2023/03/09 16:07:43 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.16 (default, Jan 17 2023, 23:13:24) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1588147245 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /nvme/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.12.1+cu113 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - 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_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 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -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-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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, 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: 0.13.1+cu113 OpenCV: 4.7.0 MMEngine: 0.5.0 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 1588147245 deterministic: False diff_rank_seed: True Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/03/09 16:07:44 - mmengine - INFO - Config: dataset_type = 'SemanticKittiDataset' data_root = 'data/semantickitti/' class_names = [ 'car', 'bicycle', 'motorcycle', 'truck', 'bus', 'person', 'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground', 'building', 'fence', 'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign' ] labels_map = dict({ 0: 19, 1: 19, 10: 0, 11: 1, 13: 4, 15: 2, 16: 4, 18: 3, 20: 4, 30: 5, 31: 6, 32: 7, 40: 8, 44: 9, 48: 10, 49: 11, 50: 12, 51: 13, 52: 19, 60: 8, 70: 14, 71: 15, 72: 16, 80: 17, 81: 18, 99: 19, 252: 0, 253: 6, 254: 5, 255: 7, 256: 4, 257: 4, 258: 3, 259: 4 }) metainfo = dict( classes=[ 'car', 'bicycle', 'motorcycle', 'truck', 'bus', 'person', 'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground', 'building', 'fence', 'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign' ], seg_label_mapping=dict({ 0: 19, 1: 19, 10: 0, 11: 1, 13: 4, 15: 2, 16: 4, 18: 3, 20: 4, 30: 5, 31: 6, 32: 7, 40: 8, 44: 9, 48: 10, 49: 11, 50: 12, 51: 13, 52: 19, 60: 8, 70: 14, 71: 15, 72: 16, 80: 17, 81: 18, 99: 19, 252: 0, 253: 6, 254: 5, 255: 7, 256: 4, 257: 4, 258: 3, 259: 4 }), max_label=259) input_modality = dict(use_lidar=True, use_camera=False) file_client_args = dict(backend='disk') train_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict( type='GlobalRotScaleTrans', rot_range=[0.0, 6.28318531], scale_ratio_range=[0.95, 1.05], translation_std=[0, 0, 0]), dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ] test_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ] eval_pipeline = [ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ] train_dataloader = dict( batch_size=2, num_workers=4, sampler=dict(type='DefaultSampler', shuffle=True, seed=0), dataset=dict( type='RepeatDataset', times=1, dataset=dict( type='SemanticKittiDataset', data_root='data/semantickitti/', ann_file='semantickitti_infos_train.pkl', pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict( type='GlobalRotScaleTrans', rot_range=[0.0, 6.28318531], scale_ratio_range=[0.95, 1.05], translation_std=[0, 0, 0]), dict( type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ], metainfo=dict( classes=[ 'car', 'bicycle', 'motorcycle', 'truck', 'bus', 'person', 'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground', 'building', 'fence', 'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign' ], seg_label_mapping=dict({ 0: 19, 1: 19, 10: 0, 11: 1, 13: 4, 15: 2, 16: 4, 18: 3, 20: 4, 30: 5, 31: 6, 32: 7, 40: 8, 44: 9, 48: 10, 49: 11, 50: 12, 51: 13, 52: 19, 60: 8, 70: 14, 71: 15, 72: 16, 80: 17, 81: 18, 99: 19, 252: 0, 253: 6, 254: 5, 255: 7, 256: 4, 257: 4, 258: 3, 259: 4 }), max_label=259), modality=dict(use_lidar=True, use_camera=False), ignore_index=19))) test_dataloader = dict( batch_size=1, num_workers=1, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='RepeatDataset', times=1, dataset=dict( type='SemanticKittiDataset', data_root='data/semantickitti/', ann_file='semantickitti_infos_val.pkl', pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict( type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ], metainfo=dict( classes=[ 'car', 'bicycle', 'motorcycle', 'truck', 'bus', 'person', 'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground', 'building', 'fence', 'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign' ], seg_label_mapping=dict({ 0: 19, 1: 19, 10: 0, 11: 1, 13: 4, 15: 2, 16: 4, 18: 3, 20: 4, 30: 5, 31: 6, 32: 7, 40: 8, 44: 9, 48: 10, 49: 11, 50: 12, 51: 13, 52: 19, 60: 8, 70: 14, 71: 15, 72: 16, 80: 17, 81: 18, 99: 19, 252: 0, 253: 6, 254: 5, 255: 7, 256: 4, 257: 4, 258: 3, 259: 4 }), max_label=259), modality=dict(use_lidar=True, use_camera=False), ignore_index=19, test_mode=True))) val_dataloader = dict( batch_size=1, num_workers=1, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='RepeatDataset', times=1, dataset=dict( type='SemanticKittiDataset', data_root='data/semantickitti/', ann_file='semantickitti_infos_val.pkl', pipeline=[ dict( type='LoadPointsFromFile', coord_type='LIDAR', load_dim=4, use_dim=4, file_client_args=dict(backend='disk')), dict( type='LoadAnnotations3D', with_bbox_3d=False, with_label_3d=False, with_seg_3d=True, seg_3d_dtype='np.int32', seg_offset=65536, dataset_type='semantickitti'), dict(type='PointSegClassMapping'), dict( type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask']) ], metainfo=dict( classes=[ 'car', 'bicycle', 'motorcycle', 'truck', 'bus', 'person', 'bicyclist', 'motorcyclist', 'road', 'parking', 'sidewalk', 'other-ground', 'building', 'fence', 'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign' ], seg_label_mapping=dict({ 0: 19, 1: 19, 10: 0, 11: 1, 13: 4, 15: 2, 16: 4, 18: 3, 20: 4, 30: 5, 31: 6, 32: 7, 40: 8, 44: 9, 48: 10, 49: 11, 50: 12, 51: 13, 52: 19, 60: 8, 70: 14, 71: 15, 72: 16, 80: 17, 81: 18, 99: 19, 252: 0, 253: 6, 254: 5, 255: 7, 256: 4, 257: 4, 258: 3, 259: 4 }), max_label=259), modality=dict(use_lidar=True, use_camera=False), ignore_index=19, test_mode=True))) val_evaluator = dict(type='SegMetric') test_evaluator = dict(type='SegMetric') vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='Det3DLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') model = dict( type='MinkUNet', data_preprocessor=dict( type='Det3DDataPreprocessor', voxel=True, voxel_type='minkunet', voxel_layer=dict( max_num_points=-1, point_cloud_range=[-100, -100, -20, 100, 100, 20], voxel_size=[0.05, 0.05, 0.05], max_voxels=(-1, -1))), backbone=dict( type='MinkUNetBackbone', in_channels=4, base_channels=16, encoder_channels=[16, 32, 64, 128], decoder_channels=[128, 64, 48, 48], num_stages=4, init_cfg=None), decode_head=dict( type='MinkUNetHead', channels=48, num_classes=19, dropout_ratio=0, loss_decode=dict(type='mmdet.CrossEntropyLoss', avg_non_ignore=True), ignore_index=19), train_cfg=dict(), test_cfg=dict()) default_scope = 'mmdet3d' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='Det3DVisualizationHook')) env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False lr = 0.24 optim_wrapper = dict( type='AmpOptimWrapper', loss_scale='dynamic', optimizer=dict( type='SGD', lr=0.24, weight_decay=0.0001, momentum=0.9, nesterov=True)) param_scheduler = [ dict( type='LinearLR', start_factor=0.008, by_epoch=False, begin=0, end=125), dict( type='CosineAnnealingLR', begin=0, T_max=15, by_epoch=True, eta_min=1e-05, convert_to_iter_based=True) ] train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=15, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') randomness = dict(seed=1588147245, deterministic=False, diff_rank_seed=True) launcher = 'pytorch' work_dir = './work_dirs/minkunet_w16_8xb2-15e_semantickitti' 2023/03/09 16:07:45 - mmengine - WARNING - The "model" registry in mmdet did not set import location. Fallback to call `mmdet.utils.register_all_modules` instead. 2023/03/09 16:07:46 - 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 -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) Det3DVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) Det3DVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.conv_input.0.net.0.kernel - torch.Size([27, 4, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.conv_input.0.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.conv_input.0.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.conv_input.1.net.0.kernel - torch.Size([27, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.conv_input.1.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.conv_input.1.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.0.net.0.kernel - torch.Size([8, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.0.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.0.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.0.kernel - torch.Size([27, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.3.kernel - torch.Size([27, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.1.net.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.0.kernel - torch.Size([27, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.3.kernel - torch.Size([27, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.0.2.net.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.0.net.0.kernel - torch.Size([8, 16, 16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.0.net.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.0.net.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.0.kernel - torch.Size([27, 16, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.3.kernel - torch.Size([27, 32, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.4.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.net.4.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.downsample.0.kernel - torch.Size([16, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.downsample.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.1.downsample.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.0.kernel - torch.Size([27, 32, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.3.kernel - torch.Size([27, 32, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.4.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.1.2.net.4.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.0.net.0.kernel - torch.Size([8, 32, 32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.0.net.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.0.net.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.0.kernel - torch.Size([27, 32, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.3.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.net.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.downsample.0.kernel - torch.Size([32, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.downsample.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.1.downsample.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.0.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.3.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.2.2.net.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.0.net.0.kernel - torch.Size([8, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.0.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.0.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.0.kernel - torch.Size([27, 64, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.4.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.net.4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.downsample.0.kernel - torch.Size([64, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.downsample.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.1.downsample.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.0.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.4.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.encoder.3.2.net.4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.0.net.0.kernel - torch.Size([8, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.0.net.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.0.net.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.0.kernel - torch.Size([27, 192, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.4.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.net.4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.downsample.0.kernel - torch.Size([192, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.downsample.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.0.downsample.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.0.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.3.kernel - torch.Size([27, 128, 128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.4.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.0.1.1.net.4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.0.net.0.kernel - torch.Size([8, 128, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.0.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.0.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.0.kernel - torch.Size([27, 96, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.3.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.net.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.downsample.0.kernel - torch.Size([96, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.downsample.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.0.downsample.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.0.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.3.kernel - torch.Size([27, 64, 64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.1.1.1.net.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.0.net.0.kernel - torch.Size([8, 64, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.0.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.0.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.0.kernel - torch.Size([27, 64, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.3.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.4.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.net.4.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.downsample.0.kernel - torch.Size([64, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.downsample.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.0.downsample.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.0.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.3.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.4.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.2.1.1.net.4.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.0.net.0.kernel - torch.Size([8, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.0.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.0.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.0.kernel - torch.Size([27, 64, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.3.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.4.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.net.4.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.downsample.0.kernel - torch.Size([64, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.downsample.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.0.downsample.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.0.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.1.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.1.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.3.kernel - torch.Size([27, 48, 48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.4.weight - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet backbone.decoder.3.1.1.net.4.bias - torch.Size([48]): The value is the same before and after calling `init_weights` of MinkUNet decode_head.conv_seg.weight - torch.Size([19, 48]): Initialized by user-defined `init_weights` in MinkUNetHead decode_head.conv_seg.bias - torch.Size([19]): Initialized by user-defined `init_weights` in MinkUNetHead 2023/03/09 16:07:48 - mmengine - INFO - Checkpoints will be saved to /nvme/sunjiahao/projects/mmdetection3d/work_dirs/minkunet_w16_8xb2-15e_semantickitti. 2023/03/09 16:08:12 - mmengine - INFO - Epoch(train) [1][ 50/1196] lr: 9.5998e-02 eta: 2:24:24 time: 0.4843 data_time: 0.0084 memory: 1013 loss: 1.7847 loss_sem_seg: 1.7847 2023/03/09 16:08:34 - mmengine - INFO - Epoch(train) [1][ 100/1196] lr: 1.9199e-01 eta: 2:16:11 time: 0.4318 data_time: 0.0031 memory: 1058 loss: 1.1961 loss_sem_seg: 1.1961 2023/03/09 16:08:55 - mmengine - INFO - Epoch(train) [1][ 150/1196] lr: 2.3996e-01 eta: 2:13:06 time: 0.4307 data_time: 0.0034 memory: 1040 loss: 1.0052 loss_sem_seg: 1.0052 2023/03/09 16:09:17 - mmengine - INFO - Epoch(train) [1][ 200/1196] lr: 2.3993e-01 eta: 2:11:12 time: 0.4282 data_time: 0.0031 memory: 1043 loss: 0.8591 loss_sem_seg: 0.8591 2023/03/09 16:09:38 - mmengine - INFO - Epoch(train) [1][ 250/1196] lr: 2.3989e-01 eta: 2:09:51 time: 0.4273 data_time: 0.0032 memory: 1036 loss: 0.7492 loss_sem_seg: 0.7492 2023/03/09 16:10:00 - mmengine - INFO - Epoch(train) [1][ 300/1196] lr: 2.3984e-01 eta: 2:09:07 time: 0.4329 data_time: 0.0032 memory: 991 loss: 0.6740 loss_sem_seg: 0.6740 2023/03/09 16:10:21 - mmengine - INFO - Epoch(train) [1][ 350/1196] lr: 2.3978e-01 eta: 2:08:20 time: 0.4294 data_time: 0.0033 memory: 1039 loss: 0.6505 loss_sem_seg: 0.6505 2023/03/09 16:10:43 - mmengine - INFO - Epoch(train) [1][ 400/1196] lr: 2.3971e-01 eta: 2:07:45 time: 0.4317 data_time: 0.0032 memory: 1074 loss: 0.5906 loss_sem_seg: 0.5906 2023/03/09 16:11:05 - mmengine - INFO - Epoch(train) [1][ 450/1196] lr: 2.3963e-01 eta: 2:07:18 time: 0.4345 data_time: 0.0033 memory: 1027 loss: 0.5393 loss_sem_seg: 0.5393 2023/03/09 16:11:26 - mmengine - INFO - Epoch(train) [1][ 500/1196] lr: 2.3954e-01 eta: 2:06:48 time: 0.4316 data_time: 0.0033 memory: 1026 loss: 0.5237 loss_sem_seg: 0.5237 2023/03/09 16:11:48 - mmengine - INFO - Epoch(train) [1][ 550/1196] lr: 2.3945e-01 eta: 2:06:12 time: 0.4273 data_time: 0.0032 memory: 1008 loss: 0.5457 loss_sem_seg: 0.5457 2023/03/09 16:12:09 - mmengine - INFO - Epoch(train) [1][ 600/1196] lr: 2.3934e-01 eta: 2:05:40 time: 0.4283 data_time: 0.0031 memory: 1010 loss: 0.5001 loss_sem_seg: 0.5001 2023/03/09 16:12:31 - mmengine - INFO - Epoch(train) [1][ 650/1196] lr: 2.3923e-01 eta: 2:05:16 time: 0.4336 data_time: 0.0032 memory: 1090 loss: 0.5200 loss_sem_seg: 0.5200 2023/03/09 16:12:52 - mmengine - INFO - Epoch(train) [1][ 700/1196] lr: 2.3910e-01 eta: 2:04:48 time: 0.4292 data_time: 0.0032 memory: 1010 loss: 0.4819 loss_sem_seg: 0.4819 2023/03/09 16:13:14 - mmengine - INFO - Epoch(train) [1][ 750/1196] lr: 2.3897e-01 eta: 2:04:20 time: 0.4288 data_time: 0.0032 memory: 1072 loss: 0.4717 loss_sem_seg: 0.4717 2023/03/09 16:13:35 - mmengine - INFO - Epoch(train) [1][ 800/1196] lr: 2.3883e-01 eta: 2:03:55 time: 0.4310 data_time: 0.0035 memory: 1044 loss: 0.4591 loss_sem_seg: 0.4591 2023/03/09 16:13:57 - mmengine - INFO - Epoch(train) [1][ 850/1196] lr: 2.3868e-01 eta: 2:03:26 time: 0.4272 data_time: 0.0032 memory: 982 loss: 0.4242 loss_sem_seg: 0.4242 2023/03/09 16:14:18 - mmengine - INFO - Epoch(train) [1][ 900/1196] lr: 2.3852e-01 eta: 2:03:00 time: 0.4280 data_time: 0.0033 memory: 1041 loss: 0.4220 loss_sem_seg: 0.4220 2023/03/09 16:14:39 - mmengine - INFO - Epoch(train) [1][ 950/1196] lr: 2.3835e-01 eta: 2:02:31 time: 0.4250 data_time: 0.0033 memory: 1054 loss: 0.4211 loss_sem_seg: 0.4211 2023/03/09 16:15:01 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:15:01 - mmengine - INFO - Epoch(train) [1][1000/1196] lr: 2.3817e-01 eta: 2:02:04 time: 0.4273 data_time: 0.0031 memory: 1074 loss: 0.4337 loss_sem_seg: 0.4337 2023/03/09 16:15:22 - mmengine - INFO - Epoch(train) [1][1050/1196] lr: 2.3798e-01 eta: 2:01:42 time: 0.4311 data_time: 0.0031 memory: 1063 loss: 0.4180 loss_sem_seg: 0.4180 2023/03/09 16:15:44 - mmengine - INFO - Epoch(train) [1][1100/1196] lr: 2.3778e-01 eta: 2:01:21 time: 0.4339 data_time: 0.0032 memory: 1030 loss: 0.4192 loss_sem_seg: 0.4192 2023/03/09 16:16:05 - mmengine - INFO - Epoch(train) [1][1150/1196] lr: 2.3758e-01 eta: 2:00:58 time: 0.4298 data_time: 0.0032 memory: 1043 loss: 0.4218 loss_sem_seg: 0.4218 2023/03/09 16:16:24 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:16:25 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/03/09 16:16:36 - mmengine - INFO - Epoch(val) [1][ 50/509] eta: 0:01:39 time: 0.2163 data_time: 0.0058 memory: 1031 2023/03/09 16:16:44 - mmengine - INFO - Epoch(val) [1][100/509] eta: 0:01:15 time: 0.1517 data_time: 0.0045 memory: 264 2023/03/09 16:16:52 - mmengine - INFO - Epoch(val) [1][150/509] eta: 0:01:03 time: 0.1617 data_time: 0.0042 memory: 263 2023/03/09 16:17:00 - mmengine - INFO - Epoch(val) [1][200/509] eta: 0:00:53 time: 0.1648 data_time: 0.0040 memory: 257 2023/03/09 16:17:08 - mmengine - INFO - Epoch(val) [1][250/509] eta: 0:00:44 time: 0.1629 data_time: 0.0041 memory: 267 2023/03/09 16:17:16 - mmengine - INFO - Epoch(val) [1][300/509] eta: 0:00:35 time: 0.1565 data_time: 0.0040 memory: 245 2023/03/09 16:17:24 - mmengine - INFO - Epoch(val) [1][350/509] eta: 0:00:26 time: 0.1576 data_time: 0.0040 memory: 254 2023/03/09 16:17:32 - mmengine - INFO - Epoch(val) [1][400/509] eta: 0:00:18 time: 0.1604 data_time: 0.0040 memory: 255 2023/03/09 16:17:40 - mmengine - INFO - Epoch(val) [1][450/509] eta: 0:00:09 time: 0.1625 data_time: 0.0040 memory: 263 2023/03/09 16:17:48 - mmengine - INFO - Epoch(val) [1][500/509] eta: 0:00:01 time: 0.1546 data_time: 0.0041 memory: 255 2023/03/09 16:18:09 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9056 | 0.0000 | 0.0000 | 0.0394 | 0.1054 | 0.0000 | 0.0000 | 0.0000 | 0.8595 | 0.1111 | 0.7143 | 0.0002 | 0.8509 | 0.4826 | 0.8477 | 0.5166 | 0.6783 | 0.4588 | 0.0177 | 0.3467 | 0.8763 | 0.3964 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 16:18:09 - mmengine - INFO - Epoch(val) [1][509/509] car: 0.9056 bicycle: 0.0000 motorcycle: 0.0000 truck: 0.0394 bus: 0.1054 person: 0.0000 bicyclist: 0.0000 motorcyclist: 0.0000 road: 0.8595 parking: 0.1111 sidewalk: 0.7143 other-ground: 0.0002 building: 0.8509 fence: 0.4826 vegetation: 0.8477 trunck: 0.5166 terrian: 0.6783 pole: 0.4588 traffic-sign: 0.0177 miou: 0.3467 acc: 0.8763 acc_cls: 0.3964 2023/03/09 16:18:39 - mmengine - INFO - Epoch(train) [2][ 50/1196] lr: 2.3716e-01 eta: 2:02:00 time: 0.6009 data_time: 0.0223 memory: 1052 loss: 0.4061 loss_sem_seg: 0.4061 2023/03/09 16:19:01 - mmengine - INFO - Epoch(train) [2][ 100/1196] lr: 2.3693e-01 eta: 2:01:37 time: 0.4379 data_time: 0.0034 memory: 1015 loss: 0.3636 loss_sem_seg: 0.3636 2023/03/09 16:19:23 - mmengine - INFO - Epoch(train) [2][ 150/1196] lr: 2.3669e-01 eta: 2:01:15 time: 0.4374 data_time: 0.0031 memory: 1003 loss: 0.3556 loss_sem_seg: 0.3556 2023/03/09 16:19:44 - mmengine - INFO - Epoch(train) [2][ 200/1196] lr: 2.3644e-01 eta: 2:00:50 time: 0.4326 data_time: 0.0031 memory: 981 loss: 0.4202 loss_sem_seg: 0.4202 2023/03/09 16:20:06 - mmengine - INFO - Epoch(train) [2][ 250/1196] lr: 2.3618e-01 eta: 2:00:27 time: 0.4371 data_time: 0.0031 memory: 1052 loss: 0.3812 loss_sem_seg: 0.3812 2023/03/09 16:20:28 - mmengine - INFO - Epoch(train) [2][ 300/1196] lr: 2.3591e-01 eta: 2:00:03 time: 0.4352 data_time: 0.0035 memory: 1049 loss: 0.3750 loss_sem_seg: 0.3750 2023/03/09 16:20:50 - mmengine - INFO - Epoch(train) [2][ 350/1196] lr: 2.3563e-01 eta: 1:59:42 time: 0.4384 data_time: 0.0033 memory: 989 loss: 0.4216 loss_sem_seg: 0.4216 2023/03/09 16:21:12 - mmengine - INFO - Epoch(train) [2][ 400/1196] lr: 2.3535e-01 eta: 1:59:19 time: 0.4370 data_time: 0.0032 memory: 1000 loss: 0.3794 loss_sem_seg: 0.3794 2023/03/09 16:21:34 - mmengine - INFO - Epoch(train) [2][ 450/1196] lr: 2.3506e-01 eta: 1:58:57 time: 0.4370 data_time: 0.0032 memory: 1010 loss: 0.3356 loss_sem_seg: 0.3356 2023/03/09 16:21:55 - mmengine - INFO - Epoch(train) [2][ 500/1196] lr: 2.3475e-01 eta: 1:58:34 time: 0.4360 data_time: 0.0032 memory: 1050 loss: 0.3638 loss_sem_seg: 0.3638 2023/03/09 16:22:17 - mmengine - INFO - Epoch(train) [2][ 550/1196] lr: 2.3444e-01 eta: 1:58:12 time: 0.4387 data_time: 0.0034 memory: 1036 loss: 0.4058 loss_sem_seg: 0.4058 2023/03/09 16:22:39 - mmengine - INFO - Epoch(train) [2][ 600/1196] lr: 2.3412e-01 eta: 1:57:52 time: 0.4406 data_time: 0.0033 memory: 1016 loss: 0.3526 loss_sem_seg: 0.3526 2023/03/09 16:23:01 - mmengine - INFO - Epoch(train) [2][ 650/1196] lr: 2.3379e-01 eta: 1:57:31 time: 0.4403 data_time: 0.0032 memory: 1004 loss: 0.3439 loss_sem_seg: 0.3439 2023/03/09 16:23:23 - mmengine - INFO - Epoch(train) [2][ 700/1196] lr: 2.3345e-01 eta: 1:57:08 time: 0.4364 data_time: 0.0033 memory: 1013 loss: 0.3668 loss_sem_seg: 0.3668 2023/03/09 16:23:45 - mmengine - INFO - Epoch(train) [2][ 750/1196] lr: 2.3311e-01 eta: 1:56:46 time: 0.4387 data_time: 0.0033 memory: 1063 loss: 0.3579 loss_sem_seg: 0.3579 2023/03/09 16:24:07 - mmengine - INFO - Epoch(train) [2][ 800/1196] lr: 2.3275e-01 eta: 1:56:24 time: 0.4370 data_time: 0.0032 memory: 1009 loss: 0.3307 loss_sem_seg: 0.3307 2023/03/09 16:24:09 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:24:29 - mmengine - INFO - Epoch(train) [2][ 850/1196] lr: 2.3239e-01 eta: 1:56:03 time: 0.4398 data_time: 0.0034 memory: 1024 loss: 0.3211 loss_sem_seg: 0.3211 2023/03/09 16:24:51 - mmengine - INFO - Epoch(train) [2][ 900/1196] lr: 2.3201e-01 eta: 1:55:40 time: 0.4349 data_time: 0.0032 memory: 1019 loss: 0.3600 loss_sem_seg: 0.3600 2023/03/09 16:25:13 - mmengine - INFO - Epoch(train) [2][ 950/1196] lr: 2.3163e-01 eta: 1:55:18 time: 0.4373 data_time: 0.0035 memory: 1047 loss: 0.3385 loss_sem_seg: 0.3385 2023/03/09 16:25:35 - mmengine - INFO - Epoch(train) [2][1000/1196] lr: 2.3124e-01 eta: 1:54:56 time: 0.4402 data_time: 0.0034 memory: 1050 loss: 0.3491 loss_sem_seg: 0.3491 2023/03/09 16:25:56 - mmengine - INFO - Epoch(train) [2][1050/1196] lr: 2.3085e-01 eta: 1:54:33 time: 0.4346 data_time: 0.0034 memory: 982 loss: 0.3187 loss_sem_seg: 0.3187 2023/03/09 16:26:18 - mmengine - INFO - Epoch(train) [2][1100/1196] lr: 2.3044e-01 eta: 1:54:11 time: 0.4376 data_time: 0.0033 memory: 1003 loss: 0.3432 loss_sem_seg: 0.3432 2023/03/09 16:26:40 - mmengine - INFO - Epoch(train) [2][1150/1196] lr: 2.3002e-01 eta: 1:53:49 time: 0.4364 data_time: 0.0033 memory: 1046 loss: 0.3402 loss_sem_seg: 0.3402 2023/03/09 16:27:00 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:27:01 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/03/09 16:27:14 - mmengine - INFO - Epoch(val) [2][ 50/509] eta: 0:01:55 time: 0.2520 data_time: 0.0088 memory: 1090 2023/03/09 16:27:27 - mmengine - INFO - Epoch(val) [2][100/509] eta: 0:01:42 time: 0.2484 data_time: 0.0046 memory: 264 2023/03/09 16:27:38 - mmengine - INFO - Epoch(val) [2][150/509] eta: 0:01:25 time: 0.2152 data_time: 0.0050 memory: 263 2023/03/09 16:27:46 - mmengine - INFO - Epoch(val) [2][200/509] eta: 0:01:08 time: 0.1656 data_time: 0.0045 memory: 257 2023/03/09 16:27:54 - mmengine - INFO - Epoch(val) [2][250/509] eta: 0:00:54 time: 0.1624 data_time: 0.0044 memory: 267 2023/03/09 16:28:02 - mmengine - INFO - Epoch(val) [2][300/509] eta: 0:00:41 time: 0.1597 data_time: 0.0050 memory: 245 2023/03/09 16:28:10 - mmengine - INFO - Epoch(val) [2][350/509] eta: 0:00:31 time: 0.1619 data_time: 0.0050 memory: 254 2023/03/09 16:28:18 - mmengine - INFO - Epoch(val) [2][400/509] eta: 0:00:20 time: 0.1633 data_time: 0.0048 memory: 255 2023/03/09 16:28:26 - mmengine - INFO - Epoch(val) [2][450/509] eta: 0:00:11 time: 0.1574 data_time: 0.0048 memory: 263 2023/03/09 16:28:34 - mmengine - INFO - Epoch(val) [2][500/509] eta: 0:00:01 time: 0.1570 data_time: 0.0046 memory: 255 2023/03/09 16:28:56 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9179 | 0.0000 | 0.0395 | 0.0347 | 0.2847 | 0.0022 | 0.0000 | 0.0000 | 0.8888 | 0.2974 | 0.7451 | 0.0004 | 0.8646 | 0.5011 | 0.8547 | 0.3948 | 0.7279 | 0.5088 | 0.1682 | 0.3806 | 0.8889 | 0.4421 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 16:28:56 - mmengine - INFO - Epoch(val) [2][509/509] car: 0.9179 bicycle: 0.0000 motorcycle: 0.0395 truck: 0.0347 bus: 0.2847 person: 0.0022 bicyclist: 0.0000 motorcyclist: 0.0000 road: 0.8888 parking: 0.2974 sidewalk: 0.7451 other-ground: 0.0004 building: 0.8646 fence: 0.5011 vegetation: 0.8547 trunck: 0.3948 terrian: 0.7279 pole: 0.5088 traffic-sign: 0.1682 miou: 0.3806 acc: 0.8889 acc_cls: 0.4421 2023/03/09 16:29:31 - mmengine - INFO - Epoch(train) [3][ 50/1196] lr: 2.2920e-01 eta: 1:54:31 time: 0.6988 data_time: 0.0230 memory: 1115 loss: 0.3451 loss_sem_seg: 0.3451 2023/03/09 16:30:00 - mmengine - INFO - Epoch(train) [3][ 100/1196] lr: 2.2876e-01 eta: 1:54:53 time: 0.5881 data_time: 0.0038 memory: 1041 loss: 0.3222 loss_sem_seg: 0.3222 2023/03/09 16:30:22 - mmengine - INFO - Epoch(train) [3][ 150/1196] lr: 2.2832e-01 eta: 1:54:29 time: 0.4406 data_time: 0.0037 memory: 1045 loss: 0.3263 loss_sem_seg: 0.3263 2023/03/09 16:30:44 - mmengine - INFO - Epoch(train) [3][ 200/1196] lr: 2.2786e-01 eta: 1:54:04 time: 0.4351 data_time: 0.0032 memory: 1001 loss: 0.3216 loss_sem_seg: 0.3216 2023/03/09 16:31:06 - mmengine - INFO - Epoch(train) [3][ 250/1196] lr: 2.2739e-01 eta: 1:53:38 time: 0.4354 data_time: 0.0033 memory: 1026 loss: 0.3255 loss_sem_seg: 0.3255 2023/03/09 16:31:28 - mmengine - INFO - Epoch(train) [3][ 300/1196] lr: 2.2692e-01 eta: 1:53:14 time: 0.4393 data_time: 0.0033 memory: 1045 loss: 0.3103 loss_sem_seg: 0.3103 2023/03/09 16:31:49 - mmengine - INFO - Epoch(train) [3][ 350/1196] lr: 2.2644e-01 eta: 1:52:50 time: 0.4380 data_time: 0.0034 memory: 1052 loss: 0.3239 loss_sem_seg: 0.3239 2023/03/09 16:32:11 - mmengine - INFO - Epoch(train) [3][ 400/1196] lr: 2.2595e-01 eta: 1:52:26 time: 0.4410 data_time: 0.0035 memory: 1030 loss: 0.3175 loss_sem_seg: 0.3175 2023/03/09 16:32:33 - mmengine - INFO - Epoch(train) [3][ 450/1196] lr: 2.2545e-01 eta: 1:52:02 time: 0.4380 data_time: 0.0035 memory: 994 loss: 0.3073 loss_sem_seg: 0.3073 2023/03/09 16:32:55 - mmengine - INFO - Epoch(train) [3][ 500/1196] lr: 2.2495e-01 eta: 1:51:38 time: 0.4373 data_time: 0.0033 memory: 1040 loss: 0.3143 loss_sem_seg: 0.3143 2023/03/09 16:33:17 - mmengine - INFO - Epoch(train) [3][ 550/1196] lr: 2.2443e-01 eta: 1:51:14 time: 0.4373 data_time: 0.0034 memory: 1020 loss: 0.3191 loss_sem_seg: 0.3191 2023/03/09 16:33:39 - mmengine - INFO - Epoch(train) [3][ 600/1196] lr: 2.2391e-01 eta: 1:50:50 time: 0.4382 data_time: 0.0038 memory: 1043 loss: 0.3046 loss_sem_seg: 0.3046 2023/03/09 16:33:43 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:34:01 - mmengine - INFO - Epoch(train) [3][ 650/1196] lr: 2.2338e-01 eta: 1:50:25 time: 0.4365 data_time: 0.0033 memory: 1025 loss: 0.2976 loss_sem_seg: 0.2976 2023/03/09 16:34:22 - mmengine - INFO - Epoch(train) [3][ 700/1196] lr: 2.2285e-01 eta: 1:50:00 time: 0.4326 data_time: 0.0034 memory: 1043 loss: 0.3187 loss_sem_seg: 0.3187 2023/03/09 16:34:45 - mmengine - INFO - Epoch(train) [3][ 750/1196] lr: 2.2230e-01 eta: 1:49:37 time: 0.4419 data_time: 0.0033 memory: 1010 loss: 0.3285 loss_sem_seg: 0.3285 2023/03/09 16:35:06 - mmengine - INFO - Epoch(train) [3][ 800/1196] lr: 2.2175e-01 eta: 1:49:13 time: 0.4352 data_time: 0.0035 memory: 1062 loss: 0.3112 loss_sem_seg: 0.3112 2023/03/09 16:35:28 - mmengine - INFO - Epoch(train) [3][ 850/1196] lr: 2.2119e-01 eta: 1:48:49 time: 0.4365 data_time: 0.0034 memory: 1035 loss: 0.2905 loss_sem_seg: 0.2905 2023/03/09 16:35:50 - mmengine - INFO - Epoch(train) [3][ 900/1196] lr: 2.2062e-01 eta: 1:48:25 time: 0.4360 data_time: 0.0033 memory: 1065 loss: 0.2995 loss_sem_seg: 0.2995 2023/03/09 16:36:12 - mmengine - INFO - Epoch(train) [3][ 950/1196] lr: 2.2004e-01 eta: 1:48:00 time: 0.4339 data_time: 0.0034 memory: 1098 loss: 0.3162 loss_sem_seg: 0.3162 2023/03/09 16:36:33 - mmengine - INFO - Epoch(train) [3][1000/1196] lr: 2.1946e-01 eta: 1:47:37 time: 0.4362 data_time: 0.0034 memory: 1007 loss: 0.3094 loss_sem_seg: 0.3094 2023/03/09 16:36:55 - mmengine - INFO - Epoch(train) [3][1050/1196] lr: 2.1887e-01 eta: 1:47:13 time: 0.4347 data_time: 0.0033 memory: 1006 loss: 0.3265 loss_sem_seg: 0.3265 2023/03/09 16:37:17 - mmengine - INFO - Epoch(train) [3][1100/1196] lr: 2.1827e-01 eta: 1:46:49 time: 0.4355 data_time: 0.0033 memory: 1016 loss: 0.3017 loss_sem_seg: 0.3017 2023/03/09 16:37:39 - mmengine - INFO - Epoch(train) [3][1150/1196] lr: 2.1766e-01 eta: 1:46:25 time: 0.4373 data_time: 0.0035 memory: 1025 loss: 0.2802 loss_sem_seg: 0.2802 2023/03/09 16:37:59 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:37:59 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/03/09 16:38:13 - mmengine - INFO - Epoch(val) [3][ 50/509] eta: 0:01:55 time: 0.2520 data_time: 0.0087 memory: 1047 2023/03/09 16:38:25 - mmengine - INFO - Epoch(val) [3][100/509] eta: 0:01:41 time: 0.2457 data_time: 0.0045 memory: 264 2023/03/09 16:38:37 - mmengine - INFO - Epoch(val) [3][150/509] eta: 0:01:28 time: 0.2417 data_time: 0.0044 memory: 263 2023/03/09 16:38:50 - mmengine - INFO - Epoch(val) [3][200/509] eta: 0:01:16 time: 0.2478 data_time: 0.0044 memory: 257 2023/03/09 16:39:00 - mmengine - INFO - Epoch(val) [3][250/509] eta: 0:01:01 time: 0.2083 data_time: 0.0047 memory: 267 2023/03/09 16:39:08 - mmengine - INFO - Epoch(val) [3][300/509] eta: 0:00:46 time: 0.1479 data_time: 0.0046 memory: 245 2023/03/09 16:39:16 - mmengine - INFO - Epoch(val) [3][350/509] eta: 0:00:34 time: 0.1615 data_time: 0.0042 memory: 254 2023/03/09 16:39:24 - mmengine - INFO - Epoch(val) [3][400/509] eta: 0:00:22 time: 0.1616 data_time: 0.0042 memory: 255 2023/03/09 16:39:32 - mmengine - INFO - Epoch(val) [3][450/509] eta: 0:00:12 time: 0.1652 data_time: 0.0045 memory: 263 2023/03/09 16:39:40 - mmengine - INFO - Epoch(val) [3][500/509] eta: 0:00:01 time: 0.1607 data_time: 0.0049 memory: 255 2023/03/09 16:40:02 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9243 | 0.0000 | 0.1926 | 0.1931 | 0.1873 | 0.0789 | 0.1284 | 0.0000 | 0.8773 | 0.2103 | 0.7362 | 0.0000 | 0.8785 | 0.5318 | 0.8600 | 0.5696 | 0.6937 | 0.5551 | 0.2563 | 0.4144 | 0.8878 | 0.5013 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 16:40:02 - mmengine - INFO - Epoch(val) [3][509/509] car: 0.9243 bicycle: 0.0000 motorcycle: 0.1926 truck: 0.1931 bus: 0.1873 person: 0.0789 bicyclist: 0.1284 motorcyclist: 0.0000 road: 0.8773 parking: 0.2103 sidewalk: 0.7362 other-ground: 0.0000 building: 0.8785 fence: 0.5318 vegetation: 0.8600 trunck: 0.5696 terrian: 0.6937 pole: 0.5551 traffic-sign: 0.2563 miou: 0.4144 acc: 0.8878 acc_cls: 0.5013 2023/03/09 16:40:29 - mmengine - INFO - Epoch(train) [4][ 50/1196] lr: 2.1647e-01 eta: 1:46:00 time: 0.5367 data_time: 0.0246 memory: 1066 loss: 0.2819 loss_sem_seg: 0.2819 2023/03/09 16:41:06 - mmengine - INFO - Epoch(train) [4][ 100/1196] lr: 2.1585e-01 eta: 1:46:35 time: 0.7445 data_time: 0.0035 memory: 1019 loss: 0.2889 loss_sem_seg: 0.2889 2023/03/09 16:41:33 - mmengine - INFO - Epoch(train) [4][ 150/1196] lr: 2.1521e-01 eta: 1:46:29 time: 0.5314 data_time: 0.0035 memory: 1051 loss: 0.2986 loss_sem_seg: 0.2986 2023/03/09 16:41:55 - mmengine - INFO - Epoch(train) [4][ 200/1196] lr: 2.1457e-01 eta: 1:46:03 time: 0.4357 data_time: 0.0035 memory: 1062 loss: 0.2853 loss_sem_seg: 0.2853 2023/03/09 16:42:17 - mmengine - INFO - Epoch(train) [4][ 250/1196] lr: 2.1392e-01 eta: 1:45:39 time: 0.4386 data_time: 0.0033 memory: 1019 loss: 0.2949 loss_sem_seg: 0.2949 2023/03/09 16:42:38 - mmengine - INFO - Epoch(train) [4][ 300/1196] lr: 2.1326e-01 eta: 1:45:13 time: 0.4310 data_time: 0.0034 memory: 1004 loss: 0.3026 loss_sem_seg: 0.3026 2023/03/09 16:43:00 - mmengine - INFO - Epoch(train) [4][ 350/1196] lr: 2.1259e-01 eta: 1:44:48 time: 0.4370 data_time: 0.0033 memory: 1091 loss: 0.3082 loss_sem_seg: 0.3082 2023/03/09 16:43:22 - mmengine - INFO - Epoch(train) [4][ 400/1196] lr: 2.1192e-01 eta: 1:44:24 time: 0.4356 data_time: 0.0035 memory: 1040 loss: 0.3226 loss_sem_seg: 0.3226 2023/03/09 16:43:27 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:43:44 - mmengine - INFO - Epoch(train) [4][ 450/1196] lr: 2.1124e-01 eta: 1:43:59 time: 0.4343 data_time: 0.0034 memory: 1085 loss: 0.3171 loss_sem_seg: 0.3171 2023/03/09 16:44:05 - mmengine - INFO - Epoch(train) [4][ 500/1196] lr: 2.1056e-01 eta: 1:43:34 time: 0.4358 data_time: 0.0035 memory: 1062 loss: 0.3031 loss_sem_seg: 0.3031 2023/03/09 16:44:27 - mmengine - INFO - Epoch(train) [4][ 550/1196] lr: 2.0986e-01 eta: 1:43:09 time: 0.4310 data_time: 0.0035 memory: 1035 loss: 0.2957 loss_sem_seg: 0.2957 2023/03/09 16:44:49 - mmengine - INFO - Epoch(train) [4][ 600/1196] lr: 2.0916e-01 eta: 1:42:45 time: 0.4384 data_time: 0.0034 memory: 1032 loss: 0.2999 loss_sem_seg: 0.2999 2023/03/09 16:45:11 - mmengine - INFO - Epoch(train) [4][ 650/1196] lr: 2.0846e-01 eta: 1:42:20 time: 0.4379 data_time: 0.0035 memory: 1076 loss: 0.2876 loss_sem_seg: 0.2876 2023/03/09 16:45:32 - mmengine - INFO - Epoch(train) [4][ 700/1196] lr: 2.0774e-01 eta: 1:41:55 time: 0.4308 data_time: 0.0034 memory: 1006 loss: 0.2860 loss_sem_seg: 0.2860 2023/03/09 16:45:54 - mmengine - INFO - Epoch(train) [4][ 750/1196] lr: 2.0702e-01 eta: 1:41:31 time: 0.4342 data_time: 0.0036 memory: 1059 loss: 0.2908 loss_sem_seg: 0.2908 2023/03/09 16:46:16 - mmengine - INFO - Epoch(train) [4][ 800/1196] lr: 2.0630e-01 eta: 1:41:06 time: 0.4352 data_time: 0.0035 memory: 1043 loss: 0.3022 loss_sem_seg: 0.3022 2023/03/09 16:46:38 - mmengine - INFO - Epoch(train) [4][ 850/1196] lr: 2.0556e-01 eta: 1:40:42 time: 0.4340 data_time: 0.0034 memory: 999 loss: 0.3056 loss_sem_seg: 0.3056 2023/03/09 16:46:59 - mmengine - INFO - Epoch(train) [4][ 900/1196] lr: 2.0482e-01 eta: 1:40:17 time: 0.4311 data_time: 0.0034 memory: 1014 loss: 0.2853 loss_sem_seg: 0.2853 2023/03/09 16:47:21 - mmengine - INFO - Epoch(train) [4][ 950/1196] lr: 2.0408e-01 eta: 1:39:52 time: 0.4298 data_time: 0.0034 memory: 1042 loss: 0.2958 loss_sem_seg: 0.2958 2023/03/09 16:47:42 - mmengine - INFO - Epoch(train) [4][1000/1196] lr: 2.0333e-01 eta: 1:39:27 time: 0.4286 data_time: 0.0034 memory: 1031 loss: 0.2644 loss_sem_seg: 0.2644 2023/03/09 16:48:04 - mmengine - INFO - Epoch(train) [4][1050/1196] lr: 2.0257e-01 eta: 1:39:02 time: 0.4309 data_time: 0.0034 memory: 1052 loss: 0.2767 loss_sem_seg: 0.2767 2023/03/09 16:48:25 - mmengine - INFO - Epoch(train) [4][1100/1196] lr: 2.0180e-01 eta: 1:38:37 time: 0.4272 data_time: 0.0034 memory: 1013 loss: 0.2759 loss_sem_seg: 0.2759 2023/03/09 16:48:46 - mmengine - INFO - Epoch(train) [4][1150/1196] lr: 2.0103e-01 eta: 1:38:13 time: 0.4317 data_time: 0.0035 memory: 1025 loss: 0.2781 loss_sem_seg: 0.2781 2023/03/09 16:49:06 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:49:07 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/03/09 16:49:21 - mmengine - INFO - Epoch(val) [4][ 50/509] eta: 0:01:58 time: 0.2572 data_time: 0.0091 memory: 986 2023/03/09 16:49:33 - mmengine - INFO - Epoch(val) [4][100/509] eta: 0:01:44 time: 0.2522 data_time: 0.0047 memory: 264 2023/03/09 16:49:46 - mmengine - INFO - Epoch(val) [4][150/509] eta: 0:01:30 time: 0.2493 data_time: 0.0046 memory: 263 2023/03/09 16:49:58 - mmengine - INFO - Epoch(val) [4][200/509] eta: 0:01:17 time: 0.2506 data_time: 0.0045 memory: 257 2023/03/09 16:50:11 - mmengine - INFO - Epoch(val) [4][250/509] eta: 0:01:05 time: 0.2494 data_time: 0.0045 memory: 267 2023/03/09 16:50:22 - mmengine - INFO - Epoch(val) [4][300/509] eta: 0:00:51 time: 0.2201 data_time: 0.0047 memory: 245 2023/03/09 16:50:30 - mmengine - INFO - Epoch(val) [4][350/509] eta: 0:00:37 time: 0.1601 data_time: 0.0049 memory: 254 2023/03/09 16:50:38 - mmengine - INFO - Epoch(val) [4][400/509] eta: 0:00:24 time: 0.1630 data_time: 0.0047 memory: 255 2023/03/09 16:50:46 - mmengine - INFO - Epoch(val) [4][450/509] eta: 0:00:12 time: 0.1614 data_time: 0.0051 memory: 263 2023/03/09 16:50:54 - mmengine - INFO - Epoch(val) [4][500/509] eta: 0:00:01 time: 0.1636 data_time: 0.0048 memory: 255 2023/03/09 16:51:15 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9260 | 0.0000 | 0.2409 | 0.3873 | 0.2249 | 0.2839 | 0.2734 | 0.0000 | 0.9124 | 0.3100 | 0.7725 | 0.0006 | 0.8697 | 0.5127 | 0.8567 | 0.5553 | 0.7128 | 0.5929 | 0.3328 | 0.4613 | 0.8965 | 0.5238 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 16:51:15 - mmengine - INFO - Epoch(val) [4][509/509] car: 0.9260 bicycle: 0.0000 motorcycle: 0.2409 truck: 0.3873 bus: 0.2249 person: 0.2839 bicyclist: 0.2734 motorcyclist: 0.0000 road: 0.9124 parking: 0.3100 sidewalk: 0.7725 other-ground: 0.0006 building: 0.8697 fence: 0.5127 vegetation: 0.8567 trunck: 0.5553 terrian: 0.7128 pole: 0.5929 traffic-sign: 0.3328 miou: 0.4613 acc: 0.8965 acc_cls: 0.5238 2023/03/09 16:51:31 - mmengine - INFO - Epoch(train) [5][ 50/1196] lr: 1.9953e-01 eta: 1:37:10 time: 0.3150 data_time: 0.0227 memory: 1016 loss: 0.2825 loss_sem_seg: 0.2825 2023/03/09 16:51:57 - mmengine - INFO - Epoch(train) [5][ 100/1196] lr: 1.9874e-01 eta: 1:37:00 time: 0.5311 data_time: 0.0033 memory: 1058 loss: 0.2784 loss_sem_seg: 0.2784 2023/03/09 16:52:34 - mmengine - INFO - Epoch(train) [5][ 150/1196] lr: 1.9794e-01 eta: 1:37:15 time: 0.7346 data_time: 0.0036 memory: 1058 loss: 0.2659 loss_sem_seg: 0.2659 2023/03/09 16:52:59 - mmengine - INFO - Epoch(train) [5][ 200/1196] lr: 1.9714e-01 eta: 1:37:01 time: 0.5075 data_time: 0.0036 memory: 1048 loss: 0.2808 loss_sem_seg: 0.2808 2023/03/09 16:53:06 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 16:53:21 - mmengine - INFO - Epoch(train) [5][ 250/1196] lr: 1.9633e-01 eta: 1:36:36 time: 0.4347 data_time: 0.0034 memory: 1027 loss: 0.2748 loss_sem_seg: 0.2748 2023/03/09 16:53:43 - mmengine - INFO - Epoch(train) [5][ 300/1196] lr: 1.9552e-01 eta: 1:36:12 time: 0.4338 data_time: 0.0034 memory: 1004 loss: 0.2732 loss_sem_seg: 0.2732 2023/03/09 16:54:05 - mmengine - INFO - Epoch(train) [5][ 350/1196] lr: 1.9470e-01 eta: 1:35:48 time: 0.4352 data_time: 0.0033 memory: 980 loss: 0.2676 loss_sem_seg: 0.2676 2023/03/09 16:54:26 - mmengine - INFO - Epoch(train) [5][ 400/1196] lr: 1.9388e-01 eta: 1:35:23 time: 0.4329 data_time: 0.0034 memory: 1014 loss: 0.2875 loss_sem_seg: 0.2875 2023/03/09 16:54:48 - mmengine - INFO - Epoch(train) [5][ 450/1196] lr: 1.9304e-01 eta: 1:34:59 time: 0.4329 data_time: 0.0033 memory: 1055 loss: 0.2757 loss_sem_seg: 0.2757 2023/03/09 16:55:10 - mmengine - INFO - Epoch(train) [5][ 500/1196] lr: 1.9221e-01 eta: 1:34:34 time: 0.4312 data_time: 0.0033 memory: 1024 loss: 0.2766 loss_sem_seg: 0.2766 2023/03/09 16:55:31 - mmengine - INFO - Epoch(train) [5][ 550/1196] lr: 1.9137e-01 eta: 1:34:10 time: 0.4320 data_time: 0.0033 memory: 998 loss: 0.2858 loss_sem_seg: 0.2858 2023/03/09 16:55:53 - mmengine - INFO - Epoch(train) [5][ 600/1196] lr: 1.9052e-01 eta: 1:33:46 time: 0.4318 data_time: 0.0033 memory: 1036 loss: 0.2993 loss_sem_seg: 0.2993 2023/03/09 16:56:14 - mmengine - INFO - Epoch(train) [5][ 650/1196] lr: 1.8967e-01 eta: 1:33:22 time: 0.4328 data_time: 0.0033 memory: 1023 loss: 0.2607 loss_sem_seg: 0.2607 2023/03/09 16:56:36 - mmengine - INFO - Epoch(train) [5][ 700/1196] lr: 1.8881e-01 eta: 1:32:57 time: 0.4287 data_time: 0.0033 memory: 1068 loss: 0.2677 loss_sem_seg: 0.2677 2023/03/09 16:56:57 - mmengine - INFO - Epoch(train) [5][ 750/1196] lr: 1.8794e-01 eta: 1:32:32 time: 0.4273 data_time: 0.0032 memory: 1077 loss: 0.2703 loss_sem_seg: 0.2703 2023/03/09 16:57:19 - mmengine - INFO - Epoch(train) [5][ 800/1196] lr: 1.8708e-01 eta: 1:32:08 time: 0.4280 data_time: 0.0033 memory: 1057 loss: 0.2535 loss_sem_seg: 0.2535 2023/03/09 16:57:40 - mmengine - INFO - Epoch(train) [5][ 850/1196] lr: 1.8620e-01 eta: 1:31:44 time: 0.4342 data_time: 0.0034 memory: 1088 loss: 0.2747 loss_sem_seg: 0.2747 2023/03/09 16:58:02 - mmengine - INFO - Epoch(train) [5][ 900/1196] lr: 1.8532e-01 eta: 1:31:19 time: 0.4274 data_time: 0.0033 memory: 989 loss: 0.2681 loss_sem_seg: 0.2681 2023/03/09 16:58:23 - mmengine - INFO - Epoch(train) [5][ 950/1196] lr: 1.8444e-01 eta: 1:30:55 time: 0.4311 data_time: 0.0033 memory: 990 loss: 0.2470 loss_sem_seg: 0.2470 2023/03/09 16:58:45 - mmengine - INFO - Epoch(train) [5][1000/1196] lr: 1.8355e-01 eta: 1:30:31 time: 0.4294 data_time: 0.0033 memory: 1045 loss: 0.2478 loss_sem_seg: 0.2478 2023/03/09 16:59:06 - mmengine - INFO - Epoch(train) [5][1050/1196] lr: 1.8266e-01 eta: 1:30:07 time: 0.4304 data_time: 0.0033 memory: 995 loss: 0.2553 loss_sem_seg: 0.2553 2023/03/09 16:59:28 - mmengine - INFO - Epoch(train) [5][1100/1196] lr: 1.8176e-01 eta: 1:29:44 time: 0.4346 data_time: 0.0033 memory: 1000 loss: 0.2515 loss_sem_seg: 0.2515 2023/03/09 16:59:49 - mmengine - INFO - Epoch(train) [5][1150/1196] lr: 1.8086e-01 eta: 1:29:20 time: 0.4303 data_time: 0.0033 memory: 1027 loss: 0.2721 loss_sem_seg: 0.2721 2023/03/09 17:00:09 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:00:10 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/03/09 17:00:23 - mmengine - INFO - Epoch(val) [5][ 50/509] eta: 0:01:56 time: 0.2531 data_time: 0.0094 memory: 990 2023/03/09 17:00:36 - mmengine - INFO - Epoch(val) [5][100/509] eta: 0:01:42 time: 0.2470 data_time: 0.0046 memory: 264 2023/03/09 17:00:48 - mmengine - INFO - Epoch(val) [5][150/509] eta: 0:01:29 time: 0.2475 data_time: 0.0045 memory: 263 2023/03/09 17:01:01 - mmengine - INFO - Epoch(val) [5][200/509] eta: 0:01:16 time: 0.2477 data_time: 0.0046 memory: 257 2023/03/09 17:01:13 - mmengine - INFO - Epoch(val) [5][250/509] eta: 0:01:04 time: 0.2470 data_time: 0.0048 memory: 267 2023/03/09 17:01:25 - mmengine - INFO - Epoch(val) [5][300/509] eta: 0:00:51 time: 0.2442 data_time: 0.0047 memory: 245 2023/03/09 17:01:37 - mmengine - INFO - Epoch(val) [5][350/509] eta: 0:00:39 time: 0.2447 data_time: 0.0047 memory: 254 2023/03/09 17:01:47 - mmengine - INFO - Epoch(val) [5][400/509] eta: 0:00:26 time: 0.1914 data_time: 0.0050 memory: 255 2023/03/09 17:01:55 - mmengine - INFO - Epoch(val) [5][450/509] eta: 0:00:13 time: 0.1503 data_time: 0.0046 memory: 263 2023/03/09 17:02:02 - mmengine - INFO - Epoch(val) [5][500/509] eta: 0:00:02 time: 0.1590 data_time: 0.0044 memory: 255 2023/03/09 17:02:22 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9420 | 0.0000 | 0.2127 | 0.3351 | 0.3179 | 0.2798 | 0.3413 | 0.0000 | 0.9063 | 0.2728 | 0.7790 | 0.0000 | 0.8891 | 0.5926 | 0.8846 | 0.5462 | 0.7685 | 0.5922 | 0.3583 | 0.4747 | 0.9092 | 0.5619 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:02:22 - mmengine - INFO - Epoch(val) [5][509/509] car: 0.9420 bicycle: 0.0000 motorcycle: 0.2127 truck: 0.3351 bus: 0.3179 person: 0.2798 bicyclist: 0.3413 motorcyclist: 0.0000 road: 0.9063 parking: 0.2728 sidewalk: 0.7790 other-ground: 0.0000 building: 0.8891 fence: 0.5926 vegetation: 0.8846 trunck: 0.5462 terrian: 0.7685 pole: 0.5922 traffic-sign: 0.3583 miou: 0.4747 acc: 0.9092 acc_cls: 0.5619 2023/03/09 17:02:29 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:02:38 - mmengine - INFO - Epoch(train) [6][ 50/1196] lr: 1.7911e-01 eta: 1:28:23 time: 0.3182 data_time: 0.0209 memory: 1078 loss: 0.2587 loss_sem_seg: 0.2587 2023/03/09 17:02:53 - mmengine - INFO - Epoch(train) [6][ 100/1196] lr: 1.7819e-01 eta: 1:27:46 time: 0.2950 data_time: 0.0032 memory: 1025 loss: 0.2570 loss_sem_seg: 0.2570 2023/03/09 17:03:13 - mmengine - INFO - Epoch(train) [6][ 150/1196] lr: 1.7727e-01 eta: 1:27:19 time: 0.3966 data_time: 0.0031 memory: 1053 loss: 0.2729 loss_sem_seg: 0.2729 2023/03/09 17:03:49 - mmengine - INFO - Epoch(train) [6][ 200/1196] lr: 1.7635e-01 eta: 1:27:25 time: 0.7322 data_time: 0.0031 memory: 1054 loss: 0.2721 loss_sem_seg: 0.2721 2023/03/09 17:04:17 - mmengine - INFO - Epoch(train) [6][ 250/1196] lr: 1.7542e-01 eta: 1:27:13 time: 0.5635 data_time: 0.0035 memory: 1031 loss: 0.2445 loss_sem_seg: 0.2445 2023/03/09 17:04:39 - mmengine - INFO - Epoch(train) [6][ 300/1196] lr: 1.7448e-01 eta: 1:26:50 time: 0.4321 data_time: 0.0032 memory: 1079 loss: 0.2773 loss_sem_seg: 0.2773 2023/03/09 17:05:00 - mmengine - INFO - Epoch(train) [6][ 350/1196] lr: 1.7354e-01 eta: 1:26:26 time: 0.4311 data_time: 0.0032 memory: 1028 loss: 0.2746 loss_sem_seg: 0.2746 2023/03/09 17:05:22 - mmengine - INFO - Epoch(train) [6][ 400/1196] lr: 1.7260e-01 eta: 1:26:02 time: 0.4274 data_time: 0.0032 memory: 1042 loss: 0.2577 loss_sem_seg: 0.2577 2023/03/09 17:05:44 - mmengine - INFO - Epoch(train) [6][ 450/1196] lr: 1.7165e-01 eta: 1:25:38 time: 0.4330 data_time: 0.0031 memory: 1075 loss: 0.2568 loss_sem_seg: 0.2568 2023/03/09 17:06:05 - mmengine - INFO - Epoch(train) [6][ 500/1196] lr: 1.7070e-01 eta: 1:25:15 time: 0.4319 data_time: 0.0032 memory: 1040 loss: 0.2590 loss_sem_seg: 0.2590 2023/03/09 17:06:27 - mmengine - INFO - Epoch(train) [6][ 550/1196] lr: 1.6975e-01 eta: 1:24:51 time: 0.4330 data_time: 0.0033 memory: 1050 loss: 0.2577 loss_sem_seg: 0.2577 2023/03/09 17:06:48 - mmengine - INFO - Epoch(train) [6][ 600/1196] lr: 1.6879e-01 eta: 1:24:27 time: 0.4275 data_time: 0.0032 memory: 1023 loss: 0.2522 loss_sem_seg: 0.2522 2023/03/09 17:07:10 - mmengine - INFO - Epoch(train) [6][ 650/1196] lr: 1.6783e-01 eta: 1:24:03 time: 0.4305 data_time: 0.0034 memory: 1029 loss: 0.2624 loss_sem_seg: 0.2624 2023/03/09 17:07:31 - mmengine - INFO - Epoch(train) [6][ 700/1196] lr: 1.6686e-01 eta: 1:23:40 time: 0.4306 data_time: 0.0031 memory: 1033 loss: 0.2799 loss_sem_seg: 0.2799 2023/03/09 17:07:53 - mmengine - INFO - Epoch(train) [6][ 750/1196] lr: 1.6590e-01 eta: 1:23:17 time: 0.4339 data_time: 0.0034 memory: 1043 loss: 0.2386 loss_sem_seg: 0.2386 2023/03/09 17:08:15 - mmengine - INFO - Epoch(train) [6][ 800/1196] lr: 1.6492e-01 eta: 1:22:53 time: 0.4334 data_time: 0.0032 memory: 1035 loss: 0.2484 loss_sem_seg: 0.2484 2023/03/09 17:08:36 - mmengine - INFO - Epoch(train) [6][ 850/1196] lr: 1.6395e-01 eta: 1:22:30 time: 0.4317 data_time: 0.0032 memory: 1024 loss: 0.2490 loss_sem_seg: 0.2490 2023/03/09 17:08:58 - mmengine - INFO - Epoch(train) [6][ 900/1196] lr: 1.6297e-01 eta: 1:22:06 time: 0.4310 data_time: 0.0032 memory: 1047 loss: 0.2581 loss_sem_seg: 0.2581 2023/03/09 17:09:19 - mmengine - INFO - Epoch(train) [6][ 950/1196] lr: 1.6199e-01 eta: 1:21:43 time: 0.4306 data_time: 0.0032 memory: 991 loss: 0.2586 loss_sem_seg: 0.2586 2023/03/09 17:09:41 - mmengine - INFO - Epoch(train) [6][1000/1196] lr: 1.6100e-01 eta: 1:21:19 time: 0.4299 data_time: 0.0032 memory: 1044 loss: 0.2440 loss_sem_seg: 0.2440 2023/03/09 17:09:49 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:10:02 - mmengine - INFO - Epoch(train) [6][1050/1196] lr: 1.6001e-01 eta: 1:20:56 time: 0.4308 data_time: 0.0032 memory: 1017 loss: 0.2554 loss_sem_seg: 0.2554 2023/03/09 17:10:24 - mmengine - INFO - Epoch(train) [6][1100/1196] lr: 1.5902e-01 eta: 1:20:33 time: 0.4306 data_time: 0.0033 memory: 1033 loss: 0.2562 loss_sem_seg: 0.2562 2023/03/09 17:10:45 - mmengine - INFO - Epoch(train) [6][1150/1196] lr: 1.5802e-01 eta: 1:20:09 time: 0.4285 data_time: 0.0032 memory: 1015 loss: 0.2981 loss_sem_seg: 0.2981 2023/03/09 17:11:05 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:11:05 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/03/09 17:11:19 - mmengine - INFO - Epoch(val) [6][ 50/509] eta: 0:01:58 time: 0.2581 data_time: 0.0096 memory: 1004 2023/03/09 17:11:32 - mmengine - INFO - Epoch(val) [6][100/509] eta: 0:01:44 time: 0.2513 data_time: 0.0049 memory: 264 2023/03/09 17:11:44 - mmengine - INFO - Epoch(val) [6][150/509] eta: 0:01:30 time: 0.2495 data_time: 0.0046 memory: 263 2023/03/09 17:11:57 - mmengine - INFO - Epoch(val) [6][200/509] eta: 0:01:17 time: 0.2486 data_time: 0.0047 memory: 257 2023/03/09 17:12:09 - mmengine - INFO - Epoch(val) [6][250/509] eta: 0:01:05 time: 0.2477 data_time: 0.0045 memory: 267 2023/03/09 17:12:21 - mmengine - INFO - Epoch(val) [6][300/509] eta: 0:00:52 time: 0.2442 data_time: 0.0046 memory: 245 2023/03/09 17:12:34 - mmengine - INFO - Epoch(val) [6][350/509] eta: 0:00:39 time: 0.2465 data_time: 0.0045 memory: 254 2023/03/09 17:12:46 - mmengine - INFO - Epoch(val) [6][400/509] eta: 0:00:27 time: 0.2467 data_time: 0.0044 memory: 255 2023/03/09 17:12:58 - mmengine - INFO - Epoch(val) [6][450/509] eta: 0:00:14 time: 0.2412 data_time: 0.0045 memory: 263 2023/03/09 17:13:07 - mmengine - INFO - Epoch(val) [6][500/509] eta: 0:00:02 time: 0.1736 data_time: 0.0049 memory: 255 2023/03/09 17:13:26 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9438 | 0.0000 | 0.1768 | 0.5795 | 0.3713 | 0.3404 | 0.2199 | 0.0000 | 0.9076 | 0.3657 | 0.7755 | 0.0025 | 0.8763 | 0.5291 | 0.8808 | 0.6052 | 0.7580 | 0.5994 | 0.3648 | 0.4893 | 0.9068 | 0.5677 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:13:26 - mmengine - INFO - Epoch(val) [6][509/509] car: 0.9438 bicycle: 0.0000 motorcycle: 0.1768 truck: 0.5795 bus: 0.3713 person: 0.3404 bicyclist: 0.2199 motorcyclist: 0.0000 road: 0.9076 parking: 0.3657 sidewalk: 0.7755 other-ground: 0.0025 building: 0.8763 fence: 0.5291 vegetation: 0.8808 trunck: 0.6052 terrian: 0.7580 pole: 0.5994 traffic-sign: 0.3648 miou: 0.4893 acc: 0.9068 acc_cls: 0.5677 2023/03/09 17:13:42 - mmengine - INFO - Epoch(train) [7][ 50/1196] lr: 1.5610e-01 eta: 1:19:16 time: 0.3207 data_time: 0.0218 memory: 1076 loss: 0.2386 loss_sem_seg: 0.2386 2023/03/09 17:13:57 - mmengine - INFO - Epoch(train) [7][ 100/1196] lr: 1.5510e-01 eta: 1:18:44 time: 0.3033 data_time: 0.0033 memory: 1023 loss: 0.2644 loss_sem_seg: 0.2644 2023/03/09 17:14:12 - mmengine - INFO - Epoch(train) [7][ 150/1196] lr: 1.5410e-01 eta: 1:18:11 time: 0.2926 data_time: 0.0032 memory: 1029 loss: 0.2486 loss_sem_seg: 0.2486 2023/03/09 17:14:29 - mmengine - INFO - Epoch(train) [7][ 200/1196] lr: 1.5309e-01 eta: 1:17:41 time: 0.3387 data_time: 0.0031 memory: 1035 loss: 0.2457 loss_sem_seg: 0.2457 2023/03/09 17:15:05 - mmengine - INFO - Epoch(train) [7][ 250/1196] lr: 1.5208e-01 eta: 1:17:39 time: 0.7282 data_time: 0.0031 memory: 1010 loss: 0.2478 loss_sem_seg: 0.2478 2023/03/09 17:15:36 - mmengine - INFO - Epoch(train) [7][ 300/1196] lr: 1.5106e-01 eta: 1:17:30 time: 0.6251 data_time: 0.0034 memory: 1047 loss: 0.2646 loss_sem_seg: 0.2646 2023/03/09 17:15:59 - mmengine - INFO - Epoch(train) [7][ 350/1196] lr: 1.5005e-01 eta: 1:17:08 time: 0.4537 data_time: 0.0033 memory: 1007 loss: 0.2523 loss_sem_seg: 0.2523 2023/03/09 17:16:21 - mmengine - INFO - Epoch(train) [7][ 400/1196] lr: 1.4903e-01 eta: 1:16:45 time: 0.4344 data_time: 0.0034 memory: 1017 loss: 0.2473 loss_sem_seg: 0.2473 2023/03/09 17:16:43 - mmengine - INFO - Epoch(train) [7][ 450/1196] lr: 1.4801e-01 eta: 1:16:23 time: 0.4359 data_time: 0.0034 memory: 991 loss: 0.2403 loss_sem_seg: 0.2403 2023/03/09 17:17:04 - mmengine - INFO - Epoch(train) [7][ 500/1196] lr: 1.4698e-01 eta: 1:16:00 time: 0.4362 data_time: 0.0033 memory: 1016 loss: 0.2477 loss_sem_seg: 0.2477 2023/03/09 17:17:26 - mmengine - INFO - Epoch(train) [7][ 550/1196] lr: 1.4596e-01 eta: 1:15:37 time: 0.4367 data_time: 0.0034 memory: 1008 loss: 0.2408 loss_sem_seg: 0.2408 2023/03/09 17:17:48 - mmengine - INFO - Epoch(train) [7][ 600/1196] lr: 1.4493e-01 eta: 1:15:15 time: 0.4410 data_time: 0.0035 memory: 1004 loss: 0.2358 loss_sem_seg: 0.2358 2023/03/09 17:18:10 - mmengine - INFO - Epoch(train) [7][ 650/1196] lr: 1.4390e-01 eta: 1:14:52 time: 0.4409 data_time: 0.0034 memory: 1059 loss: 0.2547 loss_sem_seg: 0.2547 2023/03/09 17:18:32 - mmengine - INFO - Epoch(train) [7][ 700/1196] lr: 1.4287e-01 eta: 1:14:30 time: 0.4365 data_time: 0.0037 memory: 1020 loss: 0.2552 loss_sem_seg: 0.2552 2023/03/09 17:18:54 - mmengine - INFO - Epoch(train) [7][ 750/1196] lr: 1.4184e-01 eta: 1:14:07 time: 0.4352 data_time: 0.0034 memory: 1005 loss: 0.2522 loss_sem_seg: 0.2522 2023/03/09 17:19:16 - mmengine - INFO - Epoch(train) [7][ 800/1196] lr: 1.4081e-01 eta: 1:13:44 time: 0.4375 data_time: 0.0035 memory: 999 loss: 0.2310 loss_sem_seg: 0.2310 2023/03/09 17:19:26 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:19:38 - mmengine - INFO - Epoch(train) [7][ 850/1196] lr: 1.3977e-01 eta: 1:13:22 time: 0.4362 data_time: 0.0034 memory: 1015 loss: 0.2366 loss_sem_seg: 0.2366 2023/03/09 17:19:59 - mmengine - INFO - Epoch(train) [7][ 900/1196] lr: 1.3873e-01 eta: 1:12:59 time: 0.4338 data_time: 0.0036 memory: 992 loss: 0.2403 loss_sem_seg: 0.2403 2023/03/09 17:20:21 - mmengine - INFO - Epoch(train) [7][ 950/1196] lr: 1.3770e-01 eta: 1:12:36 time: 0.4365 data_time: 0.0034 memory: 1048 loss: 0.2338 loss_sem_seg: 0.2338 2023/03/09 17:20:43 - mmengine - INFO - Epoch(train) [7][1000/1196] lr: 1.3666e-01 eta: 1:12:14 time: 0.4416 data_time: 0.0033 memory: 1030 loss: 0.2416 loss_sem_seg: 0.2416 2023/03/09 17:21:05 - mmengine - INFO - Epoch(train) [7][1050/1196] lr: 1.3562e-01 eta: 1:11:51 time: 0.4346 data_time: 0.0037 memory: 1028 loss: 0.2530 loss_sem_seg: 0.2530 2023/03/09 17:21:27 - mmengine - INFO - Epoch(train) [7][1100/1196] lr: 1.3457e-01 eta: 1:11:29 time: 0.4391 data_time: 0.0034 memory: 1019 loss: 0.2623 loss_sem_seg: 0.2623 2023/03/09 17:21:49 - mmengine - INFO - Epoch(train) [7][1150/1196] lr: 1.3353e-01 eta: 1:11:06 time: 0.4363 data_time: 0.0034 memory: 1010 loss: 0.2303 loss_sem_seg: 0.2303 2023/03/09 17:22:09 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:22:09 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/03/09 17:22:23 - mmengine - INFO - Epoch(val) [7][ 50/509] eta: 0:01:56 time: 0.2534 data_time: 0.0093 memory: 1034 2023/03/09 17:22:36 - mmengine - INFO - Epoch(val) [7][100/509] eta: 0:01:42 time: 0.2476 data_time: 0.0050 memory: 264 2023/03/09 17:22:48 - mmengine - INFO - Epoch(val) [7][150/509] eta: 0:01:29 time: 0.2456 data_time: 0.0052 memory: 263 2023/03/09 17:23:00 - mmengine - INFO - Epoch(val) [7][200/509] eta: 0:01:16 time: 0.2472 data_time: 0.0047 memory: 257 2023/03/09 17:23:13 - mmengine - INFO - Epoch(val) [7][250/509] eta: 0:01:04 time: 0.2471 data_time: 0.0048 memory: 267 2023/03/09 17:23:25 - mmengine - INFO - Epoch(val) [7][300/509] eta: 0:00:51 time: 0.2462 data_time: 0.0059 memory: 245 2023/03/09 17:23:37 - mmengine - INFO - Epoch(val) [7][350/509] eta: 0:00:39 time: 0.2468 data_time: 0.0054 memory: 254 2023/03/09 17:23:50 - mmengine - INFO - Epoch(val) [7][400/509] eta: 0:00:26 time: 0.2464 data_time: 0.0052 memory: 255 2023/03/09 17:24:02 - mmengine - INFO - Epoch(val) [7][450/509] eta: 0:00:14 time: 0.2451 data_time: 0.0052 memory: 263 2023/03/09 17:24:14 - mmengine - INFO - Epoch(val) [7][500/509] eta: 0:00:02 time: 0.2454 data_time: 0.0054 memory: 255 2023/03/09 17:24:36 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9456 | 0.0179 | 0.3540 | 0.5767 | 0.4044 | 0.4110 | 0.6301 | 0.0000 | 0.8955 | 0.2751 | 0.7570 | 0.0005 | 0.8911 | 0.5455 | 0.8841 | 0.6372 | 0.7708 | 0.6048 | 0.3395 | 0.5232 | 0.9069 | 0.5918 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:24:36 - mmengine - INFO - Epoch(val) [7][509/509] car: 0.9456 bicycle: 0.0179 motorcycle: 0.3540 truck: 0.5767 bus: 0.4044 person: 0.4110 bicyclist: 0.6301 motorcyclist: 0.0000 road: 0.8955 parking: 0.2751 sidewalk: 0.7570 other-ground: 0.0005 building: 0.8911 fence: 0.5455 vegetation: 0.8841 trunck: 0.6372 terrian: 0.7708 pole: 0.6048 traffic-sign: 0.3395 miou: 0.5232 acc: 0.9069 acc_cls: 0.5918 2023/03/09 17:24:53 - mmengine - INFO - Epoch(train) [8][ 50/1196] lr: 1.3152e-01 eta: 1:10:16 time: 0.3259 data_time: 0.0218 memory: 1017 loss: 0.2348 loss_sem_seg: 0.2348 2023/03/09 17:25:08 - mmengine - INFO - Epoch(train) [8][ 100/1196] lr: 1.3048e-01 eta: 1:09:47 time: 0.3066 data_time: 0.0034 memory: 1015 loss: 0.2318 loss_sem_seg: 0.2318 2023/03/09 17:25:23 - mmengine - INFO - Epoch(train) [8][ 150/1196] lr: 1.2943e-01 eta: 1:09:17 time: 0.3014 data_time: 0.0035 memory: 1062 loss: 0.2397 loss_sem_seg: 0.2397 2023/03/09 17:25:38 - mmengine - INFO - Epoch(train) [8][ 200/1196] lr: 1.2838e-01 eta: 1:08:47 time: 0.2957 data_time: 0.0035 memory: 1006 loss: 0.2347 loss_sem_seg: 0.2347 2023/03/09 17:25:53 - mmengine - INFO - Epoch(train) [8][ 250/1196] lr: 1.2733e-01 eta: 1:08:17 time: 0.3010 data_time: 0.0036 memory: 1090 loss: 0.2302 loss_sem_seg: 0.2302 2023/03/09 17:26:12 - mmengine - INFO - Epoch(train) [8][ 300/1196] lr: 1.2629e-01 eta: 1:07:52 time: 0.3812 data_time: 0.0034 memory: 1005 loss: 0.2432 loss_sem_seg: 0.2432 2023/03/09 17:26:47 - mmengine - INFO - Epoch(train) [8][ 350/1196] lr: 1.2524e-01 eta: 1:07:44 time: 0.7066 data_time: 0.0042 memory: 1060 loss: 0.2253 loss_sem_seg: 0.2253 2023/03/09 17:27:10 - mmengine - INFO - Epoch(train) [8][ 400/1196] lr: 1.2419e-01 eta: 1:07:23 time: 0.4498 data_time: 0.0035 memory: 1039 loss: 0.2364 loss_sem_seg: 0.2364 2023/03/09 17:27:32 - mmengine - INFO - Epoch(train) [8][ 450/1196] lr: 1.2314e-01 eta: 1:07:01 time: 0.4430 data_time: 0.0035 memory: 998 loss: 0.2348 loss_sem_seg: 0.2348 2023/03/09 17:27:54 - mmengine - INFO - Epoch(train) [8][ 500/1196] lr: 1.2209e-01 eta: 1:06:39 time: 0.4432 data_time: 0.0035 memory: 993 loss: 0.2227 loss_sem_seg: 0.2227 2023/03/09 17:28:16 - mmengine - INFO - Epoch(train) [8][ 550/1196] lr: 1.2103e-01 eta: 1:06:16 time: 0.4345 data_time: 0.0034 memory: 1074 loss: 0.2299 loss_sem_seg: 0.2299 2023/03/09 17:28:38 - mmengine - INFO - Epoch(train) [8][ 600/1196] lr: 1.1998e-01 eta: 1:05:54 time: 0.4419 data_time: 0.0035 memory: 1029 loss: 0.2191 loss_sem_seg: 0.2191 2023/03/09 17:28:50 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:29:00 - mmengine - INFO - Epoch(train) [8][ 650/1196] lr: 1.1893e-01 eta: 1:05:32 time: 0.4370 data_time: 0.0033 memory: 1074 loss: 0.2492 loss_sem_seg: 0.2492 2023/03/09 17:29:23 - mmengine - INFO - Epoch(train) [8][ 700/1196] lr: 1.1788e-01 eta: 1:05:11 time: 0.4654 data_time: 0.0035 memory: 1040 loss: 0.2206 loss_sem_seg: 0.2206 2023/03/09 17:29:46 - mmengine - INFO - Epoch(train) [8][ 750/1196] lr: 1.1683e-01 eta: 1:04:50 time: 0.4648 data_time: 0.0034 memory: 1030 loss: 0.2221 loss_sem_seg: 0.2221 2023/03/09 17:30:09 - mmengine - INFO - Epoch(train) [8][ 800/1196] lr: 1.1578e-01 eta: 1:04:28 time: 0.4465 data_time: 0.0035 memory: 1024 loss: 0.2145 loss_sem_seg: 0.2145 2023/03/09 17:30:31 - mmengine - INFO - Epoch(train) [8][ 850/1196] lr: 1.1473e-01 eta: 1:04:07 time: 0.4459 data_time: 0.0036 memory: 1005 loss: 0.2322 loss_sem_seg: 0.2322 2023/03/09 17:30:53 - mmengine - INFO - Epoch(train) [8][ 900/1196] lr: 1.1368e-01 eta: 1:03:44 time: 0.4352 data_time: 0.0036 memory: 1025 loss: 0.2265 loss_sem_seg: 0.2265 2023/03/09 17:31:15 - mmengine - INFO - Epoch(train) [8][ 950/1196] lr: 1.1263e-01 eta: 1:03:22 time: 0.4392 data_time: 0.0035 memory: 1040 loss: 0.2281 loss_sem_seg: 0.2281 2023/03/09 17:31:37 - mmengine - INFO - Epoch(train) [8][1000/1196] lr: 1.1159e-01 eta: 1:03:00 time: 0.4363 data_time: 0.0036 memory: 1008 loss: 0.2179 loss_sem_seg: 0.2179 2023/03/09 17:31:59 - mmengine - INFO - Epoch(train) [8][1050/1196] lr: 1.1054e-01 eta: 1:02:38 time: 0.4436 data_time: 0.0035 memory: 1035 loss: 0.2156 loss_sem_seg: 0.2156 2023/03/09 17:32:21 - mmengine - INFO - Epoch(train) [8][1100/1196] lr: 1.0949e-01 eta: 1:02:16 time: 0.4425 data_time: 0.0034 memory: 1060 loss: 0.2397 loss_sem_seg: 0.2397 2023/03/09 17:32:43 - mmengine - INFO - Epoch(train) [8][1150/1196] lr: 1.0844e-01 eta: 1:01:54 time: 0.4381 data_time: 0.0036 memory: 1026 loss: 0.2145 loss_sem_seg: 0.2145 2023/03/09 17:33:03 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:33:03 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/03/09 17:33:17 - mmengine - INFO - Epoch(val) [8][ 50/509] eta: 0:01:57 time: 0.2569 data_time: 0.0088 memory: 992 2023/03/09 17:33:30 - mmengine - INFO - Epoch(val) [8][100/509] eta: 0:01:43 time: 0.2496 data_time: 0.0053 memory: 264 2023/03/09 17:33:42 - mmengine - INFO - Epoch(val) [8][150/509] eta: 0:01:30 time: 0.2474 data_time: 0.0052 memory: 263 2023/03/09 17:33:55 - mmengine - INFO - Epoch(val) [8][200/509] eta: 0:01:17 time: 0.2504 data_time: 0.0053 memory: 257 2023/03/09 17:34:07 - mmengine - INFO - Epoch(val) [8][250/509] eta: 0:01:04 time: 0.2481 data_time: 0.0052 memory: 267 2023/03/09 17:34:19 - mmengine - INFO - Epoch(val) [8][300/509] eta: 0:00:52 time: 0.2463 data_time: 0.0055 memory: 245 2023/03/09 17:34:32 - mmengine - INFO - Epoch(val) [8][350/509] eta: 0:00:39 time: 0.2465 data_time: 0.0053 memory: 254 2023/03/09 17:34:44 - mmengine - INFO - Epoch(val) [8][400/509] eta: 0:00:27 time: 0.2482 data_time: 0.0052 memory: 255 2023/03/09 17:34:57 - mmengine - INFO - Epoch(val) [8][450/509] eta: 0:00:14 time: 0.2503 data_time: 0.0051 memory: 263 2023/03/09 17:35:09 - mmengine - INFO - Epoch(val) [8][500/509] eta: 0:00:02 time: 0.2481 data_time: 0.0053 memory: 255 2023/03/09 17:35:32 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9480 | 0.0065 | 0.3450 | 0.5124 | 0.4263 | 0.5105 | 0.6225 | 0.0000 | 0.9147 | 0.2394 | 0.7834 | 0.0007 | 0.8962 | 0.5559 | 0.8834 | 0.6605 | 0.7727 | 0.6277 | 0.3994 | 0.5318 | 0.9116 | 0.6227 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:35:32 - mmengine - INFO - Epoch(val) [8][509/509] car: 0.9480 bicycle: 0.0065 motorcycle: 0.3450 truck: 0.5124 bus: 0.4263 person: 0.5105 bicyclist: 0.6225 motorcyclist: 0.0000 road: 0.9147 parking: 0.2394 sidewalk: 0.7834 other-ground: 0.0007 building: 0.8962 fence: 0.5559 vegetation: 0.8834 trunck: 0.6605 terrian: 0.7727 pole: 0.6277 traffic-sign: 0.3994 miou: 0.5318 acc: 0.9116 acc_cls: 0.6227 2023/03/09 17:35:55 - mmengine - INFO - Epoch(train) [9][ 50/1196] lr: 1.0644e-01 eta: 1:01:12 time: 0.4639 data_time: 0.0232 memory: 1017 loss: 0.2305 loss_sem_seg: 0.2305 2023/03/09 17:36:12 - mmengine - INFO - Epoch(train) [9][ 100/1196] lr: 1.0540e-01 eta: 1:00:45 time: 0.3329 data_time: 0.0041 memory: 1039 loss: 0.2154 loss_sem_seg: 0.2154 2023/03/09 17:36:27 - mmengine - INFO - Epoch(train) [9][ 150/1196] lr: 1.0435e-01 eta: 1:00:17 time: 0.3056 data_time: 0.0035 memory: 1029 loss: 0.2199 loss_sem_seg: 0.2199 2023/03/09 17:36:42 - mmengine - INFO - Epoch(train) [9][ 200/1196] lr: 1.0331e-01 eta: 0:59:50 time: 0.3044 data_time: 0.0033 memory: 1107 loss: 0.2307 loss_sem_seg: 0.2307 2023/03/09 17:36:57 - mmengine - INFO - Epoch(train) [9][ 250/1196] lr: 1.0227e-01 eta: 0:59:22 time: 0.2977 data_time: 0.0035 memory: 1004 loss: 0.2069 loss_sem_seg: 0.2069 2023/03/09 17:37:12 - mmengine - INFO - Epoch(train) [9][ 300/1196] lr: 1.0123e-01 eta: 0:58:54 time: 0.2980 data_time: 0.0035 memory: 1030 loss: 0.2234 loss_sem_seg: 0.2234 2023/03/09 17:37:27 - mmengine - INFO - Epoch(train) [9][ 350/1196] lr: 1.0020e-01 eta: 0:58:27 time: 0.3040 data_time: 0.0036 memory: 1073 loss: 0.2376 loss_sem_seg: 0.2376 2023/03/09 17:37:46 - mmengine - INFO - Epoch(train) [9][ 400/1196] lr: 9.9161e-02 eta: 0:58:02 time: 0.3671 data_time: 0.0034 memory: 1032 loss: 0.2263 loss_sem_seg: 0.2263 2023/03/09 17:38:08 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:38:15 - mmengine - INFO - Epoch(train) [9][ 450/1196] lr: 9.8127e-02 eta: 0:57:47 time: 0.5988 data_time: 0.0037 memory: 1061 loss: 0.2270 loss_sem_seg: 0.2270 2023/03/09 17:38:37 - mmengine - INFO - Epoch(train) [9][ 500/1196] lr: 9.7095e-02 eta: 0:57:25 time: 0.4361 data_time: 0.0036 memory: 1070 loss: 0.2026 loss_sem_seg: 0.2026 2023/03/09 17:38:59 - mmengine - INFO - Epoch(train) [9][ 550/1196] lr: 9.6065e-02 eta: 0:57:03 time: 0.4395 data_time: 0.0034 memory: 1036 loss: 0.2264 loss_sem_seg: 0.2264 2023/03/09 17:39:21 - mmengine - INFO - Epoch(train) [9][ 600/1196] lr: 9.5036e-02 eta: 0:56:41 time: 0.4363 data_time: 0.0034 memory: 1001 loss: 0.2162 loss_sem_seg: 0.2162 2023/03/09 17:39:43 - mmengine - INFO - Epoch(train) [9][ 650/1196] lr: 9.4009e-02 eta: 0:56:19 time: 0.4361 data_time: 0.0035 memory: 1030 loss: 0.2089 loss_sem_seg: 0.2089 2023/03/09 17:40:05 - mmengine - INFO - Epoch(train) [9][ 700/1196] lr: 9.2985e-02 eta: 0:55:57 time: 0.4369 data_time: 0.0036 memory: 1019 loss: 0.2266 loss_sem_seg: 0.2266 2023/03/09 17:40:26 - mmengine - INFO - Epoch(train) [9][ 750/1196] lr: 9.1962e-02 eta: 0:55:35 time: 0.4355 data_time: 0.0037 memory: 973 loss: 0.2089 loss_sem_seg: 0.2089 2023/03/09 17:40:48 - mmengine - INFO - Epoch(train) [9][ 800/1196] lr: 9.0942e-02 eta: 0:55:13 time: 0.4374 data_time: 0.0035 memory: 1051 loss: 0.2194 loss_sem_seg: 0.2194 2023/03/09 17:41:10 - mmengine - INFO - Epoch(train) [9][ 850/1196] lr: 8.9923e-02 eta: 0:54:51 time: 0.4341 data_time: 0.0035 memory: 1031 loss: 0.2102 loss_sem_seg: 0.2102 2023/03/09 17:41:32 - mmengine - INFO - Epoch(train) [9][ 900/1196] lr: 8.8907e-02 eta: 0:54:30 time: 0.4394 data_time: 0.0036 memory: 999 loss: 0.2168 loss_sem_seg: 0.2168 2023/03/09 17:41:54 - mmengine - INFO - Epoch(train) [9][ 950/1196] lr: 8.7894e-02 eta: 0:54:08 time: 0.4383 data_time: 0.0033 memory: 1045 loss: 0.2079 loss_sem_seg: 0.2079 2023/03/09 17:42:16 - mmengine - INFO - Epoch(train) [9][1000/1196] lr: 8.6883e-02 eta: 0:53:46 time: 0.4438 data_time: 0.0035 memory: 1000 loss: 0.2040 loss_sem_seg: 0.2040 2023/03/09 17:42:38 - mmengine - INFO - Epoch(train) [9][1050/1196] lr: 8.5874e-02 eta: 0:53:24 time: 0.4352 data_time: 0.0034 memory: 1028 loss: 0.2156 loss_sem_seg: 0.2156 2023/03/09 17:43:00 - mmengine - INFO - Epoch(train) [9][1100/1196] lr: 8.4868e-02 eta: 0:53:02 time: 0.4402 data_time: 0.0036 memory: 1058 loss: 0.1876 loss_sem_seg: 0.1876 2023/03/09 17:43:22 - mmengine - INFO - Epoch(train) [9][1150/1196] lr: 8.3865e-02 eta: 0:52:41 time: 0.4395 data_time: 0.0035 memory: 1031 loss: 0.2271 loss_sem_seg: 0.2271 2023/03/09 17:43:42 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:43:42 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/03/09 17:43:56 - mmengine - INFO - Epoch(val) [9][ 50/509] eta: 0:01:53 time: 0.2479 data_time: 0.0091 memory: 996 2023/03/09 17:44:08 - mmengine - INFO - Epoch(val) [9][100/509] eta: 0:01:41 time: 0.2469 data_time: 0.0054 memory: 264 2023/03/09 17:44:21 - mmengine - INFO - Epoch(val) [9][150/509] eta: 0:01:29 time: 0.2500 data_time: 0.0048 memory: 263 2023/03/09 17:44:33 - mmengine - INFO - Epoch(val) [9][200/509] eta: 0:01:16 time: 0.2484 data_time: 0.0045 memory: 257 2023/03/09 17:44:45 - mmengine - INFO - Epoch(val) [9][250/509] eta: 0:01:04 time: 0.2454 data_time: 0.0050 memory: 267 2023/03/09 17:44:58 - mmengine - INFO - Epoch(val) [9][300/509] eta: 0:00:51 time: 0.2430 data_time: 0.0052 memory: 245 2023/03/09 17:45:10 - mmengine - INFO - Epoch(val) [9][350/509] eta: 0:00:39 time: 0.2477 data_time: 0.0052 memory: 254 2023/03/09 17:45:22 - mmengine - INFO - Epoch(val) [9][400/509] eta: 0:00:26 time: 0.2482 data_time: 0.0051 memory: 255 2023/03/09 17:45:35 - mmengine - INFO - Epoch(val) [9][450/509] eta: 0:00:14 time: 0.2492 data_time: 0.0050 memory: 263 2023/03/09 17:45:47 - mmengine - INFO - Epoch(val) [9][500/509] eta: 0:00:02 time: 0.2469 data_time: 0.0044 memory: 255 2023/03/09 17:46:14 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9557 | 0.0168 | 0.4504 | 0.6306 | 0.4995 | 0.4796 | 0.4293 | 0.0000 | 0.9248 | 0.3853 | 0.7917 | 0.0012 | 0.9036 | 0.5939 | 0.8841 | 0.6713 | 0.7641 | 0.6219 | 0.4222 | 0.5487 | 0.9162 | 0.6320 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:46:14 - mmengine - INFO - Epoch(val) [9][509/509] car: 0.9557 bicycle: 0.0168 motorcycle: 0.4504 truck: 0.6306 bus: 0.4995 person: 0.4796 bicyclist: 0.4293 motorcyclist: 0.0000 road: 0.9248 parking: 0.3853 sidewalk: 0.7917 other-ground: 0.0012 building: 0.9036 fence: 0.5939 vegetation: 0.8841 trunck: 0.6713 terrian: 0.7641 pole: 0.6219 traffic-sign: 0.4222 miou: 0.5487 acc: 0.9162 acc_cls: 0.6320 2023/03/09 17:46:37 - mmengine - INFO - Epoch(train) [10][ 50/1196] lr: 8.1947e-02 eta: 0:51:59 time: 0.4652 data_time: 0.0240 memory: 1050 loss: 0.2046 loss_sem_seg: 0.2046 2023/03/09 17:46:59 - mmengine - INFO - Epoch(train) [10][ 100/1196] lr: 8.0952e-02 eta: 0:51:37 time: 0.4310 data_time: 0.0037 memory: 1045 loss: 0.2133 loss_sem_seg: 0.2133 2023/03/09 17:47:18 - mmengine - INFO - Epoch(train) [10][ 150/1196] lr: 7.9960e-02 eta: 0:51:14 time: 0.3925 data_time: 0.0037 memory: 1044 loss: 0.2132 loss_sem_seg: 0.2132 2023/03/09 17:47:34 - mmengine - INFO - Epoch(train) [10][ 200/1196] lr: 7.8971e-02 eta: 0:50:48 time: 0.3081 data_time: 0.0034 memory: 1025 loss: 0.2067 loss_sem_seg: 0.2067 2023/03/09 17:47:45 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:47:49 - mmengine - INFO - Epoch(train) [10][ 250/1196] lr: 7.7985e-02 eta: 0:50:22 time: 0.3034 data_time: 0.0035 memory: 1017 loss: 0.2003 loss_sem_seg: 0.2003 2023/03/09 17:48:04 - mmengine - INFO - Epoch(train) [10][ 300/1196] lr: 7.7003e-02 eta: 0:49:56 time: 0.3053 data_time: 0.0033 memory: 994 loss: 0.2078 loss_sem_seg: 0.2078 2023/03/09 17:48:19 - mmengine - INFO - Epoch(train) [10][ 350/1196] lr: 7.6023e-02 eta: 0:49:30 time: 0.2920 data_time: 0.0033 memory: 1006 loss: 0.2052 loss_sem_seg: 0.2052 2023/03/09 17:48:34 - mmengine - INFO - Epoch(train) [10][ 400/1196] lr: 7.5048e-02 eta: 0:49:04 time: 0.2982 data_time: 0.0034 memory: 1081 loss: 0.2172 loss_sem_seg: 0.2172 2023/03/09 17:48:49 - mmengine - INFO - Epoch(train) [10][ 450/1196] lr: 7.4075e-02 eta: 0:48:38 time: 0.2984 data_time: 0.0034 memory: 1018 loss: 0.1925 loss_sem_seg: 0.1925 2023/03/09 17:49:20 - mmengine - INFO - Epoch(train) [10][ 500/1196] lr: 7.3106e-02 eta: 0:48:22 time: 0.6200 data_time: 0.0037 memory: 1102 loss: 0.2026 loss_sem_seg: 0.2026 2023/03/09 17:49:42 - mmengine - INFO - Epoch(train) [10][ 550/1196] lr: 7.2141e-02 eta: 0:48:01 time: 0.4530 data_time: 0.0037 memory: 990 loss: 0.2090 loss_sem_seg: 0.2090 2023/03/09 17:50:04 - mmengine - INFO - Epoch(train) [10][ 600/1196] lr: 7.1179e-02 eta: 0:47:39 time: 0.4390 data_time: 0.0034 memory: 978 loss: 0.1994 loss_sem_seg: 0.1994 2023/03/09 17:50:26 - mmengine - INFO - Epoch(train) [10][ 650/1196] lr: 7.0222e-02 eta: 0:47:17 time: 0.4408 data_time: 0.0037 memory: 998 loss: 0.1940 loss_sem_seg: 0.1940 2023/03/09 17:50:48 - mmengine - INFO - Epoch(train) [10][ 700/1196] lr: 6.9268e-02 eta: 0:46:56 time: 0.4393 data_time: 0.0036 memory: 988 loss: 0.2074 loss_sem_seg: 0.2074 2023/03/09 17:51:10 - mmengine - INFO - Epoch(train) [10][ 750/1196] lr: 6.8317e-02 eta: 0:46:34 time: 0.4355 data_time: 0.0035 memory: 1034 loss: 0.2022 loss_sem_seg: 0.2022 2023/03/09 17:51:32 - mmengine - INFO - Epoch(train) [10][ 800/1196] lr: 6.7371e-02 eta: 0:46:12 time: 0.4361 data_time: 0.0034 memory: 1007 loss: 0.2023 loss_sem_seg: 0.2023 2023/03/09 17:51:54 - mmengine - INFO - Epoch(train) [10][ 850/1196] lr: 6.6429e-02 eta: 0:45:51 time: 0.4364 data_time: 0.0034 memory: 1045 loss: 0.1909 loss_sem_seg: 0.1909 2023/03/09 17:52:16 - mmengine - INFO - Epoch(train) [10][ 900/1196] lr: 6.5491e-02 eta: 0:45:29 time: 0.4399 data_time: 0.0033 memory: 1015 loss: 0.1962 loss_sem_seg: 0.1962 2023/03/09 17:52:37 - mmengine - INFO - Epoch(train) [10][ 950/1196] lr: 6.4557e-02 eta: 0:45:07 time: 0.4369 data_time: 0.0035 memory: 1025 loss: 0.1877 loss_sem_seg: 0.1877 2023/03/09 17:52:59 - mmengine - INFO - Epoch(train) [10][1000/1196] lr: 6.3627e-02 eta: 0:44:46 time: 0.4346 data_time: 0.0035 memory: 1050 loss: 0.2013 loss_sem_seg: 0.2013 2023/03/09 17:53:21 - mmengine - INFO - Epoch(train) [10][1050/1196] lr: 6.2702e-02 eta: 0:44:24 time: 0.4382 data_time: 0.0034 memory: 1058 loss: 0.2048 loss_sem_seg: 0.2048 2023/03/09 17:53:43 - mmengine - INFO - Epoch(train) [10][1100/1196] lr: 6.1781e-02 eta: 0:44:02 time: 0.4392 data_time: 0.0036 memory: 1022 loss: 0.2070 loss_sem_seg: 0.2070 2023/03/09 17:54:05 - mmengine - INFO - Epoch(train) [10][1150/1196] lr: 6.0865e-02 eta: 0:43:41 time: 0.4359 data_time: 0.0034 memory: 993 loss: 0.2008 loss_sem_seg: 0.2008 2023/03/09 17:54:25 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:54:25 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/03/09 17:54:40 - mmengine - INFO - Epoch(val) [10][ 50/509] eta: 0:01:58 time: 0.2572 data_time: 0.0094 memory: 1012 2023/03/09 17:54:52 - mmengine - INFO - Epoch(val) [10][100/509] eta: 0:01:43 time: 0.2502 data_time: 0.0051 memory: 264 2023/03/09 17:55:04 - mmengine - INFO - Epoch(val) [10][150/509] eta: 0:01:30 time: 0.2464 data_time: 0.0048 memory: 263 2023/03/09 17:55:17 - mmengine - INFO - Epoch(val) [10][200/509] eta: 0:01:17 time: 0.2457 data_time: 0.0048 memory: 257 2023/03/09 17:55:29 - mmengine - INFO - Epoch(val) [10][250/509] eta: 0:01:04 time: 0.2479 data_time: 0.0047 memory: 267 2023/03/09 17:55:41 - mmengine - INFO - Epoch(val) [10][300/509] eta: 0:00:51 time: 0.2430 data_time: 0.0046 memory: 245 2023/03/09 17:55:53 - mmengine - INFO - Epoch(val) [10][350/509] eta: 0:00:39 time: 0.2435 data_time: 0.0046 memory: 254 2023/03/09 17:56:06 - mmengine - INFO - Epoch(val) [10][400/509] eta: 0:00:26 time: 0.2456 data_time: 0.0047 memory: 255 2023/03/09 17:56:18 - mmengine - INFO - Epoch(val) [10][450/509] eta: 0:00:14 time: 0.2462 data_time: 0.0053 memory: 263 2023/03/09 17:56:30 - mmengine - INFO - Epoch(val) [10][500/509] eta: 0:00:02 time: 0.2462 data_time: 0.0052 memory: 255 2023/03/09 17:56:55 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9595 | 0.0179 | 0.5289 | 0.5264 | 0.4973 | 0.5671 | 0.7123 | 0.0008 | 0.9239 | 0.4427 | 0.7910 | 0.0085 | 0.9031 | 0.6100 | 0.8846 | 0.5978 | 0.7636 | 0.6266 | 0.4627 | 0.5697 | 0.9166 | 0.6575 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 17:56:55 - mmengine - INFO - Epoch(val) [10][509/509] car: 0.9595 bicycle: 0.0179 motorcycle: 0.5289 truck: 0.5264 bus: 0.4973 person: 0.5671 bicyclist: 0.7123 motorcyclist: 0.0008 road: 0.9239 parking: 0.4427 sidewalk: 0.7910 other-ground: 0.0085 building: 0.9031 fence: 0.6100 vegetation: 0.8846 trunck: 0.5978 terrian: 0.7636 pole: 0.6266 traffic-sign: 0.4627 miou: 0.5697 acc: 0.9166 acc_cls: 0.6575 2023/03/09 17:57:14 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 17:57:19 - mmengine - INFO - Epoch(train) [11][ 50/1196] lr: 5.9118e-02 eta: 0:43:00 time: 0.4645 data_time: 0.0258 memory: 1038 loss: 0.1812 loss_sem_seg: 0.1812 2023/03/09 17:57:40 - mmengine - INFO - Epoch(train) [11][ 100/1196] lr: 5.8215e-02 eta: 0:42:38 time: 0.4338 data_time: 0.0038 memory: 1018 loss: 0.1998 loss_sem_seg: 0.1998 2023/03/09 17:58:03 - mmengine - INFO - Epoch(train) [11][ 150/1196] lr: 5.7317e-02 eta: 0:42:16 time: 0.4438 data_time: 0.0037 memory: 1021 loss: 0.1844 loss_sem_seg: 0.1844 2023/03/09 17:58:25 - mmengine - INFO - Epoch(train) [11][ 200/1196] lr: 5.6423e-02 eta: 0:41:55 time: 0.4409 data_time: 0.0035 memory: 1036 loss: 0.1880 loss_sem_seg: 0.1880 2023/03/09 17:58:42 - mmengine - INFO - Epoch(train) [11][ 250/1196] lr: 5.5535e-02 eta: 0:41:31 time: 0.3449 data_time: 0.0034 memory: 1053 loss: 0.1745 loss_sem_seg: 0.1745 2023/03/09 17:58:57 - mmengine - INFO - Epoch(train) [11][ 300/1196] lr: 5.4651e-02 eta: 0:41:06 time: 0.2998 data_time: 0.0033 memory: 982 loss: 0.1957 loss_sem_seg: 0.1957 2023/03/09 17:59:12 - mmengine - INFO - Epoch(train) [11][ 350/1196] lr: 5.3772e-02 eta: 0:40:41 time: 0.3047 data_time: 0.0037 memory: 1007 loss: 0.1756 loss_sem_seg: 0.1756 2023/03/09 17:59:27 - mmengine - INFO - Epoch(train) [11][ 400/1196] lr: 5.2899e-02 eta: 0:40:17 time: 0.3041 data_time: 0.0038 memory: 1028 loss: 0.1889 loss_sem_seg: 0.1889 2023/03/09 17:59:42 - mmengine - INFO - Epoch(train) [11][ 450/1196] lr: 5.2030e-02 eta: 0:39:52 time: 0.2967 data_time: 0.0035 memory: 1002 loss: 0.2013 loss_sem_seg: 0.2013 2023/03/09 17:59:57 - mmengine - INFO - Epoch(train) [11][ 500/1196] lr: 5.1167e-02 eta: 0:39:28 time: 0.3030 data_time: 0.0034 memory: 1018 loss: 0.2098 loss_sem_seg: 0.2098 2023/03/09 18:00:17 - mmengine - INFO - Epoch(train) [11][ 550/1196] lr: 5.0309e-02 eta: 0:39:05 time: 0.3980 data_time: 0.0034 memory: 1039 loss: 0.1908 loss_sem_seg: 0.1908 2023/03/09 18:00:48 - mmengine - INFO - Epoch(train) [11][ 600/1196] lr: 4.9457e-02 eta: 0:38:48 time: 0.6202 data_time: 0.0041 memory: 1021 loss: 0.1897 loss_sem_seg: 0.1897 2023/03/09 18:01:10 - mmengine - INFO - Epoch(train) [11][ 650/1196] lr: 4.8610e-02 eta: 0:38:26 time: 0.4419 data_time: 0.0038 memory: 1017 loss: 0.1966 loss_sem_seg: 0.1966 2023/03/09 18:01:32 - mmengine - INFO - Epoch(train) [11][ 700/1196] lr: 4.7768e-02 eta: 0:38:05 time: 0.4402 data_time: 0.0038 memory: 1058 loss: 0.1880 loss_sem_seg: 0.1880 2023/03/09 18:01:54 - mmengine - INFO - Epoch(train) [11][ 750/1196] lr: 4.6932e-02 eta: 0:37:43 time: 0.4371 data_time: 0.0036 memory: 1006 loss: 0.1838 loss_sem_seg: 0.1838 2023/03/09 18:02:16 - mmengine - INFO - Epoch(train) [11][ 800/1196] lr: 4.6101e-02 eta: 0:37:22 time: 0.4395 data_time: 0.0034 memory: 1040 loss: 0.1825 loss_sem_seg: 0.1825 2023/03/09 18:02:38 - mmengine - INFO - Epoch(train) [11][ 850/1196] lr: 4.5276e-02 eta: 0:37:00 time: 0.4431 data_time: 0.0037 memory: 1001 loss: 0.1756 loss_sem_seg: 0.1756 2023/03/09 18:03:00 - mmengine - INFO - Epoch(train) [11][ 900/1196] lr: 4.4457e-02 eta: 0:36:39 time: 0.4342 data_time: 0.0036 memory: 1019 loss: 0.1899 loss_sem_seg: 0.1899 2023/03/09 18:03:22 - mmengine - INFO - Epoch(train) [11][ 950/1196] lr: 4.3644e-02 eta: 0:36:17 time: 0.4375 data_time: 0.0035 memory: 1048 loss: 0.1858 loss_sem_seg: 0.1858 2023/03/09 18:03:44 - mmengine - INFO - Epoch(train) [11][1000/1196] lr: 4.2836e-02 eta: 0:35:55 time: 0.4345 data_time: 0.0033 memory: 1036 loss: 0.1830 loss_sem_seg: 0.1830 2023/03/09 18:04:01 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:04:06 - mmengine - INFO - Epoch(train) [11][1050/1196] lr: 4.2035e-02 eta: 0:35:34 time: 0.4393 data_time: 0.0037 memory: 1091 loss: 0.1927 loss_sem_seg: 0.1927 2023/03/09 18:04:28 - mmengine - INFO - Epoch(train) [11][1100/1196] lr: 4.1239e-02 eta: 0:35:12 time: 0.4383 data_time: 0.0036 memory: 1015 loss: 0.1775 loss_sem_seg: 0.1775 2023/03/09 18:04:49 - mmengine - INFO - Epoch(train) [11][1150/1196] lr: 4.0449e-02 eta: 0:34:51 time: 0.4397 data_time: 0.0035 memory: 994 loss: 0.1835 loss_sem_seg: 0.1835 2023/03/09 18:05:09 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:05:10 - mmengine - INFO - Saving checkpoint at 11 epochs 2023/03/09 18:05:24 - mmengine - INFO - Epoch(val) [11][ 50/509] eta: 0:01:58 time: 0.2581 data_time: 0.0094 memory: 988 2023/03/09 18:05:36 - mmengine - INFO - Epoch(val) [11][100/509] eta: 0:01:43 time: 0.2462 data_time: 0.0048 memory: 264 2023/03/09 18:05:49 - mmengine - INFO - Epoch(val) [11][150/509] eta: 0:01:29 time: 0.2476 data_time: 0.0046 memory: 263 2023/03/09 18:06:01 - mmengine - INFO - Epoch(val) [11][200/509] eta: 0:01:17 time: 0.2461 data_time: 0.0047 memory: 257 2023/03/09 18:06:13 - mmengine - INFO - Epoch(val) [11][250/509] eta: 0:01:04 time: 0.2457 data_time: 0.0048 memory: 267 2023/03/09 18:06:26 - mmengine - INFO - Epoch(val) [11][300/509] eta: 0:00:51 time: 0.2447 data_time: 0.0047 memory: 245 2023/03/09 18:06:38 - mmengine - INFO - Epoch(val) [11][350/509] eta: 0:00:39 time: 0.2455 data_time: 0.0045 memory: 254 2023/03/09 18:06:50 - mmengine - INFO - Epoch(val) [11][400/509] eta: 0:00:26 time: 0.2458 data_time: 0.0047 memory: 255 2023/03/09 18:07:02 - mmengine - INFO - Epoch(val) [11][450/509] eta: 0:00:14 time: 0.2464 data_time: 0.0054 memory: 263 2023/03/09 18:07:15 - mmengine - INFO - Epoch(val) [11][500/509] eta: 0:00:02 time: 0.2476 data_time: 0.0054 memory: 255 2023/03/09 18:07:38 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9556 | 0.0568 | 0.4082 | 0.8012 | 0.4848 | 0.5108 | 0.6245 | 0.0000 | 0.9221 | 0.3799 | 0.7813 | 0.0010 | 0.9052 | 0.6013 | 0.8744 | 0.6592 | 0.7315 | 0.6280 | 0.4510 | 0.5672 | 0.9110 | 0.6340 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 18:07:38 - mmengine - INFO - Epoch(val) [11][509/509] car: 0.9556 bicycle: 0.0568 motorcycle: 0.4082 truck: 0.8012 bus: 0.4848 person: 0.5108 bicyclist: 0.6245 motorcyclist: 0.0000 road: 0.9221 parking: 0.3799 sidewalk: 0.7813 other-ground: 0.0010 building: 0.9052 fence: 0.6013 vegetation: 0.8744 trunck: 0.6592 terrian: 0.7315 pole: 0.6280 traffic-sign: 0.4510 miou: 0.5672 acc: 0.9110 acc_cls: 0.6340 2023/03/09 18:08:02 - mmengine - INFO - Epoch(train) [12][ 50/1196] lr: 3.8950e-02 eta: 0:34:10 time: 0.4652 data_time: 0.0247 memory: 1026 loss: 0.1785 loss_sem_seg: 0.1785 2023/03/09 18:08:24 - mmengine - INFO - Epoch(train) [12][ 100/1196] lr: 3.8179e-02 eta: 0:33:48 time: 0.4377 data_time: 0.0034 memory: 1033 loss: 0.1870 loss_sem_seg: 0.1870 2023/03/09 18:08:45 - mmengine - INFO - Epoch(train) [12][ 150/1196] lr: 3.7414e-02 eta: 0:33:27 time: 0.4360 data_time: 0.0035 memory: 1042 loss: 0.1854 loss_sem_seg: 0.1854 2023/03/09 18:09:07 - mmengine - INFO - Epoch(train) [12][ 200/1196] lr: 3.6655e-02 eta: 0:33:05 time: 0.4384 data_time: 0.0035 memory: 1176 loss: 0.1813 loss_sem_seg: 0.1813 2023/03/09 18:09:29 - mmengine - INFO - Epoch(train) [12][ 250/1196] lr: 3.5902e-02 eta: 0:32:43 time: 0.4320 data_time: 0.0036 memory: 1004 loss: 0.1826 loss_sem_seg: 0.1826 2023/03/09 18:09:49 - mmengine - INFO - Epoch(train) [12][ 300/1196] lr: 3.5156e-02 eta: 0:32:21 time: 0.4105 data_time: 0.0036 memory: 1082 loss: 0.1753 loss_sem_seg: 0.1753 2023/03/09 18:10:05 - mmengine - INFO - Epoch(train) [12][ 350/1196] lr: 3.4416e-02 eta: 0:31:58 time: 0.3111 data_time: 0.0034 memory: 1020 loss: 0.1883 loss_sem_seg: 0.1883 2023/03/09 18:10:20 - mmengine - INFO - Epoch(train) [12][ 400/1196] lr: 3.3683e-02 eta: 0:31:34 time: 0.2999 data_time: 0.0035 memory: 986 loss: 0.1739 loss_sem_seg: 0.1739 2023/03/09 18:10:35 - mmengine - INFO - Epoch(train) [12][ 450/1196] lr: 3.2956e-02 eta: 0:31:10 time: 0.3041 data_time: 0.0036 memory: 1048 loss: 0.1809 loss_sem_seg: 0.1809 2023/03/09 18:10:50 - mmengine - INFO - Epoch(train) [12][ 500/1196] lr: 3.2237e-02 eta: 0:30:47 time: 0.2928 data_time: 0.0036 memory: 1020 loss: 0.1735 loss_sem_seg: 0.1735 2023/03/09 18:11:05 - mmengine - INFO - Epoch(train) [12][ 550/1196] lr: 3.1524e-02 eta: 0:30:23 time: 0.2982 data_time: 0.0036 memory: 1017 loss: 0.1778 loss_sem_seg: 0.1778 2023/03/09 18:11:20 - mmengine - INFO - Epoch(train) [12][ 600/1196] lr: 3.0817e-02 eta: 0:29:59 time: 0.2998 data_time: 0.0035 memory: 1016 loss: 0.1800 loss_sem_seg: 0.1800 2023/03/09 18:11:50 - mmengine - INFO - Epoch(train) [12][ 650/1196] lr: 3.0118e-02 eta: 0:29:40 time: 0.5955 data_time: 0.0034 memory: 1018 loss: 0.1718 loss_sem_seg: 0.1718 2023/03/09 18:12:14 - mmengine - INFO - Epoch(train) [12][ 700/1196] lr: 2.9425e-02 eta: 0:29:20 time: 0.4810 data_time: 0.0035 memory: 1052 loss: 0.1765 loss_sem_seg: 0.1765 2023/03/09 18:12:36 - mmengine - INFO - Epoch(train) [12][ 750/1196] lr: 2.8740e-02 eta: 0:28:58 time: 0.4384 data_time: 0.0035 memory: 1014 loss: 0.1797 loss_sem_seg: 0.1797 2023/03/09 18:12:57 - mmengine - INFO - Epoch(train) [12][ 800/1196] lr: 2.8061e-02 eta: 0:28:37 time: 0.4379 data_time: 0.0036 memory: 1030 loss: 0.1720 loss_sem_seg: 0.1720 2023/03/09 18:13:17 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:13:19 - mmengine - INFO - Epoch(train) [12][ 850/1196] lr: 2.7389e-02 eta: 0:28:15 time: 0.4374 data_time: 0.0034 memory: 1073 loss: 0.1742 loss_sem_seg: 0.1742 2023/03/09 18:13:41 - mmengine - INFO - Epoch(train) [12][ 900/1196] lr: 2.6725e-02 eta: 0:27:54 time: 0.4387 data_time: 0.0033 memory: 1087 loss: 0.1587 loss_sem_seg: 0.1587 2023/03/09 18:14:03 - mmengine - INFO - Epoch(train) [12][ 950/1196] lr: 2.6068e-02 eta: 0:27:32 time: 0.4324 data_time: 0.0036 memory: 1057 loss: 0.1706 loss_sem_seg: 0.1706 2023/03/09 18:14:25 - mmengine - INFO - Epoch(train) [12][1000/1196] lr: 2.5417e-02 eta: 0:27:11 time: 0.4400 data_time: 0.0037 memory: 1011 loss: 0.1739 loss_sem_seg: 0.1739 2023/03/09 18:14:47 - mmengine - INFO - Epoch(train) [12][1050/1196] lr: 2.4775e-02 eta: 0:26:49 time: 0.4418 data_time: 0.0040 memory: 995 loss: 0.1598 loss_sem_seg: 0.1598 2023/03/09 18:15:09 - mmengine - INFO - Epoch(train) [12][1100/1196] lr: 2.4139e-02 eta: 0:26:28 time: 0.4398 data_time: 0.0035 memory: 1004 loss: 0.1572 loss_sem_seg: 0.1572 2023/03/09 18:15:31 - mmengine - INFO - Epoch(train) [12][1150/1196] lr: 2.3511e-02 eta: 0:26:07 time: 0.4407 data_time: 0.0034 memory: 1044 loss: 0.1659 loss_sem_seg: 0.1659 2023/03/09 18:15:51 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:15:52 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/03/09 18:16:06 - mmengine - INFO - Epoch(val) [12][ 50/509] eta: 0:01:57 time: 0.2563 data_time: 0.0096 memory: 1044 2023/03/09 18:16:18 - mmengine - INFO - Epoch(val) [12][100/509] eta: 0:01:44 time: 0.2529 data_time: 0.0055 memory: 264 2023/03/09 18:16:31 - mmengine - INFO - Epoch(val) [12][150/509] eta: 0:01:31 time: 0.2518 data_time: 0.0057 memory: 263 2023/03/09 18:16:43 - mmengine - INFO - Epoch(val) [12][200/509] eta: 0:01:18 time: 0.2501 data_time: 0.0054 memory: 257 2023/03/09 18:16:56 - mmengine - INFO - Epoch(val) [12][250/509] eta: 0:01:05 time: 0.2502 data_time: 0.0053 memory: 267 2023/03/09 18:17:08 - mmengine - INFO - Epoch(val) [12][300/509] eta: 0:00:52 time: 0.2471 data_time: 0.0057 memory: 245 2023/03/09 18:17:21 - mmengine - INFO - Epoch(val) [12][350/509] eta: 0:00:39 time: 0.2489 data_time: 0.0055 memory: 254 2023/03/09 18:17:33 - mmengine - INFO - Epoch(val) [12][400/509] eta: 0:00:27 time: 0.2487 data_time: 0.0052 memory: 255 2023/03/09 18:17:46 - mmengine - INFO - Epoch(val) [12][450/509] eta: 0:00:14 time: 0.2509 data_time: 0.0053 memory: 263 2023/03/09 18:17:58 - mmengine - INFO - Epoch(val) [12][500/509] eta: 0:00:02 time: 0.2522 data_time: 0.0053 memory: 255 2023/03/09 18:18:22 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9654 | 0.0618 | 0.5342 | 0.7262 | 0.5908 | 0.5720 | 0.7310 | 0.0020 | 0.9201 | 0.4016 | 0.7925 | 0.0047 | 0.9050 | 0.6270 | 0.8825 | 0.6497 | 0.7546 | 0.6306 | 0.4519 | 0.5897 | 0.9168 | 0.6602 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 18:18:22 - mmengine - INFO - Epoch(val) [12][509/509] car: 0.9654 bicycle: 0.0618 motorcycle: 0.5342 truck: 0.7262 bus: 0.5908 person: 0.5720 bicyclist: 0.7310 motorcyclist: 0.0020 road: 0.9201 parking: 0.4016 sidewalk: 0.7925 other-ground: 0.0047 building: 0.9050 fence: 0.6270 vegetation: 0.8825 trunck: 0.6497 terrian: 0.7546 pole: 0.6306 traffic-sign: 0.4519 miou: 0.5897 acc: 0.9168 acc_cls: 0.6602 2023/03/09 18:18:45 - mmengine - INFO - Epoch(train) [13][ 50/1196] lr: 2.2325e-02 eta: 0:25:26 time: 0.4641 data_time: 0.0251 memory: 1065 loss: 0.1712 loss_sem_seg: 0.1712 2023/03/09 18:19:07 - mmengine - INFO - Epoch(train) [13][ 100/1196] lr: 2.1719e-02 eta: 0:25:04 time: 0.4393 data_time: 0.0034 memory: 993 loss: 0.1670 loss_sem_seg: 0.1670 2023/03/09 18:19:29 - mmengine - INFO - Epoch(train) [13][ 150/1196] lr: 2.1120e-02 eta: 0:24:43 time: 0.4376 data_time: 0.0034 memory: 1046 loss: 0.1834 loss_sem_seg: 0.1834 2023/03/09 18:19:51 - mmengine - INFO - Epoch(train) [13][ 200/1196] lr: 2.0529e-02 eta: 0:24:21 time: 0.4403 data_time: 0.0034 memory: 1009 loss: 0.1564 loss_sem_seg: 0.1564 2023/03/09 18:20:13 - mmengine - INFO - Epoch(train) [13][ 250/1196] lr: 1.9945e-02 eta: 0:24:00 time: 0.4403 data_time: 0.0037 memory: 1031 loss: 0.1684 loss_sem_seg: 0.1684 2023/03/09 18:20:35 - mmengine - INFO - Epoch(train) [13][ 300/1196] lr: 1.9369e-02 eta: 0:23:38 time: 0.4383 data_time: 0.0035 memory: 1053 loss: 0.1598 loss_sem_seg: 0.1598 2023/03/09 18:20:57 - mmengine - INFO - Epoch(train) [13][ 350/1196] lr: 1.8800e-02 eta: 0:23:17 time: 0.4390 data_time: 0.0034 memory: 1005 loss: 0.1569 loss_sem_seg: 0.1569 2023/03/09 18:21:15 - mmengine - INFO - Epoch(train) [13][ 400/1196] lr: 1.8240e-02 eta: 0:22:54 time: 0.3535 data_time: 0.0040 memory: 1073 loss: 0.1716 loss_sem_seg: 0.1716 2023/03/09 18:21:30 - mmengine - INFO - Epoch(train) [13][ 450/1196] lr: 1.7687e-02 eta: 0:22:31 time: 0.3035 data_time: 0.0038 memory: 1039 loss: 0.1691 loss_sem_seg: 0.1691 2023/03/09 18:21:45 - mmengine - INFO - Epoch(train) [13][ 500/1196] lr: 1.7142e-02 eta: 0:22:09 time: 0.3050 data_time: 0.0036 memory: 1059 loss: 0.1721 loss_sem_seg: 0.1721 2023/03/09 18:22:00 - mmengine - INFO - Epoch(train) [13][ 550/1196] lr: 1.6605e-02 eta: 0:21:46 time: 0.2994 data_time: 0.0036 memory: 1020 loss: 0.1600 loss_sem_seg: 0.1600 2023/03/09 18:22:15 - mmengine - INFO - Epoch(train) [13][ 600/1196] lr: 1.6076e-02 eta: 0:21:23 time: 0.2937 data_time: 0.0033 memory: 1098 loss: 0.1673 loss_sem_seg: 0.1673 2023/03/09 18:22:29 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:22:30 - mmengine - INFO - Epoch(train) [13][ 650/1196] lr: 1.5555e-02 eta: 0:21:00 time: 0.3005 data_time: 0.0034 memory: 1001 loss: 0.1613 loss_sem_seg: 0.1613 2023/03/09 18:22:48 - mmengine - INFO - Epoch(train) [13][ 700/1196] lr: 1.5041e-02 eta: 0:20:38 time: 0.3705 data_time: 0.0034 memory: 1009 loss: 0.1681 loss_sem_seg: 0.1681 2023/03/09 18:23:22 - mmengine - INFO - Epoch(train) [13][ 750/1196] lr: 1.4536e-02 eta: 0:20:19 time: 0.6655 data_time: 0.0035 memory: 1029 loss: 0.1700 loss_sem_seg: 0.1700 2023/03/09 18:23:44 - mmengine - INFO - Epoch(train) [13][ 800/1196] lr: 1.4039e-02 eta: 0:19:57 time: 0.4402 data_time: 0.0036 memory: 1040 loss: 0.1755 loss_sem_seg: 0.1755 2023/03/09 18:24:06 - mmengine - INFO - Epoch(train) [13][ 850/1196] lr: 1.3550e-02 eta: 0:19:36 time: 0.4374 data_time: 0.0034 memory: 1071 loss: 0.1598 loss_sem_seg: 0.1598 2023/03/09 18:24:27 - mmengine - INFO - Epoch(train) [13][ 900/1196] lr: 1.3070e-02 eta: 0:19:15 time: 0.4350 data_time: 0.0034 memory: 1020 loss: 0.1670 loss_sem_seg: 0.1670 2023/03/09 18:24:49 - mmengine - INFO - Epoch(train) [13][ 950/1196] lr: 1.2597e-02 eta: 0:18:53 time: 0.4370 data_time: 0.0038 memory: 1036 loss: 0.1585 loss_sem_seg: 0.1585 2023/03/09 18:25:11 - mmengine - INFO - Epoch(train) [13][1000/1196] lr: 1.2133e-02 eta: 0:18:32 time: 0.4362 data_time: 0.0036 memory: 1061 loss: 0.1612 loss_sem_seg: 0.1612 2023/03/09 18:25:33 - mmengine - INFO - Epoch(train) [13][1050/1196] lr: 1.1677e-02 eta: 0:18:10 time: 0.4340 data_time: 0.0038 memory: 988 loss: 0.1639 loss_sem_seg: 0.1639 2023/03/09 18:25:55 - mmengine - INFO - Epoch(train) [13][1100/1196] lr: 1.1229e-02 eta: 0:17:49 time: 0.4376 data_time: 0.0036 memory: 1036 loss: 0.1602 loss_sem_seg: 0.1602 2023/03/09 18:26:16 - mmengine - INFO - Epoch(train) [13][1150/1196] lr: 1.0790e-02 eta: 0:17:27 time: 0.4325 data_time: 0.0034 memory: 1093 loss: 0.1527 loss_sem_seg: 0.1527 2023/03/09 18:26:36 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:26:37 - mmengine - INFO - Saving checkpoint at 13 epochs 2023/03/09 18:26:51 - mmengine - INFO - Epoch(val) [13][ 50/509] eta: 0:01:57 time: 0.2570 data_time: 0.0098 memory: 1021 2023/03/09 18:27:03 - mmengine - INFO - Epoch(val) [13][100/509] eta: 0:01:43 time: 0.2509 data_time: 0.0050 memory: 264 2023/03/09 18:27:16 - mmengine - INFO - Epoch(val) [13][150/509] eta: 0:01:30 time: 0.2473 data_time: 0.0047 memory: 263 2023/03/09 18:27:28 - mmengine - INFO - Epoch(val) [13][200/509] eta: 0:01:17 time: 0.2525 data_time: 0.0051 memory: 257 2023/03/09 18:27:41 - mmengine - INFO - Epoch(val) [13][250/509] eta: 0:01:05 time: 0.2491 data_time: 0.0053 memory: 267 2023/03/09 18:27:53 - mmengine - INFO - Epoch(val) [13][300/509] eta: 0:00:52 time: 0.2471 data_time: 0.0053 memory: 245 2023/03/09 18:28:06 - mmengine - INFO - Epoch(val) [13][350/509] eta: 0:00:39 time: 0.2504 data_time: 0.0051 memory: 254 2023/03/09 18:28:18 - mmengine - INFO - Epoch(val) [13][400/509] eta: 0:00:27 time: 0.2506 data_time: 0.0053 memory: 255 2023/03/09 18:28:31 - mmengine - INFO - Epoch(val) [13][450/509] eta: 0:00:14 time: 0.2503 data_time: 0.0053 memory: 263 2023/03/09 18:28:44 - mmengine - INFO - Epoch(val) [13][500/509] eta: 0:00:02 time: 0.2539 data_time: 0.0053 memory: 255 2023/03/09 18:29:07 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9660 | 0.0747 | 0.5064 | 0.7617 | 0.6205 | 0.6108 | 0.7793 | 0.0033 | 0.9266 | 0.4262 | 0.7990 | 0.0021 | 0.9057 | 0.6196 | 0.8788 | 0.6650 | 0.7413 | 0.6308 | 0.4701 | 0.5994 | 0.9166 | 0.6721 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 18:29:07 - mmengine - INFO - Epoch(val) [13][509/509] car: 0.9660 bicycle: 0.0747 motorcycle: 0.5064 truck: 0.7617 bus: 0.6205 person: 0.6108 bicyclist: 0.7793 motorcyclist: 0.0033 road: 0.9266 parking: 0.4262 sidewalk: 0.7990 other-ground: 0.0021 building: 0.9057 fence: 0.6196 vegetation: 0.8788 trunck: 0.6650 terrian: 0.7413 pole: 0.6308 traffic-sign: 0.4701 miou: 0.5994 acc: 0.9166 acc_cls: 0.6721 2023/03/09 18:29:30 - mmengine - INFO - Epoch(train) [14][ 50/1196] lr: 9.9694e-03 eta: 0:16:46 time: 0.4599 data_time: 0.0234 memory: 1034 loss: 0.1582 loss_sem_seg: 0.1582 2023/03/09 18:29:52 - mmengine - INFO - Epoch(train) [14][ 100/1196] lr: 9.5545e-03 eta: 0:16:25 time: 0.4362 data_time: 0.0035 memory: 991 loss: 0.1563 loss_sem_seg: 0.1563 2023/03/09 18:30:14 - mmengine - INFO - Epoch(train) [14][ 150/1196] lr: 9.1481e-03 eta: 0:16:04 time: 0.4362 data_time: 0.0035 memory: 1006 loss: 0.1632 loss_sem_seg: 0.1632 2023/03/09 18:30:35 - mmengine - INFO - Epoch(train) [14][ 200/1196] lr: 8.7502e-03 eta: 0:15:42 time: 0.4370 data_time: 0.0035 memory: 1049 loss: 0.1679 loss_sem_seg: 0.1679 2023/03/09 18:30:57 - mmengine - INFO - Epoch(train) [14][ 250/1196] lr: 8.3608e-03 eta: 0:15:21 time: 0.4402 data_time: 0.0034 memory: 1043 loss: 0.1581 loss_sem_seg: 0.1581 2023/03/09 18:31:19 - mmengine - INFO - Epoch(train) [14][ 300/1196] lr: 7.9800e-03 eta: 0:14:59 time: 0.4376 data_time: 0.0038 memory: 994 loss: 0.1486 loss_sem_seg: 0.1486 2023/03/09 18:31:41 - mmengine - INFO - Epoch(train) [14][ 350/1196] lr: 7.6078e-03 eta: 0:14:38 time: 0.4365 data_time: 0.0037 memory: 1028 loss: 0.1621 loss_sem_seg: 0.1621 2023/03/09 18:32:03 - mmengine - INFO - Epoch(train) [14][ 400/1196] lr: 7.2442e-03 eta: 0:14:16 time: 0.4411 data_time: 0.0040 memory: 1042 loss: 0.1641 loss_sem_seg: 0.1641 2023/03/09 18:32:24 - mmengine - INFO - Epoch(train) [14][ 450/1196] lr: 6.8892e-03 eta: 0:13:55 time: 0.4125 data_time: 0.0035 memory: 1030 loss: 0.1535 loss_sem_seg: 0.1535 2023/03/09 18:32:24 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:32:39 - mmengine - INFO - Epoch(train) [14][ 500/1196] lr: 6.5429e-03 eta: 0:13:32 time: 0.3029 data_time: 0.0034 memory: 1030 loss: 0.1625 loss_sem_seg: 0.1625 2023/03/09 18:32:54 - mmengine - INFO - Epoch(train) [14][ 550/1196] lr: 6.2053e-03 eta: 0:13:10 time: 0.2985 data_time: 0.0036 memory: 1010 loss: 0.1545 loss_sem_seg: 0.1545 2023/03/09 18:33:09 - mmengine - INFO - Epoch(train) [14][ 600/1196] lr: 5.8765e-03 eta: 0:12:48 time: 0.3064 data_time: 0.0035 memory: 1013 loss: 0.1553 loss_sem_seg: 0.1553 2023/03/09 18:33:24 - mmengine - INFO - Epoch(train) [14][ 650/1196] lr: 5.5564e-03 eta: 0:12:26 time: 0.2993 data_time: 0.0035 memory: 1036 loss: 0.1560 loss_sem_seg: 0.1560 2023/03/09 18:33:39 - mmengine - INFO - Epoch(train) [14][ 700/1196] lr: 5.2450e-03 eta: 0:12:04 time: 0.2997 data_time: 0.0035 memory: 1022 loss: 0.1632 loss_sem_seg: 0.1632 2023/03/09 18:33:54 - mmengine - INFO - Epoch(train) [14][ 750/1196] lr: 4.9425e-03 eta: 0:11:42 time: 0.3016 data_time: 0.0033 memory: 1027 loss: 0.1565 loss_sem_seg: 0.1565 2023/03/09 18:34:24 - mmengine - INFO - Epoch(train) [14][ 800/1196] lr: 4.6488e-03 eta: 0:11:21 time: 0.5901 data_time: 0.0035 memory: 1141 loss: 0.1574 loss_sem_seg: 0.1574 2023/03/09 18:34:48 - mmengine - INFO - Epoch(train) [14][ 850/1196] lr: 4.3639e-03 eta: 0:11:00 time: 0.4937 data_time: 0.0036 memory: 1025 loss: 0.1570 loss_sem_seg: 0.1570 2023/03/09 18:35:10 - mmengine - INFO - Epoch(train) [14][ 900/1196] lr: 4.0879e-03 eta: 0:10:39 time: 0.4349 data_time: 0.0035 memory: 1080 loss: 0.1551 loss_sem_seg: 0.1551 2023/03/09 18:35:32 - mmengine - INFO - Epoch(train) [14][ 950/1196] lr: 3.8207e-03 eta: 0:10:17 time: 0.4328 data_time: 0.0035 memory: 980 loss: 0.1608 loss_sem_seg: 0.1608 2023/03/09 18:35:54 - mmengine - INFO - Epoch(train) [14][1000/1196] lr: 3.5625e-03 eta: 0:09:56 time: 0.4382 data_time: 0.0036 memory: 1098 loss: 0.1519 loss_sem_seg: 0.1519 2023/03/09 18:36:16 - mmengine - INFO - Epoch(train) [14][1050/1196] lr: 3.3132e-03 eta: 0:09:35 time: 0.4364 data_time: 0.0037 memory: 1009 loss: 0.1613 loss_sem_seg: 0.1613 2023/03/09 18:36:37 - mmengine - INFO - Epoch(train) [14][1100/1196] lr: 3.0729e-03 eta: 0:09:13 time: 0.4382 data_time: 0.0037 memory: 1016 loss: 0.1542 loss_sem_seg: 0.1542 2023/03/09 18:36:59 - mmengine - INFO - Epoch(train) [14][1150/1196] lr: 2.8415e-03 eta: 0:08:52 time: 0.4370 data_time: 0.0035 memory: 1029 loss: 0.1535 loss_sem_seg: 0.1535 2023/03/09 18:37:20 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:37:20 - mmengine - INFO - Saving checkpoint at 14 epochs 2023/03/09 18:37:34 - mmengine - INFO - Epoch(val) [14][ 50/509] eta: 0:01:56 time: 0.2547 data_time: 0.0094 memory: 994 2023/03/09 18:37:47 - mmengine - INFO - Epoch(val) [14][100/509] eta: 0:01:43 time: 0.2515 data_time: 0.0053 memory: 264 2023/03/09 18:37:59 - mmengine - INFO - Epoch(val) [14][150/509] eta: 0:01:30 time: 0.2476 data_time: 0.0051 memory: 263 2023/03/09 18:38:11 - mmengine - INFO - Epoch(val) [14][200/509] eta: 0:01:17 time: 0.2488 data_time: 0.0053 memory: 257 2023/03/09 18:38:24 - mmengine - INFO - Epoch(val) [14][250/509] eta: 0:01:04 time: 0.2494 data_time: 0.0053 memory: 267 2023/03/09 18:38:36 - mmengine - INFO - Epoch(val) [14][300/509] eta: 0:00:52 time: 0.2432 data_time: 0.0051 memory: 245 2023/03/09 18:38:48 - mmengine - INFO - Epoch(val) [14][350/509] eta: 0:00:39 time: 0.2472 data_time: 0.0050 memory: 254 2023/03/09 18:39:01 - mmengine - INFO - Epoch(val) [14][400/509] eta: 0:00:27 time: 0.2477 data_time: 0.0050 memory: 255 2023/03/09 18:39:13 - mmengine - INFO - Epoch(val) [14][450/509] eta: 0:00:14 time: 0.2479 data_time: 0.0048 memory: 263 2023/03/09 18:39:25 - mmengine - INFO - Epoch(val) [14][500/509] eta: 0:00:02 time: 0.2467 data_time: 0.0051 memory: 255 2023/03/09 18:39:49 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9658 | 0.0659 | 0.5071 | 0.8070 | 0.6147 | 0.6126 | 0.7880 | 0.0031 | 0.9285 | 0.4462 | 0.8000 | 0.0008 | 0.9070 | 0.6177 | 0.8793 | 0.6591 | 0.7431 | 0.6315 | 0.4661 | 0.6023 | 0.9171 | 0.6688 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 18:39:49 - mmengine - INFO - Epoch(val) [14][509/509] car: 0.9658 bicycle: 0.0659 motorcycle: 0.5071 truck: 0.8070 bus: 0.6147 person: 0.6126 bicyclist: 0.7880 motorcyclist: 0.0031 road: 0.9285 parking: 0.4462 sidewalk: 0.8000 other-ground: 0.0008 building: 0.9070 fence: 0.6177 vegetation: 0.8793 trunck: 0.6591 terrian: 0.7431 pole: 0.6315 traffic-sign: 0.4661 miou: 0.6023 acc: 0.9171 acc_cls: 0.6688 2023/03/09 18:40:12 - mmengine - INFO - Epoch(train) [15][ 50/1196] lr: 2.4224e-03 eta: 0:08:11 time: 0.4649 data_time: 0.0240 memory: 1064 loss: 0.1584 loss_sem_seg: 0.1584 2023/03/09 18:40:34 - mmengine - INFO - Epoch(train) [15][ 100/1196] lr: 2.2173e-03 eta: 0:07:49 time: 0.4414 data_time: 0.0038 memory: 1055 loss: 0.1633 loss_sem_seg: 0.1633 2023/03/09 18:40:56 - mmengine - INFO - Epoch(train) [15][ 150/1196] lr: 2.0212e-03 eta: 0:07:28 time: 0.4446 data_time: 0.0036 memory: 1001 loss: 0.1552 loss_sem_seg: 0.1552 2023/03/09 18:41:18 - mmengine - INFO - Epoch(train) [15][ 200/1196] lr: 1.8342e-03 eta: 0:07:07 time: 0.4403 data_time: 0.0035 memory: 1049 loss: 0.1537 loss_sem_seg: 0.1537 2023/03/09 18:41:40 - mmengine - INFO - Epoch(train) [15][ 250/1196] lr: 1.6562e-03 eta: 0:06:45 time: 0.4382 data_time: 0.0036 memory: 1018 loss: 0.1536 loss_sem_seg: 0.1536 2023/03/09 18:41:43 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:42:02 - mmengine - INFO - Epoch(train) [15][ 300/1196] lr: 1.4873e-03 eta: 0:06:24 time: 0.4404 data_time: 0.0035 memory: 1034 loss: 0.1670 loss_sem_seg: 0.1670 2023/03/09 18:42:24 - mmengine - INFO - Epoch(train) [15][ 350/1196] lr: 1.3275e-03 eta: 0:06:02 time: 0.4360 data_time: 0.0033 memory: 993 loss: 0.1672 loss_sem_seg: 0.1672 2023/03/09 18:42:46 - mmengine - INFO - Epoch(train) [15][ 400/1196] lr: 1.1768e-03 eta: 0:05:41 time: 0.4408 data_time: 0.0034 memory: 1035 loss: 0.1526 loss_sem_seg: 0.1526 2023/03/09 18:43:08 - mmengine - INFO - Epoch(train) [15][ 450/1196] lr: 1.0352e-03 eta: 0:05:19 time: 0.4372 data_time: 0.0037 memory: 1025 loss: 0.1615 loss_sem_seg: 0.1615 2023/03/09 18:43:30 - mmengine - INFO - Epoch(train) [15][ 500/1196] lr: 9.0272e-04 eta: 0:04:58 time: 0.4386 data_time: 0.0037 memory: 1063 loss: 0.1473 loss_sem_seg: 0.1473 2023/03/09 18:43:48 - mmengine - INFO - Epoch(train) [15][ 550/1196] lr: 7.7936e-04 eta: 0:04:37 time: 0.3731 data_time: 0.0036 memory: 1029 loss: 0.1655 loss_sem_seg: 0.1655 2023/03/09 18:44:04 - mmengine - INFO - Epoch(train) [15][ 600/1196] lr: 6.6515e-04 eta: 0:04:15 time: 0.3052 data_time: 0.0034 memory: 994 loss: 0.1515 loss_sem_seg: 0.1515 2023/03/09 18:44:19 - mmengine - INFO - Epoch(train) [15][ 650/1196] lr: 5.6009e-04 eta: 0:03:53 time: 0.3018 data_time: 0.0035 memory: 1036 loss: 0.1525 loss_sem_seg: 0.1525 2023/03/09 18:44:34 - mmengine - INFO - Epoch(train) [15][ 700/1196] lr: 4.6418e-04 eta: 0:03:32 time: 0.3050 data_time: 0.0035 memory: 1029 loss: 0.1626 loss_sem_seg: 0.1626 2023/03/09 18:44:49 - mmengine - INFO - Epoch(train) [15][ 750/1196] lr: 3.7744e-04 eta: 0:03:10 time: 0.2949 data_time: 0.0035 memory: 1020 loss: 0.1559 loss_sem_seg: 0.1559 2023/03/09 18:45:04 - mmengine - INFO - Epoch(train) [15][ 800/1196] lr: 2.9986e-04 eta: 0:02:49 time: 0.3026 data_time: 0.0033 memory: 991 loss: 0.1504 loss_sem_seg: 0.1504 2023/03/09 18:45:20 - mmengine - INFO - Epoch(train) [15][ 850/1196] lr: 2.3147e-04 eta: 0:02:27 time: 0.3199 data_time: 0.0033 memory: 989 loss: 0.1596 loss_sem_seg: 0.1596 2023/03/09 18:45:54 - mmengine - INFO - Epoch(train) [15][ 900/1196] lr: 1.7226e-04 eta: 0:02:06 time: 0.6788 data_time: 0.0035 memory: 1014 loss: 0.1473 loss_sem_seg: 0.1473 2023/03/09 18:46:16 - mmengine - INFO - Epoch(train) [15][ 950/1196] lr: 1.2223e-04 eta: 0:01:45 time: 0.4384 data_time: 0.0037 memory: 1010 loss: 0.1666 loss_sem_seg: 0.1666 2023/03/09 18:46:37 - mmengine - INFO - Epoch(train) [15][1000/1196] lr: 8.1397e-05 eta: 0:01:23 time: 0.4312 data_time: 0.0034 memory: 1059 loss: 0.1526 loss_sem_seg: 0.1526 2023/03/09 18:46:59 - mmengine - INFO - Epoch(train) [15][1050/1196] lr: 4.9756e-05 eta: 0:01:02 time: 0.4367 data_time: 0.0036 memory: 1034 loss: 0.1541 loss_sem_seg: 0.1541 2023/03/09 18:47:21 - mmengine - INFO - Epoch(train) [15][1100/1196] lr: 2.7311e-05 eta: 0:00:41 time: 0.4358 data_time: 0.0035 memory: 1031 loss: 0.1603 loss_sem_seg: 0.1603 2023/03/09 18:47:43 - mmengine - INFO - Epoch(train) [15][1150/1196] lr: 1.4064e-05 eta: 0:00:19 time: 0.4382 data_time: 0.0036 memory: 996 loss: 0.1477 loss_sem_seg: 0.1477 2023/03/09 18:48:03 - mmengine - INFO - Exp name: minkunet_w16_8xb2-15e_semantickitti_20230309_160737 2023/03/09 18:48:04 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/03/09 18:48:17 - mmengine - INFO - Epoch(val) [15][ 50/509] eta: 0:01:55 time: 0.2523 data_time: 0.0091 memory: 1012 2023/03/09 18:48:30 - mmengine - INFO - Epoch(val) [15][100/509] eta: 0:01:42 time: 0.2471 data_time: 0.0054 memory: 264 2023/03/09 18:48:42 - mmengine - INFO - Epoch(val) [15][150/509] eta: 0:01:29 time: 0.2490 data_time: 0.0057 memory: 263 2023/03/09 18:48:55 - mmengine - INFO - Epoch(val) [15][200/509] eta: 0:01:17 time: 0.2493 data_time: 0.0055 memory: 257 2023/03/09 18:49:07 - mmengine - INFO - Epoch(val) [15][250/509] eta: 0:01:04 time: 0.2488 data_time: 0.0054 memory: 267 2023/03/09 18:49:19 - mmengine - INFO - Epoch(val) [15][300/509] eta: 0:00:51 time: 0.2458 data_time: 0.0054 memory: 245 2023/03/09 18:49:32 - mmengine - INFO - Epoch(val) [15][350/509] eta: 0:00:39 time: 0.2451 data_time: 0.0053 memory: 254 2023/03/09 18:49:44 - mmengine - INFO - Epoch(val) [15][400/509] eta: 0:00:27 time: 0.2498 data_time: 0.0059 memory: 255 2023/03/09 18:49:57 - mmengine - INFO - Epoch(val) [15][450/509] eta: 0:00:14 time: 0.2507 data_time: 0.0054 memory: 263 2023/03/09 18:50:09 - mmengine - INFO - Epoch(val) [15][500/509] eta: 0:00:02 time: 0.2495 data_time: 0.0052 memory: 255 2023/03/09 18:50:33 - mmengine - INFO - +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | classes | car | bicycle | motorcycle | truck | bus | person | bicyclist | motorcyclist | road | parking | sidewalk | other-ground | building | fence | vegetation | trunck | terrian | pole | traffic-sign | miou | acc | acc_cls | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ | results | 0.9664 | 0.0701 | 0.5260 | 0.8080 | 0.6163 | 0.6115 | 0.7780 | 0.0030 | 0.9288 | 0.4383 | 0.8000 | 0.0016 | 0.9069 | 0.6174 | 0.8786 | 0.6606 | 0.7416 | 0.6327 | 0.4684 | 0.6029 | 0.9169 | 0.6712 | +---------+--------+---------+------------+--------+--------+--------+-----------+--------------+--------+---------+----------+--------------+----------+--------+------------+--------+---------+--------+--------------+--------+--------+---------+ 2023/03/09 18:50:33 - mmengine - INFO - Epoch(val) [15][509/509] car: 0.9664 bicycle: 0.0701 motorcycle: 0.5260 truck: 0.8080 bus: 0.6163 person: 0.6115 bicyclist: 0.7780 motorcyclist: 0.0030 road: 0.9288 parking: 0.4383 sidewalk: 0.8000 other-ground: 0.0016 building: 0.9069 fence: 0.6174 vegetation: 0.8786 trunck: 0.6606 terrian: 0.7416 pole: 0.6327 traffic-sign: 0.4684 miou: 0.6029 acc: 0.9169 acc_cls: 0.6712