6336 refrigerator: 0.1502 lamp: 0.3400 book: 0.2378 dresser: 0.0709 stool: 0.1279 fireplace: 0.0352 tv: 0.2548 blanket: 0.2326 commode: 0.0319 washing machine: 0.2667 monitor: 0.5129 window frame: 0.0134 radiator: 0.3889 mat: 0.0107 shower: 0.0132 rack: 0.0018 towel: 0.2422 ottoman: 0.1418 column: 0.0418 blinds: 0.0216 stove: 0.2006 bar: 0.2118 pillar: 0.0317 bin: 0.3881 heater: 0.1811 clothes dryer: 0.0336 backpack: 0.2354 blackboard: 0.3515 decoration: 0.0408 roof: 0.0000 bag: 0.0826 steps: 0.1132 windowsill: 0.1764 cushion: 0.0268 carpet: 0.0576 copier: 0.3242 board: 0.0108 countertop: 0.0314 basket: 0.0694 mailbox: 0.0000 kitchen island: 0.0256 washbasin: 0.0056 bicycle: 0.0797 drawer: 0.0207 oven: 0.1371 piano: 0.0736 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.3135 microwave: 0.1689 frame: 0.0000 data_time: 2.2000 time: 2.3061 2024/04/12 17:25:26 - mmengine - INFO - Epoch(train) [21][ 50/389] lr: 1.0000e-05 eta: 0:41:30 time: 1.8085 data_time: 0.4632 memory: 20021 grad_norm: 5.8937 loss: 4.0941 loss_occ_0: 2.2121 loss_occ_1: 1.1881 loss_occ_2: 0.6940 2024/04/12 17:26:46 - mmengine - INFO - Epoch(train) [21][100/389] lr: 1.0000e-05 eta: 0:40:07 time: 1.5940 data_time: 0.1571 memory: 20165 grad_norm: 6.0705 loss: 4.1955 loss_occ_0: 2.2085 loss_occ_1: 1.2225 loss_occ_2: 0.7644 2024/04/12 17:28:10 - mmengine - INFO - Epoch(train) [21][150/389] lr: 1.0000e-05 eta: 0:38:45 time: 1.6909 data_time: 0.2379 memory: 20173 grad_norm: 6.6005 loss: 4.6816 loss_occ_0: 2.1650 loss_occ_1: 1.2750 loss_occ_2: 1.2415 2024/04/12 17:29:34 - mmengine - INFO - Epoch(train) [21][200/389] lr: 1.0000e-05 eta: 0:37:22 time: 1.6765 data_time: 0.4110 memory: 19990 grad_norm: 6.4794 loss: 4.2677 loss_occ_0: 2.2418 loss_occ_1: 1.2633 loss_occ_2: 0.7625 2024/04/12 17:30:06 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:30:55 - mmengine - INFO - Epoch(train) [21][250/389] lr: 1.0000e-05 eta: 0:35:59 time: 1.6060 data_time: 0.2770 memory: 20140 grad_norm: 6.1643 loss: 10.9700 loss_occ_0: 6.0796 loss_occ_1: 3.1368 loss_occ_2: 1.7535 2024/04/12 17:32:13 - mmengine - INFO - Epoch(train) [21][300/389] lr: 1.0000e-05 eta: 0:34:36 time: 1.5716 data_time: 0.1128 memory: 20223 grad_norm: 6.1998 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 17:33:37 - mmengine - INFO - Epoch(train) [21][350/389] lr: 1.0000e-05 eta: 0:33:13 time: 1.6810 data_time: 0.1649 memory: 20069 grad_norm: 6.1593 loss: 3.9506 loss_occ_0: 2.1165 loss_occ_1: 1.1298 loss_occ_2: 0.7043 2024/04/12 17:34:40 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:34:40 - mmengine - INFO - Saving checkpoint at 21 epochs 2024/04/12 17:36:45 - mmengine - INFO - Epoch(train) [22][ 50/389] lr: 1.0000e-05 eta: 0:30:46 time: 1.6057 data_time: 0.0819 memory: 20005 grad_norm: 6.8111 loss: 5.8885 loss_occ_0: 2.3302 loss_occ_1: 2.2676 loss_occ_2: 1.2907 2024/04/12 17:38:07 - mmengine - INFO - Epoch(train) [22][100/389] lr: 1.0000e-05 eta: 0:29:23 time: 1.6407 data_time: 0.1226 memory: 19986 grad_norm: 6.3438 loss: 4.1353 loss_occ_0: 2.2407 loss_occ_1: 1.1548 loss_occ_2: 0.7398 2024/04/12 17:39:26 - mmengine - INFO - Epoch(train) [22][150/389] lr: 1.0000e-05 eta: 0:28:00 time: 1.5805 data_time: 0.2545 memory: 20049 grad_norm: 6.7000 loss: 3.8444 loss_occ_0: 1.9877 loss_occ_1: 1.1384 loss_occ_2: 0.7183 2024/04/12 17:40:49 - mmengine - INFO - Epoch(train) [22][200/389] lr: 1.0000e-05 eta: 0:26:37 time: 1.6493 data_time: 0.2695 memory: 20080 grad_norm: 6.2048 loss: 4.1037 loss_occ_0: 2.2222 loss_occ_1: 1.1213 loss_occ_2: 0.7602 2024/04/12 17:42:06 - mmengine - INFO - Epoch(train) [22][250/389] lr: 1.0000e-05 eta: 0:25:14 time: 1.5346 data_time: 0.1985 memory: 20057 grad_norm: 6.3510 loss: 4.1535 loss_occ_0: 2.1962 loss_occ_1: 1.2325 loss_occ_2: 0.7248 2024/04/12 17:43:28 - mmengine - INFO - Epoch(train) [22][300/389] lr: 1.0000e-05 eta: 0:23:51 time: 1.6547 data_time: 0.0859 memory: 20012 grad_norm: 6.3449 loss: 3.9962 loss_occ_0: 2.1038 loss_occ_1: 1.1713 loss_occ_2: 0.7211 2024/04/12 17:44:51 - mmengine - INFO - Epoch(train) [22][350/389] lr: 1.0000e-05 eta: 0:22:29 time: 1.6474 data_time: 0.1263 memory: 20092 grad_norm: 5.8144 loss: 3.6609 loss_occ_0: 1.8950 loss_occ_1: 1.0799 loss_occ_2: 0.6861 2024/04/12 17:45:55 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:45:55 - mmengine - INFO - Saving checkpoint at 22 epochs 2024/04/12 17:47:57 - mmengine - INFO - Epoch(train) [23][ 50/389] lr: 1.0000e-06 eta: 0:20:02 time: 1.5958 data_time: 0.2050 memory: 20085 grad_norm: 5.8915 loss: 4.1709 loss_occ_0: 2.2136 loss_occ_1: 1.2166 loss_occ_2: 0.7407 2024/04/12 17:49:20 - mmengine - INFO - Epoch(train) [23][100/389] lr: 1.0000e-06 eta: 0:18:39 time: 1.6485 data_time: 0.0926 memory: 19978 grad_norm: 6.4481 loss: 3.8965 loss_occ_0: 2.0610 loss_occ_1: 1.1600 loss_occ_2: 0.6756 2024/04/12 17:50:42 - mmengine - INFO - Epoch(train) [23][150/389] lr: 1.0000e-06 eta: 0:17:16 time: 1.6587 data_time: 0.3766 memory: 20062 grad_norm: 5.7585 loss: 4.1211 loss_occ_0: 2.2264 loss_occ_1: 1.1707 loss_occ_2: 0.7240 2024/04/12 17:52:03 - mmengine - INFO - Epoch(train) [23][200/389] lr: 1.0000e-06 eta: 0:15:54 time: 1.6101 data_time: 0.1391 memory: 20022 grad_norm: 6.0261 loss: 3.8687 loss_occ_0: 2.1118 loss_occ_1: 1.0917 loss_occ_2: 0.6652 2024/04/12 17:53:27 - mmengine - INFO - Epoch(train) [23][250/389] lr: 1.0000e-06 eta: 0:14:31 time: 1.6705 data_time: 0.3276 memory: 20164 grad_norm: 6.5913 loss: 4.1867 loss_occ_0: 2.2545 loss_occ_1: 1.2165 loss_occ_2: 0.7157 2024/04/12 17:54:52 - mmengine - INFO - Epoch(train) [23][300/389] lr: 1.0000e-06 eta: 0:13:09 time: 1.7115 data_time: 0.4065 memory: 20077 grad_norm: 6.7157 loss: 4.9211 loss_occ_0: 2.0742 loss_occ_1: 1.1607 loss_occ_2: 1.6863 2024/04/12 17:56:14 - mmengine - INFO - Epoch(train) [23][350/389] lr: 1.0000e-06 eta: 0:11:46 time: 1.6426 data_time: 0.1564 memory: 20070 grad_norm: 6.4410 loss: nan loss_occ_0: nan loss_occ_1: nan loss_occ_2: nan 2024/04/12 17:57:21 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 17:57:21 - mmengine - INFO - Saving checkpoint at 23 epochs 2024/04/12 17:59:25 - mmengine - INFO - Epoch(train) [24][ 50/389] lr: 1.0000e-06 eta: 0:09:19 time: 1.6362 data_time: 0.1027 memory: 20102 grad_norm: 6.1818 loss: 3.4503 loss_occ_0: 1.7492 loss_occ_1: 1.0428 loss_occ_2: 0.6583 2024/04/12 17:59:30 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 18:00:45 - mmengine - INFO - Epoch(train) [24][100/389] lr: 1.0000e-06 eta: 0:07:57 time: 1.6020 data_time: 0.1808 memory: 20037 grad_norm: 5.7639 loss: 4.0301 loss_occ_0: 2.0641 loss_occ_1: 1.1879 loss_occ_2: 0.7781 2024/04/12 18:02:08 - mmengine - INFO - Epoch(train) [24][150/389] lr: 1.0000e-06 eta: 0:06:34 time: 1.6708 data_time: 0.1856 memory: 20147 grad_norm: 6.0563 loss: 3.8548 loss_occ_0: 2.0265 loss_occ_1: 1.1138 loss_occ_2: 0.7144 2024/04/12 18:03:31 - mmengine - INFO - Epoch(train) [24][200/389] lr: 1.0000e-06 eta: 0:05:12 time: 1.6528 data_time: 0.2161 memory: 20094 grad_norm: 6.1911 loss: 4.6468 loss_occ_0: 2.2522 loss_occ_1: 1.1895 loss_occ_2: 1.2051 2024/04/12 18:04:57 - mmengine - INFO - Epoch(train) [24][250/389] lr: 1.0000e-06 eta: 0:03:49 time: 1.7174 data_time: 0.0876 memory: 20078 grad_norm: 6.7192 loss: 4.5153 loss_occ_0: 2.1085 loss_occ_1: 1.1870 loss_occ_2: 1.2198 2024/04/12 18:06:21 - mmengine - INFO - Epoch(train) [24][300/389] lr: 1.0000e-06 eta: 0:02:27 time: 1.6781 data_time: 0.0561 memory: 20117 grad_norm: 5.7529 loss: 9.3110 loss_occ_0: 5.6898 loss_occ_1: 2.9556 loss_occ_2: 0.6656 2024/04/12 18:07:43 - mmengine - INFO - Epoch(train) [24][350/389] lr: 1.0000e-06 eta: 0:01:04 time: 1.6439 data_time: 0.2249 memory: 20037 grad_norm: 6.1909 loss: 3.7820 loss_occ_0: 2.0068 loss_occ_1: 1.0971 loss_occ_2: 0.6780 2024/04/12 18:08:48 - mmengine - INFO - Exp name: mv-occ_8xb1_embodiedscan-occ-80class_20240412_130940 2024/04/12 18:08:48 - mmengine - INFO - Saving checkpoint at 24 epochs 2024/04/12 18:10:20 - mmengine - INFO - Epoch(val) [24][ 50/103] eta: 0:00:51 time: 0.9666 data_time: 0.8586 memory: 20087 2024/04/12 18:13:16 - mmengine - INFO - Epoch(val) [24][100/103] eta: 0:00:06 time: 3.5146 data_time: 3.3977 memory: 16130 2024/04/12 18:13:57 - mmengine - INFO - +---------------------+---------+ | classes | IoU | +---------------------+---------+ | empty | 0.74128 | | floor | 0.71036 | | wall | 0.53849 | | chair | 0.52868 | | cabinet | 0.30009 | | door | 0.31151 | | table | 0.42071 | | couch | 0.44883 | | shelf | 0.42348 | | window | 0.27746 | | bed | 0.50737 | | curtain | 0.48878 | | desk | 0.29249 | | doorframe | 0.22823 | | plant | 0.37098 | | stairs | 0.33109 | | pillow | 0.35785 | | wardrobe | 0.09440 | | picture | 0.25887 | | bathtub | 0.58762 | | box | 0.17519 | | counter | 0.26421 | | bench | 0.17882 | | stand | 0.23144 | | rail | 0.21556 | | sink | 0.43548 | | clothes | 0.21870 | | mirror | 0.16491 | | toilet | 0.61955 | | refrigerator | 0.15842 | | lamp | 0.33166 | | book | 0.22514 | | dresser | 0.06542 | | stool | 0.12544 | | fireplace | 0.04878 | | tv | 0.25060 | | blanket | 0.20205 | | commode | 0.03063 | | washing machine | 0.30702 | | monitor | 0.51925 | | window frame | 0.00844 | | radiator | 0.39266 | | mat | 0.01536 | | shower | 0.00602 | | rack | 0.00233 | | towel | 0.24374 | | ottoman | 0.15974 | | column | 0.04832 | | blinds | 0.02755 | | stove | 0.19348 | | bar | 0.21840 | | pillar | 0.03707 | | bin | 0.38216 | | heater | 0.15633 | | clothes dryer | 0.01410 | | backpack | 0.24763 | | blackboard | 0.36072 | | decoration | 0.03837 | | roof | 0.00000 | | bag | 0.09380 | | steps | 0.10256 | | windowsill | 0.16168 | | cushion | 0.02448 | | carpet | 0.06564 | | copier | 0.30303 | | board | 0.01028 | | countertop | 0.02976 | | basket | 0.06852 | | mailbox | 0.00000 | | kitchen island | 0.03708 | | washbasin | 0.00867 | | bicycle | 0.07000 | | drawer | 0.02795 | | oven | 0.14737 | | piano | 0.05660 | | excercise equipment | 0.00000 | | beam | 0.00000 | | partition | 0.00000 | | printer | 0.31515 | | microwave | 0.17342 | | frame | 0.00000 | +---------------------+---------+ | mean | 0.21278 | +---------------------+---------+ 2024/04/12 18:13:57 - mmengine - INFO - Epoch(val) [24][103/103] empty: 0.7413 floor: 0.7104 wall: 0.5385 chair: 0.5287 cabinet: 0.3001 door: 0.3115 table: 0.4207 couch: 0.4488 shelf: 0.4235 window: 0.2775 bed: 0.5074 curtain: 0.4888 desk: 0.2925 doorframe: 0.2282 plant: 0.3710 stairs: 0.3311 pillow: 0.3578 wardrobe: 0.0944 picture: 0.2589 bathtub: 0.5876 box: 0.1752 counter: 0.2642 bench: 0.1788 stand: 0.2314 rail: 0.2156 sink: 0.4355 clothes: 0.2187 mirror: 0.1649 toilet: 0.6195 refrigerator: 0.1584 lamp: 0.3317 book: 0.2251 dresser: 0.0654 stool: 0.1254 fireplace: 0.0488 tv: 0.2506 blanket: 0.2020 commode: 0.0306 washing machine: 0.3070 monitor: 0.5192 window frame: 0.0084 radiator: 0.3927 mat: 0.0154 shower: 0.0060 rack: 0.0023 towel: 0.2437 ottoman: 0.1597 column: 0.0483 blinds: 0.0276 stove: 0.1935 bar: 0.2184 pillar: 0.0371 bin: 0.3822 heater: 0.1563 clothes dryer: 0.0141 backpack: 0.2476 blackboard: 0.3607 decoration: 0.0384 roof: 0.0000 bag: 0.0938 steps: 0.1026 windowsill: 0.1617 cushion: 0.0245 carpet: 0.0656 copier: 0.3030 board: 0.0103 countertop: 0.0298 basket: 0.0685 mailbox: 0.0000 kitchen island: 0.0371 washbasin: 0.0087 bicycle: 0.0700 drawer: 0.0280 oven: 0.1474 piano: 0.0566 excercise equipment: 0.0000 beam: 0.0000 partition: 0.0000 printer: 0.3152 microwave: 0.1734 frame: 0.0000 data_time: 2.2062 time: 2.3185