(py310) cjet@cjet-B560M-HDV-A-R2-0:~/桌面/ti/edgeai-tensorlab/edgeai-modelmaker$ ./run_modelmaker.sh AM62A config_detection.yaml Number of AVX cores detected in PC: 12 AVX compilation speedup in PC : 1 Target device : AM62A PYTHONPATH : .: TIDL_TOOLS_PATH : ../edgeai-benchmark/tools/AM62A/tidl_tools LD_LIBRARY_PATH : ../edgeai-benchmark/tools/AM62A/tidl_tools argv: ['./scripts/run_modelmaker.py', 'config_detection.yaml', '--target_device', 'AM62A'] {'common': {'verbose_mode': True, 'download_path': './data/downloads', 'projects_path': './data/projects', 'project_path': None, 'project_run_path': None, 'task_type': 'detection', 'target_machine': 'evm', 'target_device': 'AM62A', 'run_name': '{date-time}/{model_name}', 'target_module': 'vision'}, 'download': [{'download_url': 'https://software-dl.ti.com/jacinto7/esd/modelzoo/08_06_00_01/models/vision/detection/coco/edgeai-mmdet/yolox_nano_lite_416x416_20220214_checkpoint.pth', 'download_path': '{download_path}/pretrained/yolox_nano_lite'}], 'dataset': {'enable': True, 'dataset_name': 'tiscapes2017_driving', 'dataset_path': None, 'extract_path': None, 'split_factor': 0.8, 'split_names': ('train', 'val'), 'max_num_files': 10000, 'input_data_path': 'http://software-dl.ti.com/jacinto7/esd/modelzoo/08_06_00_01/datasets/tiscapes2017_driving.zip', 'input_annotation_path': None, 'data_path_splits': None, 'data_dir': 'images', 'annotation_path_splits': None, 'annotation_dir': 'annotations', 'annotation_prefix': 'instances', 'annotation_format': 'coco_json', 'dataset_download': True, 'dataset_reload': False}, 'training': {'enable': True, 'model_name': 'yolox_nano_lite', 'model_training_id': 'yolox_nano_lite', 'training_backend': 'edgeai_mmdetection', 'pretrained_checkpoint_path': {'download_url': 'https://software-dl.ti.com/jacinto7/esd/modelzoo/08_06_00_01/models/vision/detection/coco/edgeai-mmdet/yolox_nano_lite_416x416_20220214_checkpoint.pth', 'download_path': '{download_path}/pretrained/yolox_nano_lite'}, 'pretrained_weight_state_dict_name': None, 'target_devices': {'TDA4VM': {'performance_fps': None, 'performance_infer_time_ms': 3.74, 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}, 'AM62A': {'performance_fps': None, 'performance_infer_time_ms': 8.87, 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}, 'AM67A': {'performance_fps': None, 'performance_infer_time_ms': '8.87 (with 1/2 device capability)', 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}, 'AM68A': {'performance_fps': None, 'performance_infer_time_ms': 3.73, 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}, 'AM69A': {'performance_fps': None, 'performance_infer_time_ms': '3.64 (with 1/4th device capability)', 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}, 'AM62': {'performance_fps': None, 'performance_infer_time_ms': 516.15, 'accuracy_factor': 40.1, 'accuracy_unit': 'AP50%', 'accuracy_factor2': 24.8, 'accuracy_unit2': 'AP[.5:.95]%'}}, 'project_path': None, 'dataset_path': None, 'training_path': None, 'log_file_path': None, 'log_summary_regex': None, 'summary_file_path': None, 'model_checkpoint_path': None, 'model_export_path': None, 'model_proto_path': None, 'model_packaged_path': None, 'training_epochs': 15, 'warmup_epochs': 1, 'num_last_epochs': 5, 'batch_size': 8, 'learning_rate': 0.002, 'num_classes': None, 'weight_decay': 0.0001, 'input_resize': 416, 'input_cropsize': 416, 'training_device': None, 'num_gpus': 1, 'distributed': True, 'training_master_port': 29500, 'with_background_class': None, 'model_architecture': 'yolox', 'training_devices': {'cpu': True, 'cuda': True}}, 'compilation': {'enable': True, 'preset_name': None, 'model_compilation_id': 'od-8200', 'compilation_path': None, 'model_compiled_path': None, 'log_file_path': None, 'log_summary_regex': None, 'summary_file_path': None, 'output_tensors_path': None, 'model_packaged_path': None, 'model_visualization_path': None, 'tensor_bits': 8, 'calibration_frames': 10, 'calibration_iterations': 10, 'num_frames': None, 'num_output_frames': 50, 'detection_threshold': 0.6, 'detection_top_k': 200, 'save_output': True, 'tidl_offload': True, 'input_optimization': False, 'capture_log': True, 'runtime_options': {'advanced_options:output_feature_16bit_names_list': '/multi_level_conv_obj.2/Conv_output_0, /multi_level_conv_reg.2/Conv_output_0, /multi_level_conv_cls.2/Conv_output_0, /multi_level_conv_obj.1/Conv_output_0, /multi_level_conv_reg.1/Conv_output_0, /multi_level_conv_cls.1/Conv_output_0, /multi_level_conv_obj.0/Conv_output_0, /multi_level_conv_reg.0/Conv_output_0, /multi_level_conv_cls.0/Conv_output_0'}, 'metric': {'label_offset_pred': 0}}} --------------------------------------------------------------------- Run Name: 20241217-165534/yolox_nano_lite - Model: yolox_nano_lite - TargetDevices & Estimated Inference Times (ms): {'TDA4VM': 3.74, 'AM62A': 8.87, 'AM67A': '8.87 (with 1/2 device capability)', 'AM68A': 3.73, 'AM69A': '3.64 (with 1/4th device capability)', 'AM62': 516.15} - This model can be compiled for the above device(s). --------------------------------------------------------------------- dataset split sizes {'train': 393, 'val': 107} max_num_files is set to: 10000 dataset split sizes are limited to: {'train': 393, 'val': 107} dataset loading OK loading annotations into memory... Done (t=0.05s) creating index... index created! loading annotations into memory... Done (t=0.01s) creating index... index created! Selecting model configs from Python module: ./configs Run params is at: /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241217-165534/yolox_nano_lite/run.yaml /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/training/edgeai_mmdetection/detection.py:446: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use-env is set by default in torchrun. If your script expects `--local-rank` argument to be set, please change it to read from `os.environ['LOCAL_RANK']` instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructions distributed_launch.main() /home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: `TorchScript` support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the `torch.compile` optimizer instead. from torch.distributed.optim import \ /home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/mmengine/utils/dl_utils/setup_env.py:46: UserWarning: Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. warnings.warn( /home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/mmengine/utils/dl_utils/setup_env.py:56: UserWarning: Setting MKL_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. warnings.warn( 12/17 16:55:39 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.16 (main, Dec 17 2024, 10:43:53) [GCC 11.4.0] CUDA available: True MUSA available: False numpy_random_seed: 215094685 GPU 0: NVIDIA GeForce RTX 3060 CUDA_HOME: None GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 PyTorch: 2.4.0+cu118 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201703 - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v3.4.2 (Git Hash 1137e04ec0b5251ca2b4400a4fd3c667ce843d67) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX512 - CUDA Runtime 11.8 - NVCC architecture flags: -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;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_90,code=sm_90 - CuDNN 90.1 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.4.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, TorchVision: 0.19.0+cu118 OpenCV: 4.10.0 MMEngine: 0.10.5 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 215094685 Distributed launcher: pytorch Distributed training: True GPU number: 1 ------------------------------------------------------------ 12/17 16:55:40 - mmengine - INFO - Config: auto_scale_lr = dict(base_batch_size=64, enable=False) backend_args = None base_lr = 0.01 classes = ( 'human', 'trafficsign', 'vehicle', ) convert_to_lite_model = dict(model_surgery=1) custom_hooks = [ dict(num_last_epochs=15, priority=48, type='YOLOXModeSwitchHook'), dict(priority=48, type='SyncNormHook'), dict( ema_type='ExpMomentumEMA', momentum=0.0001, priority=49, type='EMAHook', update_buffers=True), ] data_root = '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset' dataset_type = 'CocoDataset' default_hooks = dict( checkpoint=dict(interval=1, max_keep_ckpts=3, type='CheckpointHook'), logger=dict(interval=50, type='LoggerHook'), param_scheduler=dict(type='ParamSchedulerHook'), sampler_seed=dict(type='DistSamplerSeedHook'), timer=dict(type='IterTimerHook'), visualization=dict(type='DetVisualizationHook')) default_scope = 'mmdet' env_cfg = dict( cudnn_benchmark=False, dist_cfg=dict(backend='nccl'), mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) export_onnx_model = True find_unused_parameters = True img_scale = ( 640, 640, ) img_scales = [ ( 640, 640, ), ( 320, 320, ), ( 960, 960, ), ] interval = 1 launcher = 'pytorch' load_from = './data/downloads/pretrained/yolox_nano_lite/yolox_nano_lite_416x416_20220214_checkpoint.pth' log_level = 'INFO' log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50) max_epochs = 15 model = dict( backbone=dict( act_cfg=dict(type='ReLU'), deepen_factor=0.33, norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), out_indices=( 2, 3, 4, ), spp_kernal_sizes=( 5, 9, 13, ), type='CSPDarknet', use_depthwise=False, widen_factor=0.25), bbox_head=dict( act_cfg=dict(type='ReLU'), feat_channels=64, in_channels=64, loss_bbox=dict( eps=1e-16, loss_weight=5.0, mode='square', reduction='sum', type='IoULoss'), loss_cls=dict( loss_weight=1.0, reduction='sum', type='CrossEntropyLoss', use_sigmoid=True), loss_l1=dict(loss_weight=1.0, reduction='sum', type='L1Loss'), loss_obj=dict( loss_weight=1.0, reduction='sum', type='CrossEntropyLoss', use_sigmoid=True), norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), num_classes=3, stacked_convs=2, strides=( 8, 16, 32, ), type='YOLOXHead', use_depthwise=False), data_preprocessor=dict( batch_augments=[ dict( interval=10, random_size_range=( 320, 640, ), size_divisor=32, type='BatchSyncRandomResize'), ], pad_size_divisor=32, type='DetDataPreprocessor'), neck=dict( act_cfg=dict(type='ReLU'), in_channels=[ 64, 128, 256, ], norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), num_csp_blocks=1, out_channels=64, type='YOLOXPAFPN', upsample_cfg=dict(mode='nearest', scale_factor=2), use_depthwise=False), test_cfg=dict(nms=dict(iou_threshold=0.65, type='nms'), score_thr=0.01), train_cfg=dict(assigner=dict(center_radius=2.5, type='SimOTAAssigner')), type='YOLOX') num_last_epochs = 15 optim_wrapper = dict( optimizer=dict( lr=0.002, momentum=0.9, nesterov=True, type='SGD', weight_decay=0.0005), paramwise_cfg=dict(bias_decay_mult=0.0, norm_decay_mult=0.0), type='OptimWrapper') param_scheduler = [ dict( begin=0, by_epoch=True, convert_to_iter_based=True, end=5, type='mmdet.QuadraticWarmupLR'), dict( T_max=15, begin=5, by_epoch=True, convert_to_iter_based=True, end=15, eta_min=0.0005, type='CosineAnnealingLR'), dict(begin=15, by_epoch=True, end=30, factor=1, type='ConstantLR'), ] quantization = 0 resume = False test_cfg = dict(type='TestLoop') test_dataloader = dict( batch_size=8, dataset=dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_val.json', backend_args=None, data_prefix=dict(img='val/'), data_root= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset', metainfo=dict(classes=( 'human', 'trafficsign', 'vehicle', )), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 416, 416, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict(type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', ), type='PackDetInputs'), ], test_mode=True, type='CocoDataset'), drop_last=False, num_workers=4, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) test_evaluator = dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_val.json', backend_args=None, metric='bbox', type='CocoMetric') test_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 416, 416, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict(type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', ), type='PackDetInputs'), ] train_cfg = dict(max_epochs=15, type='EpochBasedTrainLoop', val_interval=1) train_dataloader = dict( batch_size=8, dataset=dict( dataset=dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_train.json', backend_args=None, data_prefix=dict(img='train/'), data_root= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset', filter_cfg=dict(filter_empty_gt=False, min_size=32), metainfo=dict(classes=( 'human', 'trafficsign', 'vehicle', )), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='CocoDataset'), pipeline=[ dict(img_scale=( 640, 640, ), pad_val=114.0, type='Mosaic'), dict( border=( -320, -320, ), scaling_ratio_range=( 0.5, 1.5, ), type='RandomAffine'), dict(type='YOLOXHSVRandomAug'), dict(prob=0.5, type='RandomFlip'), dict(keep_ratio=True, scale=( 640, 640, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict( keep_empty=False, min_gt_bbox_wh=( 1, 1, ), type='FilterAnnotations'), dict(type='PackDetInputs'), ], type='MultiImageMixDataset'), num_workers=4, persistent_workers=True, sampler=dict(shuffle=True, type='DefaultSampler')) train_dataset = dict( dataset=dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_train.json', backend_args=None, data_prefix=dict(img='train/'), data_root= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset', filter_cfg=dict(filter_empty_gt=False, min_size=32), metainfo=dict(classes=( 'human', 'trafficsign', 'vehicle', )), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='CocoDataset'), pipeline=[ dict(img_scale=( 640, 640, ), pad_val=114.0, type='Mosaic'), dict( border=( -320, -320, ), scaling_ratio_range=( 0.1, 2, ), type='RandomAffine'), dict( img_scale=( 640, 640, ), pad_val=114.0, ratio_range=( 0.8, 1.6, ), type='MixUp'), dict(type='YOLOXHSVRandomAug'), dict(prob=0.5, type='RandomFlip'), dict(keep_ratio=True, scale=( 640, 640, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict( keep_empty=False, min_gt_bbox_wh=( 1, 1, ), type='FilterAnnotations'), dict(type='PackDetInputs'), ], type='MultiImageMixDataset') train_pipeline = [ dict(img_scale=( 640, 640, ), pad_val=114.0, type='Mosaic'), dict( border=( -320, -320, ), scaling_ratio_range=( 0.5, 1.5, ), type='RandomAffine'), dict(type='YOLOXHSVRandomAug'), dict(prob=0.5, type='RandomFlip'), dict(keep_ratio=True, scale=( 640, 640, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict(keep_empty=False, min_gt_bbox_wh=( 1, 1, ), type='FilterAnnotations'), dict(type='PackDetInputs'), ] tta_model = dict( tta_cfg=dict(max_per_img=100, nms=dict(iou_threshold=0.65, type='nms')), type='DetTTAModel') tta_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict( transforms=[ [ dict(keep_ratio=True, scale=( 640, 640, ), type='Resize'), dict(keep_ratio=True, scale=( 320, 320, ), type='Resize'), dict(keep_ratio=True, scale=( 960, 960, ), type='Resize'), ], [ dict(prob=1.0, type='RandomFlip'), dict(prob=0.0, type='RandomFlip'), ], [ dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), ], [ dict(type='LoadAnnotations', with_bbox=True), ], [ dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'flip', 'flip_direction', ), type='PackDetInputs'), ], ], type='TestTimeAug'), ] val_cfg = dict(type='ValLoop') val_dataloader = dict( batch_size=8, dataset=dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_val.json', backend_args=None, data_prefix=dict(img='val/'), data_root= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset', metainfo=dict(classes=( 'human', 'trafficsign', 'vehicle', )), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(keep_ratio=True, scale=( 416, 416, ), type='Resize'), dict( pad_to_square=True, pad_val=dict(img=( 114.0, 114.0, 114.0, )), type='Pad'), dict(type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', ), type='PackDetInputs'), ], test_mode=True, type='CocoDataset'), drop_last=False, num_workers=4, persistent_workers=True, sampler=dict(shuffle=False, type='DefaultSampler')) val_evaluator = dict( ann_file= '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_val.json', backend_args=None, metric='bbox', type='CocoMetric') vis_backends = [ dict(type='LocalVisBackend'), ] visualizer = dict( name='visualizer', type='DetLocalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), ]) work_dir = '/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241217-165534/yolox_nano_lite/training' ==================================================================== cuda ==================================================================== backbone.stem.conv.conv.weightload cuda success backbone.stem.conv.bn.weightload cuda success backbone.stem.conv.bn.biasload cuda success backbone.stage1.0.conv.weightload cuda success backbone.stage1.0.bn.weightload cuda success backbone.stage1.0.bn.biasload cuda success backbone.stage1.1.main_conv.conv.weightload cuda success backbone.stage1.1.main_conv.bn.weightload cuda success backbone.stage1.1.main_conv.bn.biasload cuda success backbone.stage1.1.short_conv.conv.weightload cuda success backbone.stage1.1.short_conv.bn.weightload cuda success backbone.stage1.1.short_conv.bn.biasload cuda success backbone.stage1.1.final_conv.conv.weightload cuda success backbone.stage1.1.final_conv.bn.weightload cuda success backbone.stage1.1.final_conv.bn.biasload cuda success backbone.stage1.1.blocks.0.conv1.conv.weightload cuda success backbone.stage1.1.blocks.0.conv1.bn.weightload cuda success backbone.stage1.1.blocks.0.conv1.bn.biasload cuda success backbone.stage1.1.blocks.0.conv2.conv.weightload cuda success backbone.stage1.1.blocks.0.conv2.bn.weightload cuda success backbone.stage1.1.blocks.0.conv2.bn.biasload cuda success backbone.stage2.0.conv.weightload cuda success backbone.stage2.0.bn.weightload cuda success backbone.stage2.0.bn.biasload cuda success backbone.stage2.1.main_conv.conv.weightload cuda success backbone.stage2.1.main_conv.bn.weightload cuda success backbone.stage2.1.main_conv.bn.biasload cuda success backbone.stage2.1.short_conv.conv.weightload cuda success backbone.stage2.1.short_conv.bn.weightload cuda success backbone.stage2.1.short_conv.bn.biasload cuda success backbone.stage2.1.final_conv.conv.weightload cuda success backbone.stage2.1.final_conv.bn.weightload cuda success backbone.stage2.1.final_conv.bn.biasload cuda success backbone.stage2.1.blocks.0.conv1.conv.weightload cuda success backbone.stage2.1.blocks.0.conv1.bn.weightload cuda success backbone.stage2.1.blocks.0.conv1.bn.biasload cuda success backbone.stage2.1.blocks.0.conv2.conv.weightload cuda success backbone.stage2.1.blocks.0.conv2.bn.weightload cuda success backbone.stage2.1.blocks.0.conv2.bn.biasload cuda success backbone.stage2.1.blocks.1.conv1.conv.weightload cuda success backbone.stage2.1.blocks.1.conv1.bn.weightload cuda success backbone.stage2.1.blocks.1.conv1.bn.biasload cuda success backbone.stage2.1.blocks.1.conv2.conv.weightload cuda success backbone.stage2.1.blocks.1.conv2.bn.weightload cuda success backbone.stage2.1.blocks.1.conv2.bn.biasload cuda success backbone.stage2.1.blocks.2.conv1.conv.weightload cuda success backbone.stage2.1.blocks.2.conv1.bn.weightload cuda success backbone.stage2.1.blocks.2.conv1.bn.biasload cuda success backbone.stage2.1.blocks.2.conv2.conv.weightload cuda success backbone.stage2.1.blocks.2.conv2.bn.weightload cuda success backbone.stage2.1.blocks.2.conv2.bn.biasload cuda success backbone.stage3.0.conv.weightload cuda success backbone.stage3.0.bn.weightload cuda success backbone.stage3.0.bn.biasload cuda success backbone.stage3.1.main_conv.conv.weightload cuda success backbone.stage3.1.main_conv.bn.weightload cuda success backbone.stage3.1.main_conv.bn.biasload cuda success backbone.stage3.1.short_conv.conv.weightload cuda success backbone.stage3.1.short_conv.bn.weightload cuda success backbone.stage3.1.short_conv.bn.biasload cuda success backbone.stage3.1.final_conv.conv.weightload cuda success backbone.stage3.1.final_conv.bn.weightload cuda success backbone.stage3.1.final_conv.bn.biasload cuda success backbone.stage3.1.blocks.0.conv1.conv.weightload cuda success backbone.stage3.1.blocks.0.conv1.bn.weightload cuda success backbone.stage3.1.blocks.0.conv1.bn.biasload cuda success backbone.stage3.1.blocks.0.conv2.conv.weightload cuda success backbone.stage3.1.blocks.0.conv2.bn.weightload cuda success backbone.stage3.1.blocks.0.conv2.bn.biasload cuda success backbone.stage3.1.blocks.1.conv1.conv.weightload cuda success backbone.stage3.1.blocks.1.conv1.bn.weightload cuda success backbone.stage3.1.blocks.1.conv1.bn.biasload cuda success backbone.stage3.1.blocks.1.conv2.conv.weightload cuda success backbone.stage3.1.blocks.1.conv2.bn.weightload cuda success backbone.stage3.1.blocks.1.conv2.bn.biasload cuda success backbone.stage3.1.blocks.2.conv1.conv.weightload cuda success backbone.stage3.1.blocks.2.conv1.bn.weightload cuda success backbone.stage3.1.blocks.2.conv1.bn.biasload cuda success backbone.stage3.1.blocks.2.conv2.conv.weightload cuda success backbone.stage3.1.blocks.2.conv2.bn.weightload cuda success backbone.stage3.1.blocks.2.conv2.bn.biasload cuda success backbone.stage4.0.conv.weightload cuda success backbone.stage4.0.bn.weightload cuda success backbone.stage4.0.bn.biasload cuda success backbone.stage4.1.conv1.conv.weightload cuda success backbone.stage4.1.conv1.bn.weightload cuda success backbone.stage4.1.conv1.bn.biasload cuda success backbone.stage4.1.conv2.conv.weightload cuda success backbone.stage4.1.conv2.bn.weightload cuda success backbone.stage4.1.conv2.bn.biasload cuda success backbone.stage4.2.main_conv.conv.weightload cuda success backbone.stage4.2.main_conv.bn.weightload cuda success backbone.stage4.2.main_conv.bn.biasload cuda success backbone.stage4.2.short_conv.conv.weightload cuda success backbone.stage4.2.short_conv.bn.weightload cuda success backbone.stage4.2.short_conv.bn.biasload cuda success backbone.stage4.2.final_conv.conv.weightload cuda success backbone.stage4.2.final_conv.bn.weightload cuda success backbone.stage4.2.final_conv.bn.biasload cuda success backbone.stage4.2.blocks.0.conv1.conv.weightload cuda success backbone.stage4.2.blocks.0.conv1.bn.weightload cuda success backbone.stage4.2.blocks.0.conv1.bn.biasload cuda success backbone.stage4.2.blocks.0.conv2.conv.weightload cuda success backbone.stage4.2.blocks.0.conv2.bn.weightload cuda success backbone.stage4.2.blocks.0.conv2.bn.biasload cuda success neck.reduce_layers.0.conv.weightload cuda success neck.reduce_layers.0.bn.weightload cuda success neck.reduce_layers.0.bn.biasload cuda success neck.reduce_layers.1.conv.weightload cuda success neck.reduce_layers.1.bn.weightload cuda success neck.reduce_layers.1.bn.biasload cuda success neck.top_down_blocks.0.main_conv.conv.weightload cuda success neck.top_down_blocks.0.main_conv.bn.weightload cuda success neck.top_down_blocks.0.main_conv.bn.biasload cuda success neck.top_down_blocks.0.short_conv.conv.weightload cuda success neck.top_down_blocks.0.short_conv.bn.weightload cuda success neck.top_down_blocks.0.short_conv.bn.biasload cuda success neck.top_down_blocks.0.final_conv.conv.weightload cuda success neck.top_down_blocks.0.final_conv.bn.weightload cuda success neck.top_down_blocks.0.final_conv.bn.biasload cuda success neck.top_down_blocks.0.blocks.0.conv1.conv.weightload cuda success neck.top_down_blocks.0.blocks.0.conv1.bn.weightload cuda success neck.top_down_blocks.0.blocks.0.conv1.bn.biasload cuda success neck.top_down_blocks.0.blocks.0.conv2.conv.weightload cuda success neck.top_down_blocks.0.blocks.0.conv2.bn.weightload cuda success neck.top_down_blocks.0.blocks.0.conv2.bn.biasload cuda success neck.top_down_blocks.1.main_conv.conv.weightload cuda success neck.top_down_blocks.1.main_conv.bn.weightload cuda success neck.top_down_blocks.1.main_conv.bn.biasload cuda success neck.top_down_blocks.1.short_conv.conv.weightload cuda success neck.top_down_blocks.1.short_conv.bn.weightload cuda success neck.top_down_blocks.1.short_conv.bn.biasload cuda success neck.top_down_blocks.1.final_conv.conv.weightload cuda success neck.top_down_blocks.1.final_conv.bn.weightload cuda success neck.top_down_blocks.1.final_conv.bn.biasload cuda success neck.top_down_blocks.1.blocks.0.conv1.conv.weightload cuda success neck.top_down_blocks.1.blocks.0.conv1.bn.weightload cuda success neck.top_down_blocks.1.blocks.0.conv1.bn.biasload cuda success neck.top_down_blocks.1.blocks.0.conv2.conv.weightload cuda success neck.top_down_blocks.1.blocks.0.conv2.bn.weightload cuda success neck.top_down_blocks.1.blocks.0.conv2.bn.biasload cuda success neck.downsamples.0.conv.weightload cuda success neck.downsamples.0.bn.weightload cuda success neck.downsamples.0.bn.biasload cuda success neck.downsamples.1.conv.weightload cuda success neck.downsamples.1.bn.weightload cuda success neck.downsamples.1.bn.biasload cuda success neck.bottom_up_blocks.0.main_conv.conv.weightload cuda success neck.bottom_up_blocks.0.main_conv.bn.weightload cuda success neck.bottom_up_blocks.0.main_conv.bn.biasload cuda success neck.bottom_up_blocks.0.short_conv.conv.weightload cuda success neck.bottom_up_blocks.0.short_conv.bn.weightload cuda success neck.bottom_up_blocks.0.short_conv.bn.biasload cuda success neck.bottom_up_blocks.0.final_conv.conv.weightload cuda success neck.bottom_up_blocks.0.final_conv.bn.weightload cuda success neck.bottom_up_blocks.0.final_conv.bn.biasload cuda success neck.bottom_up_blocks.0.blocks.0.conv1.conv.weightload cuda success neck.bottom_up_blocks.0.blocks.0.conv1.bn.weightload cuda success neck.bottom_up_blocks.0.blocks.0.conv1.bn.biasload cuda success neck.bottom_up_blocks.0.blocks.0.conv2.conv.weightload cuda success neck.bottom_up_blocks.0.blocks.0.conv2.bn.weightload cuda success neck.bottom_up_blocks.0.blocks.0.conv2.bn.biasload cuda success neck.bottom_up_blocks.1.main_conv.conv.weightload cuda success neck.bottom_up_blocks.1.main_conv.bn.weightload cuda success neck.bottom_up_blocks.1.main_conv.bn.biasload cuda success neck.bottom_up_blocks.1.short_conv.conv.weightload cuda success neck.bottom_up_blocks.1.short_conv.bn.weightload cuda success neck.bottom_up_blocks.1.short_conv.bn.biasload cuda success neck.bottom_up_blocks.1.final_conv.conv.weightload cuda success neck.bottom_up_blocks.1.final_conv.bn.weightload cuda success neck.bottom_up_blocks.1.final_conv.bn.biasload cuda success neck.bottom_up_blocks.1.blocks.0.conv1.conv.weightload cuda success neck.bottom_up_blocks.1.blocks.0.conv1.bn.weightload cuda success neck.bottom_up_blocks.1.blocks.0.conv1.bn.biasload cuda success neck.bottom_up_blocks.1.blocks.0.conv2.conv.weightload cuda success neck.bottom_up_blocks.1.blocks.0.conv2.bn.weightload cuda success neck.bottom_up_blocks.1.blocks.0.conv2.bn.biasload cuda success neck.out_convs.0.conv.weightload cuda success neck.out_convs.0.bn.weightload cuda success neck.out_convs.0.bn.biasload cuda success neck.out_convs.1.conv.weightload cuda success neck.out_convs.1.bn.weightload cuda success neck.out_convs.1.bn.biasload cuda success neck.out_convs.2.conv.weightload cuda success neck.out_convs.2.bn.weightload cuda success neck.out_convs.2.bn.biasload cuda success bbox_head.multi_level_cls_convs.0.0.conv.weightload cuda success bbox_head.multi_level_cls_convs.0.0.bn.weightload cuda success bbox_head.multi_level_cls_convs.0.0.bn.biasload cuda success bbox_head.multi_level_cls_convs.0.1.conv.weightload cuda success bbox_head.multi_level_cls_convs.0.1.bn.weightload cuda success bbox_head.multi_level_cls_convs.0.1.bn.biasload cuda success bbox_head.multi_level_cls_convs.1.0.conv.weightload cuda success bbox_head.multi_level_cls_convs.1.0.bn.weightload cuda success bbox_head.multi_level_cls_convs.1.0.bn.biasload cuda success bbox_head.multi_level_cls_convs.1.1.conv.weightload cuda success bbox_head.multi_level_cls_convs.1.1.bn.weightload cuda success bbox_head.multi_level_cls_convs.1.1.bn.biasload cuda success bbox_head.multi_level_cls_convs.2.0.conv.weightload cuda success bbox_head.multi_level_cls_convs.2.0.bn.weightload cuda success bbox_head.multi_level_cls_convs.2.0.bn.biasload cuda success bbox_head.multi_level_cls_convs.2.1.conv.weightload cuda success bbox_head.multi_level_cls_convs.2.1.bn.weightload cuda success bbox_head.multi_level_cls_convs.2.1.bn.biasload cuda success bbox_head.multi_level_reg_convs.0.0.conv.weightload cuda success bbox_head.multi_level_reg_convs.0.0.bn.weightload cuda success bbox_head.multi_level_reg_convs.0.0.bn.biasload cuda success bbox_head.multi_level_reg_convs.0.1.conv.weightload cuda success bbox_head.multi_level_reg_convs.0.1.bn.weightload cuda success bbox_head.multi_level_reg_convs.0.1.bn.biasload cuda success bbox_head.multi_level_reg_convs.1.0.conv.weightload cuda success bbox_head.multi_level_reg_convs.1.0.bn.weightload cuda success bbox_head.multi_level_reg_convs.1.0.bn.biasload cuda success bbox_head.multi_level_reg_convs.1.1.conv.weightload cuda success bbox_head.multi_level_reg_convs.1.1.bn.weightload cuda success bbox_head.multi_level_reg_convs.1.1.bn.biasload cuda success bbox_head.multi_level_reg_convs.2.0.conv.weightload cuda success bbox_head.multi_level_reg_convs.2.0.bn.weightload cuda success bbox_head.multi_level_reg_convs.2.0.bn.biasload cuda success bbox_head.multi_level_reg_convs.2.1.conv.weightload cuda success bbox_head.multi_level_reg_convs.2.1.bn.weightload cuda success bbox_head.multi_level_reg_convs.2.1.bn.biasload cuda success bbox_head.multi_level_conv_cls.0.weightload cuda success bbox_head.multi_level_conv_cls.0.biasload cuda success bbox_head.multi_level_conv_cls.1.weightload cuda success bbox_head.multi_level_conv_cls.1.biasload cuda success bbox_head.multi_level_conv_cls.2.weightload cuda success bbox_head.multi_level_conv_cls.2.biasload cuda success bbox_head.multi_level_conv_reg.0.weightload cuda success bbox_head.multi_level_conv_reg.0.biasload cuda success bbox_head.multi_level_conv_reg.1.weightload cuda success bbox_head.multi_level_conv_reg.1.biasload cuda success bbox_head.multi_level_conv_reg.2.weightload cuda success bbox_head.multi_level_conv_reg.2.biasload cuda success bbox_head.multi_level_conv_obj.0.weightload cuda success bbox_head.multi_level_conv_obj.0.biasload cuda success bbox_head.multi_level_conv_obj.1.weightload cuda success bbox_head.multi_level_conv_obj.1.biasload cuda success bbox_head.multi_level_conv_obj.2.weightload cuda success bbox_head.multi_level_conv_obj.2.biasload cuda success 12/17 16:55:44 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (BELOW_NORMAL) LoggerHook -------------------- after_load_checkpoint: (49 ) EMAHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (48 ) YOLOXModeSwitchHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val: (VERY_HIGH ) RuntimeInfoHook -------------------- before_val_epoch: (48 ) SyncNormHook (49 ) EMAHook (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) DetVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_val: (VERY_HIGH ) RuntimeInfoHook -------------------- before_save_checkpoint: (49 ) EMAHook -------------------- after_train: (VERY_HIGH ) RuntimeInfoHook (VERY_LOW ) CheckpointHook -------------------- before_test: (VERY_HIGH ) RuntimeInfoHook -------------------- before_test_epoch: (49 ) EMAHook (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) DetVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test: (VERY_HIGH ) RuntimeInfoHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modeloptimization/torchmodelopt/edgeai_torchmodelopt/xmodelopt/surgery/v1/__init__.py:68: UserWarning: WARNING - xmodelopt.v1.surgery can only replace modules. To replace functions or operators, please use the torch.fx based xmodelopt.v2.surgery instead warnings.warn("WARNING - xmodelopt.v1.surgery can only replace modules. To replace functions or operators, please use the torch.fx based xmodelopt.v2.surgery instead") model surgery done loading annotations into memory... Done (t=0.05s) creating index... index created! 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stem.conv_in.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stem.conv_in.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stem.conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stem.conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage1.1.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.1.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage2.1.blocks.2.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.1.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage3.1.blocks.2.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.1.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- backbone.stage4.2.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.reduce_layers.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.reduce_layers.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.reduce_layers.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.reduce_layers.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.0.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.top_down_blocks.1.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.downsamples.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.downsamples.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.downsamples.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.downsamples.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.0.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.main_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.main_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.short_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.short_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.final_conv.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.final_conv.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.blocks.0.conv1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.blocks.0.conv1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.blocks.0.conv2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.bottom_up_blocks.1.blocks.0.conv2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.2.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- neck.out_convs.2.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.0.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.0.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.0.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.0.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.1.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.1.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.1.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.1.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.2.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.2.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.2.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_cls_convs.2.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.0.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.0.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.0.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.0.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.1.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.1.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.1.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.1.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.2.0.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.2.0.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.2.1.bn.weight:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_reg_convs.2.1.bn.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_cls.0.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_cls.1.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_cls.2.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_reg.0.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_reg.1.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_reg.2.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_obj.0.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_obj.1.bias:weight_decay=0.0 12/17 16:55:46 - mmengine - INFO - paramwise_options -- bbox_head.multi_level_conv_obj.2.bias:weight_decay=0.0 loading annotations into memory... Done (t=0.01s) creating index... index created! loading annotations into memory... Done (t=0.01s) creating index... index created! 12/17 16:55:48 - mmengine - WARNING - init_weights of YOLOX has been called more than once. Loads checkpoint by local backend from path: ./data/downloads/pretrained/yolox_nano_lite/yolox_nano_lite_416x416_20220214_checkpoint.pth /home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/mmengine/runner/checkpoint.py:347: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. checkpoint = torch.load(filename, map_location=map_location) The model and loaded state dict do not match exactly size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.0.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). size mismatch for bbox_head.multi_level_conv_cls.1.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.1.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). size mismatch for bbox_head.multi_level_conv_cls.2.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.2.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). unexpected key in source state_dict: ema_backbone_stem_conv_in_conv_weight, ema_backbone_stem_conv_in_bn_weight, ema_backbone_stem_conv_in_bn_bias, ema_backbone_stem_conv_in_bn_running_mean, ema_backbone_stem_conv_in_bn_running_var, ema_backbone_stem_conv_in_bn_num_batches_tracked, ema_backbone_stem_conv_conv_weight, ema_backbone_stem_conv_bn_weight, ema_backbone_stem_conv_bn_bias, ema_backbone_stem_conv_bn_running_mean, ema_backbone_stem_conv_bn_running_var, ema_backbone_stem_conv_bn_num_batches_tracked, ema_backbone_stage1_0_conv_weight, ema_backbone_stage1_0_bn_weight, ema_backbone_stage1_0_bn_bias, ema_backbone_stage1_0_bn_running_mean, ema_backbone_stage1_0_bn_running_var, ema_backbone_stage1_0_bn_num_batches_tracked, ema_backbone_stage1_1_main_conv_conv_weight, ema_backbone_stage1_1_main_conv_bn_weight, ema_backbone_stage1_1_main_conv_bn_bias, ema_backbone_stage1_1_main_conv_bn_running_mean, ema_backbone_stage1_1_main_conv_bn_running_var, ema_backbone_stage1_1_main_conv_bn_num_batches_tracked, ema_backbone_stage1_1_short_conv_conv_weight, ema_backbone_stage1_1_short_conv_bn_weight, ema_backbone_stage1_1_short_conv_bn_bias, ema_backbone_stage1_1_short_conv_bn_running_mean, ema_backbone_stage1_1_short_conv_bn_running_var, ema_backbone_stage1_1_short_conv_bn_num_batches_tracked, ema_backbone_stage1_1_final_conv_conv_weight, ema_backbone_stage1_1_final_conv_bn_weight, ema_backbone_stage1_1_final_conv_bn_bias, ema_backbone_stage1_1_final_conv_bn_running_mean, ema_backbone_stage1_1_final_conv_bn_running_var, ema_backbone_stage1_1_final_conv_bn_num_batches_tracked, ema_backbone_stage1_1_blocks_0_conv1_conv_weight, ema_backbone_stage1_1_blocks_0_conv1_bn_weight, ema_backbone_stage1_1_blocks_0_conv1_bn_bias, ema_backbone_stage1_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage1_1_blocks_0_conv1_bn_running_var, ema_backbone_stage1_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage1_1_blocks_0_conv2_conv_weight, ema_backbone_stage1_1_blocks_0_conv2_bn_weight, ema_backbone_stage1_1_blocks_0_conv2_bn_bias, ema_backbone_stage1_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage1_1_blocks_0_conv2_bn_running_var, ema_backbone_stage1_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage2_0_conv_weight, ema_backbone_stage2_0_bn_weight, ema_backbone_stage2_0_bn_bias, ema_backbone_stage2_0_bn_running_mean, ema_backbone_stage2_0_bn_running_var, ema_backbone_stage2_0_bn_num_batches_tracked, ema_backbone_stage2_1_main_conv_conv_weight, ema_backbone_stage2_1_main_conv_bn_weight, ema_backbone_stage2_1_main_conv_bn_bias, ema_backbone_stage2_1_main_conv_bn_running_mean, ema_backbone_stage2_1_main_conv_bn_running_var, ema_backbone_stage2_1_main_conv_bn_num_batches_tracked, ema_backbone_stage2_1_short_conv_conv_weight, ema_backbone_stage2_1_short_conv_bn_weight, ema_backbone_stage2_1_short_conv_bn_bias, ema_backbone_stage2_1_short_conv_bn_running_mean, ema_backbone_stage2_1_short_conv_bn_running_var, ema_backbone_stage2_1_short_conv_bn_num_batches_tracked, ema_backbone_stage2_1_final_conv_conv_weight, ema_backbone_stage2_1_final_conv_bn_weight, ema_backbone_stage2_1_final_conv_bn_bias, ema_backbone_stage2_1_final_conv_bn_running_mean, ema_backbone_stage2_1_final_conv_bn_running_var, ema_backbone_stage2_1_final_conv_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_0_conv1_conv_weight, ema_backbone_stage2_1_blocks_0_conv1_bn_weight, ema_backbone_stage2_1_blocks_0_conv1_bn_bias, ema_backbone_stage2_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_0_conv1_bn_running_var, ema_backbone_stage2_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_0_conv2_conv_weight, ema_backbone_stage2_1_blocks_0_conv2_bn_weight, ema_backbone_stage2_1_blocks_0_conv2_bn_bias, ema_backbone_stage2_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_0_conv2_bn_running_var, ema_backbone_stage2_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_1_conv1_conv_weight, ema_backbone_stage2_1_blocks_1_conv1_bn_weight, ema_backbone_stage2_1_blocks_1_conv1_bn_bias, ema_backbone_stage2_1_blocks_1_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_1_conv1_bn_running_var, ema_backbone_stage2_1_blocks_1_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_1_conv2_conv_weight, ema_backbone_stage2_1_blocks_1_conv2_bn_weight, ema_backbone_stage2_1_blocks_1_conv2_bn_bias, ema_backbone_stage2_1_blocks_1_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_1_conv2_bn_running_var, ema_backbone_stage2_1_blocks_1_conv2_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_2_conv1_conv_weight, ema_backbone_stage2_1_blocks_2_conv1_bn_weight, ema_backbone_stage2_1_blocks_2_conv1_bn_bias, ema_backbone_stage2_1_blocks_2_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_2_conv1_bn_running_var, ema_backbone_stage2_1_blocks_2_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_2_conv2_conv_weight, ema_backbone_stage2_1_blocks_2_conv2_bn_weight, ema_backbone_stage2_1_blocks_2_conv2_bn_bias, ema_backbone_stage2_1_blocks_2_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_2_conv2_bn_running_var, ema_backbone_stage2_1_blocks_2_conv2_bn_num_batches_tracked, ema_backbone_stage3_0_conv_weight, ema_backbone_stage3_0_bn_weight, ema_backbone_stage3_0_bn_bias, ema_backbone_stage3_0_bn_running_mean, ema_backbone_stage3_0_bn_running_var, ema_backbone_stage3_0_bn_num_batches_tracked, ema_backbone_stage3_1_main_conv_conv_weight, ema_backbone_stage3_1_main_conv_bn_weight, ema_backbone_stage3_1_main_conv_bn_bias, ema_backbone_stage3_1_main_conv_bn_running_mean, ema_backbone_stage3_1_main_conv_bn_running_var, ema_backbone_stage3_1_main_conv_bn_num_batches_tracked, ema_backbone_stage3_1_short_conv_conv_weight, ema_backbone_stage3_1_short_conv_bn_weight, ema_backbone_stage3_1_short_conv_bn_bias, ema_backbone_stage3_1_short_conv_bn_running_mean, ema_backbone_stage3_1_short_conv_bn_running_var, ema_backbone_stage3_1_short_conv_bn_num_batches_tracked, ema_backbone_stage3_1_final_conv_conv_weight, ema_backbone_stage3_1_final_conv_bn_weight, ema_backbone_stage3_1_final_conv_bn_bias, ema_backbone_stage3_1_final_conv_bn_running_mean, ema_backbone_stage3_1_final_conv_bn_running_var, ema_backbone_stage3_1_final_conv_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_0_conv1_conv_weight, ema_backbone_stage3_1_blocks_0_conv1_bn_weight, ema_backbone_stage3_1_blocks_0_conv1_bn_bias, ema_backbone_stage3_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_0_conv1_bn_running_var, ema_backbone_stage3_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_0_conv2_conv_weight, ema_backbone_stage3_1_blocks_0_conv2_bn_weight, ema_backbone_stage3_1_blocks_0_conv2_bn_bias, ema_backbone_stage3_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_0_conv2_bn_running_var, ema_backbone_stage3_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_1_conv1_conv_weight, ema_backbone_stage3_1_blocks_1_conv1_bn_weight, ema_backbone_stage3_1_blocks_1_conv1_bn_bias, ema_backbone_stage3_1_blocks_1_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_1_conv1_bn_running_var, ema_backbone_stage3_1_blocks_1_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_1_conv2_conv_weight, ema_backbone_stage3_1_blocks_1_conv2_bn_weight, ema_backbone_stage3_1_blocks_1_conv2_bn_bias, ema_backbone_stage3_1_blocks_1_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_1_conv2_bn_running_var, ema_backbone_stage3_1_blocks_1_conv2_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_2_conv1_conv_weight, ema_backbone_stage3_1_blocks_2_conv1_bn_weight, ema_backbone_stage3_1_blocks_2_conv1_bn_bias, ema_backbone_stage3_1_blocks_2_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_2_conv1_bn_running_var, ema_backbone_stage3_1_blocks_2_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_2_conv2_conv_weight, ema_backbone_stage3_1_blocks_2_conv2_bn_weight, ema_backbone_stage3_1_blocks_2_conv2_bn_bias, ema_backbone_stage3_1_blocks_2_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_2_conv2_bn_running_var, ema_backbone_stage3_1_blocks_2_conv2_bn_num_batches_tracked, ema_backbone_stage4_0_conv_weight, ema_backbone_stage4_0_bn_weight, ema_backbone_stage4_0_bn_bias, ema_backbone_stage4_0_bn_running_mean, ema_backbone_stage4_0_bn_running_var, ema_backbone_stage4_0_bn_num_batches_tracked, ema_backbone_stage4_1_conv1_conv_weight, ema_backbone_stage4_1_conv1_bn_weight, ema_backbone_stage4_1_conv1_bn_bias, ema_backbone_stage4_1_conv1_bn_running_mean, ema_backbone_stage4_1_conv1_bn_running_var, ema_backbone_stage4_1_conv1_bn_num_batches_tracked, ema_backbone_stage4_1_conv2_conv_weight, ema_backbone_stage4_1_conv2_bn_weight, ema_backbone_stage4_1_conv2_bn_bias, ema_backbone_stage4_1_conv2_bn_running_mean, ema_backbone_stage4_1_conv2_bn_running_var, ema_backbone_stage4_1_conv2_bn_num_batches_tracked, ema_backbone_stage4_2_main_conv_conv_weight, ema_backbone_stage4_2_main_conv_bn_weight, ema_backbone_stage4_2_main_conv_bn_bias, ema_backbone_stage4_2_main_conv_bn_running_mean, ema_backbone_stage4_2_main_conv_bn_running_var, ema_backbone_stage4_2_main_conv_bn_num_batches_tracked, ema_backbone_stage4_2_short_conv_conv_weight, ema_backbone_stage4_2_short_conv_bn_weight, ema_backbone_stage4_2_short_conv_bn_bias, ema_backbone_stage4_2_short_conv_bn_running_mean, ema_backbone_stage4_2_short_conv_bn_running_var, ema_backbone_stage4_2_short_conv_bn_num_batches_tracked, ema_backbone_stage4_2_final_conv_conv_weight, ema_backbone_stage4_2_final_conv_bn_weight, ema_backbone_stage4_2_final_conv_bn_bias, ema_backbone_stage4_2_final_conv_bn_running_mean, ema_backbone_stage4_2_final_conv_bn_running_var, ema_backbone_stage4_2_final_conv_bn_num_batches_tracked, ema_backbone_stage4_2_blocks_0_conv1_conv_weight, ema_backbone_stage4_2_blocks_0_conv1_bn_weight, ema_backbone_stage4_2_blocks_0_conv1_bn_bias, ema_backbone_stage4_2_blocks_0_conv1_bn_running_mean, ema_backbone_stage4_2_blocks_0_conv1_bn_running_var, ema_backbone_stage4_2_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage4_2_blocks_0_conv2_conv_weight, ema_backbone_stage4_2_blocks_0_conv2_bn_weight, ema_backbone_stage4_2_blocks_0_conv2_bn_bias, ema_backbone_stage4_2_blocks_0_conv2_bn_running_mean, ema_backbone_stage4_2_blocks_0_conv2_bn_running_var, ema_backbone_stage4_2_blocks_0_conv2_bn_num_batches_tracked, ema_neck_reduce_layers_0_conv_weight, ema_neck_reduce_layers_0_bn_weight, ema_neck_reduce_layers_0_bn_bias, ema_neck_reduce_layers_0_bn_running_mean, ema_neck_reduce_layers_0_bn_running_var, ema_neck_reduce_layers_0_bn_num_batches_tracked, ema_neck_reduce_layers_1_conv_weight, ema_neck_reduce_layers_1_bn_weight, ema_neck_reduce_layers_1_bn_bias, ema_neck_reduce_layers_1_bn_running_mean, ema_neck_reduce_layers_1_bn_running_var, ema_neck_reduce_layers_1_bn_num_batches_tracked, ema_neck_top_down_blocks_0_main_conv_conv_weight, ema_neck_top_down_blocks_0_main_conv_bn_weight, ema_neck_top_down_blocks_0_main_conv_bn_bias, ema_neck_top_down_blocks_0_main_conv_bn_running_mean, ema_neck_top_down_blocks_0_main_conv_bn_running_var, ema_neck_top_down_blocks_0_main_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_short_conv_conv_weight, ema_neck_top_down_blocks_0_short_conv_bn_weight, ema_neck_top_down_blocks_0_short_conv_bn_bias, ema_neck_top_down_blocks_0_short_conv_bn_running_mean, ema_neck_top_down_blocks_0_short_conv_bn_running_var, ema_neck_top_down_blocks_0_short_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_final_conv_conv_weight, ema_neck_top_down_blocks_0_final_conv_bn_weight, ema_neck_top_down_blocks_0_final_conv_bn_bias, ema_neck_top_down_blocks_0_final_conv_bn_running_mean, ema_neck_top_down_blocks_0_final_conv_bn_running_var, ema_neck_top_down_blocks_0_final_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_blocks_0_conv1_conv_weight, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_weight, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_bias, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_running_mean, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_running_var, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_num_batches_tracked, ema_neck_top_down_blocks_0_blocks_0_conv2_conv_weight, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_weight, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_bias, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_running_mean, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_running_var, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_num_batches_tracked, ema_neck_top_down_blocks_1_main_conv_conv_weight, ema_neck_top_down_blocks_1_main_conv_bn_weight, ema_neck_top_down_blocks_1_main_conv_bn_bias, ema_neck_top_down_blocks_1_main_conv_bn_running_mean, ema_neck_top_down_blocks_1_main_conv_bn_running_var, ema_neck_top_down_blocks_1_main_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_short_conv_conv_weight, ema_neck_top_down_blocks_1_short_conv_bn_weight, ema_neck_top_down_blocks_1_short_conv_bn_bias, ema_neck_top_down_blocks_1_short_conv_bn_running_mean, ema_neck_top_down_blocks_1_short_conv_bn_running_var, ema_neck_top_down_blocks_1_short_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_final_conv_conv_weight, ema_neck_top_down_blocks_1_final_conv_bn_weight, ema_neck_top_down_blocks_1_final_conv_bn_bias, ema_neck_top_down_blocks_1_final_conv_bn_running_mean, ema_neck_top_down_blocks_1_final_conv_bn_running_var, ema_neck_top_down_blocks_1_final_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_blocks_0_conv1_conv_weight, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_weight, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_bias, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_running_mean, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_running_var, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_num_batches_tracked, ema_neck_top_down_blocks_1_blocks_0_conv2_conv_weight, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_weight, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_bias, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_running_mean, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_running_var, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_num_batches_tracked, ema_neck_downsamples_0_conv_weight, ema_neck_downsamples_0_bn_weight, ema_neck_downsamples_0_bn_bias, ema_neck_downsamples_0_bn_running_mean, ema_neck_downsamples_0_bn_running_var, ema_neck_downsamples_0_bn_num_batches_tracked, ema_neck_downsamples_1_conv_weight, ema_neck_downsamples_1_bn_weight, ema_neck_downsamples_1_bn_bias, ema_neck_downsamples_1_bn_running_mean, ema_neck_downsamples_1_bn_running_var, ema_neck_downsamples_1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_main_conv_conv_weight, ema_neck_bottom_up_blocks_0_main_conv_bn_weight, ema_neck_bottom_up_blocks_0_main_conv_bn_bias, ema_neck_bottom_up_blocks_0_main_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_main_conv_bn_running_var, ema_neck_bottom_up_blocks_0_main_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_short_conv_conv_weight, ema_neck_bottom_up_blocks_0_short_conv_bn_weight, ema_neck_bottom_up_blocks_0_short_conv_bn_bias, ema_neck_bottom_up_blocks_0_short_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_short_conv_bn_running_var, ema_neck_bottom_up_blocks_0_short_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_final_conv_conv_weight, ema_neck_bottom_up_blocks_0_final_conv_bn_weight, ema_neck_bottom_up_blocks_0_final_conv_bn_bias, ema_neck_bottom_up_blocks_0_final_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_final_conv_bn_running_var, ema_neck_bottom_up_blocks_0_final_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_blocks_0_conv1_conv_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_bias, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_running_mean, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_running_var, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_blocks_0_conv2_conv_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_bias, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_running_mean, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_running_var, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_main_conv_conv_weight, ema_neck_bottom_up_blocks_1_main_conv_bn_weight, ema_neck_bottom_up_blocks_1_main_conv_bn_bias, ema_neck_bottom_up_blocks_1_main_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_main_conv_bn_running_var, ema_neck_bottom_up_blocks_1_main_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_short_conv_conv_weight, ema_neck_bottom_up_blocks_1_short_conv_bn_weight, ema_neck_bottom_up_blocks_1_short_conv_bn_bias, ema_neck_bottom_up_blocks_1_short_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_short_conv_bn_running_var, ema_neck_bottom_up_blocks_1_short_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_final_conv_conv_weight, ema_neck_bottom_up_blocks_1_final_conv_bn_weight, ema_neck_bottom_up_blocks_1_final_conv_bn_bias, ema_neck_bottom_up_blocks_1_final_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_final_conv_bn_running_var, ema_neck_bottom_up_blocks_1_final_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_blocks_0_conv1_conv_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_bias, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_running_mean, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_running_var, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_blocks_0_conv2_conv_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_bias, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_running_mean, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_running_var, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_num_batches_tracked, ema_neck_out_convs_0_conv_weight, ema_neck_out_convs_0_bn_weight, ema_neck_out_convs_0_bn_bias, ema_neck_out_convs_0_bn_running_mean, ema_neck_out_convs_0_bn_running_var, ema_neck_out_convs_0_bn_num_batches_tracked, ema_neck_out_convs_1_conv_weight, ema_neck_out_convs_1_bn_weight, ema_neck_out_convs_1_bn_bias, ema_neck_out_convs_1_bn_running_mean, ema_neck_out_convs_1_bn_running_var, ema_neck_out_convs_1_bn_num_batches_tracked, ema_neck_out_convs_2_conv_weight, ema_neck_out_convs_2_bn_weight, ema_neck_out_convs_2_bn_bias, ema_neck_out_convs_2_bn_running_mean, ema_neck_out_convs_2_bn_running_var, ema_neck_out_convs_2_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_0_0_conv_weight, ema_bbox_head_multi_level_cls_convs_0_0_bn_weight, ema_bbox_head_multi_level_cls_convs_0_0_bn_bias, ema_bbox_head_multi_level_cls_convs_0_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_0_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_0_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_0_1_conv_weight, ema_bbox_head_multi_level_cls_convs_0_1_bn_weight, ema_bbox_head_multi_level_cls_convs_0_1_bn_bias, ema_bbox_head_multi_level_cls_convs_0_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_0_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_0_1_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_1_0_conv_weight, ema_bbox_head_multi_level_cls_convs_1_0_bn_weight, ema_bbox_head_multi_level_cls_convs_1_0_bn_bias, ema_bbox_head_multi_level_cls_convs_1_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_1_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_1_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_1_1_conv_weight, ema_bbox_head_multi_level_cls_convs_1_1_bn_weight, ema_bbox_head_multi_level_cls_convs_1_1_bn_bias, ema_bbox_head_multi_level_cls_convs_1_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_1_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_1_1_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_2_0_conv_weight, ema_bbox_head_multi_level_cls_convs_2_0_bn_weight, ema_bbox_head_multi_level_cls_convs_2_0_bn_bias, ema_bbox_head_multi_level_cls_convs_2_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_2_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_2_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_2_1_conv_weight, ema_bbox_head_multi_level_cls_convs_2_1_bn_weight, ema_bbox_head_multi_level_cls_convs_2_1_bn_bias, ema_bbox_head_multi_level_cls_convs_2_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_2_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_2_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_0_0_conv_weight, ema_bbox_head_multi_level_reg_convs_0_0_bn_weight, ema_bbox_head_multi_level_reg_convs_0_0_bn_bias, ema_bbox_head_multi_level_reg_convs_0_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_0_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_0_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_0_1_conv_weight, ema_bbox_head_multi_level_reg_convs_0_1_bn_weight, ema_bbox_head_multi_level_reg_convs_0_1_bn_bias, ema_bbox_head_multi_level_reg_convs_0_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_0_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_0_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_1_0_conv_weight, ema_bbox_head_multi_level_reg_convs_1_0_bn_weight, ema_bbox_head_multi_level_reg_convs_1_0_bn_bias, ema_bbox_head_multi_level_reg_convs_1_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_1_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_1_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_1_1_conv_weight, ema_bbox_head_multi_level_reg_convs_1_1_bn_weight, ema_bbox_head_multi_level_reg_convs_1_1_bn_bias, ema_bbox_head_multi_level_reg_convs_1_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_1_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_1_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_2_0_conv_weight, ema_bbox_head_multi_level_reg_convs_2_0_bn_weight, ema_bbox_head_multi_level_reg_convs_2_0_bn_bias, ema_bbox_head_multi_level_reg_convs_2_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_2_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_2_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_2_1_conv_weight, ema_bbox_head_multi_level_reg_convs_2_1_bn_weight, ema_bbox_head_multi_level_reg_convs_2_1_bn_bias, ema_bbox_head_multi_level_reg_convs_2_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_2_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_2_1_bn_num_batches_tracked, ema_bbox_head_multi_level_conv_cls_0_weight, ema_bbox_head_multi_level_conv_cls_0_bias, ema_bbox_head_multi_level_conv_cls_1_weight, ema_bbox_head_multi_level_conv_cls_1_bias, ema_bbox_head_multi_level_conv_cls_2_weight, ema_bbox_head_multi_level_conv_cls_2_bias, ema_bbox_head_multi_level_conv_reg_0_weight, ema_bbox_head_multi_level_conv_reg_0_bias, ema_bbox_head_multi_level_conv_reg_1_weight, ema_bbox_head_multi_level_conv_reg_1_bias, ema_bbox_head_multi_level_conv_reg_2_weight, ema_bbox_head_multi_level_conv_reg_2_bias, ema_bbox_head_multi_level_conv_obj_0_weight, ema_bbox_head_multi_level_conv_obj_0_bias, ema_bbox_head_multi_level_conv_obj_1_weight, ema_bbox_head_multi_level_conv_obj_1_bias, ema_bbox_head_multi_level_conv_obj_2_weight, ema_bbox_head_multi_level_conv_obj_2_bias The model and loaded state dict do not match exactly size mismatch for bbox_head.multi_level_conv_cls.0.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.0.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). size mismatch for bbox_head.multi_level_conv_cls.1.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.1.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). size mismatch for bbox_head.multi_level_conv_cls.2.weight: copying a param with shape torch.Size([80, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]). size mismatch for bbox_head.multi_level_conv_cls.2.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([3]). unexpected key in source state_dict: ema_backbone_stem_conv_in_conv_weight, ema_backbone_stem_conv_in_bn_weight, ema_backbone_stem_conv_in_bn_bias, ema_backbone_stem_conv_in_bn_running_mean, ema_backbone_stem_conv_in_bn_running_var, ema_backbone_stem_conv_in_bn_num_batches_tracked, ema_backbone_stem_conv_conv_weight, ema_backbone_stem_conv_bn_weight, ema_backbone_stem_conv_bn_bias, ema_backbone_stem_conv_bn_running_mean, ema_backbone_stem_conv_bn_running_var, ema_backbone_stem_conv_bn_num_batches_tracked, ema_backbone_stage1_0_conv_weight, ema_backbone_stage1_0_bn_weight, ema_backbone_stage1_0_bn_bias, ema_backbone_stage1_0_bn_running_mean, ema_backbone_stage1_0_bn_running_var, ema_backbone_stage1_0_bn_num_batches_tracked, ema_backbone_stage1_1_main_conv_conv_weight, ema_backbone_stage1_1_main_conv_bn_weight, ema_backbone_stage1_1_main_conv_bn_bias, ema_backbone_stage1_1_main_conv_bn_running_mean, ema_backbone_stage1_1_main_conv_bn_running_var, ema_backbone_stage1_1_main_conv_bn_num_batches_tracked, ema_backbone_stage1_1_short_conv_conv_weight, ema_backbone_stage1_1_short_conv_bn_weight, ema_backbone_stage1_1_short_conv_bn_bias, ema_backbone_stage1_1_short_conv_bn_running_mean, ema_backbone_stage1_1_short_conv_bn_running_var, ema_backbone_stage1_1_short_conv_bn_num_batches_tracked, ema_backbone_stage1_1_final_conv_conv_weight, ema_backbone_stage1_1_final_conv_bn_weight, ema_backbone_stage1_1_final_conv_bn_bias, ema_backbone_stage1_1_final_conv_bn_running_mean, ema_backbone_stage1_1_final_conv_bn_running_var, ema_backbone_stage1_1_final_conv_bn_num_batches_tracked, ema_backbone_stage1_1_blocks_0_conv1_conv_weight, ema_backbone_stage1_1_blocks_0_conv1_bn_weight, ema_backbone_stage1_1_blocks_0_conv1_bn_bias, ema_backbone_stage1_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage1_1_blocks_0_conv1_bn_running_var, ema_backbone_stage1_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage1_1_blocks_0_conv2_conv_weight, ema_backbone_stage1_1_blocks_0_conv2_bn_weight, ema_backbone_stage1_1_blocks_0_conv2_bn_bias, ema_backbone_stage1_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage1_1_blocks_0_conv2_bn_running_var, ema_backbone_stage1_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage2_0_conv_weight, ema_backbone_stage2_0_bn_weight, ema_backbone_stage2_0_bn_bias, ema_backbone_stage2_0_bn_running_mean, ema_backbone_stage2_0_bn_running_var, ema_backbone_stage2_0_bn_num_batches_tracked, ema_backbone_stage2_1_main_conv_conv_weight, ema_backbone_stage2_1_main_conv_bn_weight, ema_backbone_stage2_1_main_conv_bn_bias, ema_backbone_stage2_1_main_conv_bn_running_mean, ema_backbone_stage2_1_main_conv_bn_running_var, ema_backbone_stage2_1_main_conv_bn_num_batches_tracked, ema_backbone_stage2_1_short_conv_conv_weight, ema_backbone_stage2_1_short_conv_bn_weight, ema_backbone_stage2_1_short_conv_bn_bias, ema_backbone_stage2_1_short_conv_bn_running_mean, ema_backbone_stage2_1_short_conv_bn_running_var, ema_backbone_stage2_1_short_conv_bn_num_batches_tracked, ema_backbone_stage2_1_final_conv_conv_weight, ema_backbone_stage2_1_final_conv_bn_weight, ema_backbone_stage2_1_final_conv_bn_bias, ema_backbone_stage2_1_final_conv_bn_running_mean, ema_backbone_stage2_1_final_conv_bn_running_var, ema_backbone_stage2_1_final_conv_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_0_conv1_conv_weight, ema_backbone_stage2_1_blocks_0_conv1_bn_weight, ema_backbone_stage2_1_blocks_0_conv1_bn_bias, ema_backbone_stage2_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_0_conv1_bn_running_var, ema_backbone_stage2_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_0_conv2_conv_weight, ema_backbone_stage2_1_blocks_0_conv2_bn_weight, ema_backbone_stage2_1_blocks_0_conv2_bn_bias, ema_backbone_stage2_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_0_conv2_bn_running_var, ema_backbone_stage2_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_1_conv1_conv_weight, ema_backbone_stage2_1_blocks_1_conv1_bn_weight, ema_backbone_stage2_1_blocks_1_conv1_bn_bias, ema_backbone_stage2_1_blocks_1_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_1_conv1_bn_running_var, ema_backbone_stage2_1_blocks_1_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_1_conv2_conv_weight, ema_backbone_stage2_1_blocks_1_conv2_bn_weight, ema_backbone_stage2_1_blocks_1_conv2_bn_bias, ema_backbone_stage2_1_blocks_1_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_1_conv2_bn_running_var, ema_backbone_stage2_1_blocks_1_conv2_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_2_conv1_conv_weight, ema_backbone_stage2_1_blocks_2_conv1_bn_weight, ema_backbone_stage2_1_blocks_2_conv1_bn_bias, ema_backbone_stage2_1_blocks_2_conv1_bn_running_mean, ema_backbone_stage2_1_blocks_2_conv1_bn_running_var, ema_backbone_stage2_1_blocks_2_conv1_bn_num_batches_tracked, ema_backbone_stage2_1_blocks_2_conv2_conv_weight, ema_backbone_stage2_1_blocks_2_conv2_bn_weight, ema_backbone_stage2_1_blocks_2_conv2_bn_bias, ema_backbone_stage2_1_blocks_2_conv2_bn_running_mean, ema_backbone_stage2_1_blocks_2_conv2_bn_running_var, ema_backbone_stage2_1_blocks_2_conv2_bn_num_batches_tracked, ema_backbone_stage3_0_conv_weight, ema_backbone_stage3_0_bn_weight, ema_backbone_stage3_0_bn_bias, ema_backbone_stage3_0_bn_running_mean, ema_backbone_stage3_0_bn_running_var, ema_backbone_stage3_0_bn_num_batches_tracked, ema_backbone_stage3_1_main_conv_conv_weight, ema_backbone_stage3_1_main_conv_bn_weight, ema_backbone_stage3_1_main_conv_bn_bias, ema_backbone_stage3_1_main_conv_bn_running_mean, ema_backbone_stage3_1_main_conv_bn_running_var, ema_backbone_stage3_1_main_conv_bn_num_batches_tracked, ema_backbone_stage3_1_short_conv_conv_weight, ema_backbone_stage3_1_short_conv_bn_weight, ema_backbone_stage3_1_short_conv_bn_bias, ema_backbone_stage3_1_short_conv_bn_running_mean, ema_backbone_stage3_1_short_conv_bn_running_var, ema_backbone_stage3_1_short_conv_bn_num_batches_tracked, ema_backbone_stage3_1_final_conv_conv_weight, ema_backbone_stage3_1_final_conv_bn_weight, ema_backbone_stage3_1_final_conv_bn_bias, ema_backbone_stage3_1_final_conv_bn_running_mean, ema_backbone_stage3_1_final_conv_bn_running_var, ema_backbone_stage3_1_final_conv_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_0_conv1_conv_weight, ema_backbone_stage3_1_blocks_0_conv1_bn_weight, ema_backbone_stage3_1_blocks_0_conv1_bn_bias, ema_backbone_stage3_1_blocks_0_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_0_conv1_bn_running_var, ema_backbone_stage3_1_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_0_conv2_conv_weight, ema_backbone_stage3_1_blocks_0_conv2_bn_weight, ema_backbone_stage3_1_blocks_0_conv2_bn_bias, ema_backbone_stage3_1_blocks_0_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_0_conv2_bn_running_var, ema_backbone_stage3_1_blocks_0_conv2_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_1_conv1_conv_weight, ema_backbone_stage3_1_blocks_1_conv1_bn_weight, ema_backbone_stage3_1_blocks_1_conv1_bn_bias, ema_backbone_stage3_1_blocks_1_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_1_conv1_bn_running_var, ema_backbone_stage3_1_blocks_1_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_1_conv2_conv_weight, ema_backbone_stage3_1_blocks_1_conv2_bn_weight, ema_backbone_stage3_1_blocks_1_conv2_bn_bias, ema_backbone_stage3_1_blocks_1_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_1_conv2_bn_running_var, ema_backbone_stage3_1_blocks_1_conv2_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_2_conv1_conv_weight, ema_backbone_stage3_1_blocks_2_conv1_bn_weight, ema_backbone_stage3_1_blocks_2_conv1_bn_bias, ema_backbone_stage3_1_blocks_2_conv1_bn_running_mean, ema_backbone_stage3_1_blocks_2_conv1_bn_running_var, ema_backbone_stage3_1_blocks_2_conv1_bn_num_batches_tracked, ema_backbone_stage3_1_blocks_2_conv2_conv_weight, ema_backbone_stage3_1_blocks_2_conv2_bn_weight, ema_backbone_stage3_1_blocks_2_conv2_bn_bias, ema_backbone_stage3_1_blocks_2_conv2_bn_running_mean, ema_backbone_stage3_1_blocks_2_conv2_bn_running_var, ema_backbone_stage3_1_blocks_2_conv2_bn_num_batches_tracked, ema_backbone_stage4_0_conv_weight, ema_backbone_stage4_0_bn_weight, ema_backbone_stage4_0_bn_bias, ema_backbone_stage4_0_bn_running_mean, ema_backbone_stage4_0_bn_running_var, ema_backbone_stage4_0_bn_num_batches_tracked, ema_backbone_stage4_1_conv1_conv_weight, ema_backbone_stage4_1_conv1_bn_weight, ema_backbone_stage4_1_conv1_bn_bias, ema_backbone_stage4_1_conv1_bn_running_mean, ema_backbone_stage4_1_conv1_bn_running_var, ema_backbone_stage4_1_conv1_bn_num_batches_tracked, ema_backbone_stage4_1_conv2_conv_weight, ema_backbone_stage4_1_conv2_bn_weight, ema_backbone_stage4_1_conv2_bn_bias, ema_backbone_stage4_1_conv2_bn_running_mean, ema_backbone_stage4_1_conv2_bn_running_var, ema_backbone_stage4_1_conv2_bn_num_batches_tracked, ema_backbone_stage4_2_main_conv_conv_weight, ema_backbone_stage4_2_main_conv_bn_weight, ema_backbone_stage4_2_main_conv_bn_bias, ema_backbone_stage4_2_main_conv_bn_running_mean, ema_backbone_stage4_2_main_conv_bn_running_var, ema_backbone_stage4_2_main_conv_bn_num_batches_tracked, ema_backbone_stage4_2_short_conv_conv_weight, ema_backbone_stage4_2_short_conv_bn_weight, ema_backbone_stage4_2_short_conv_bn_bias, ema_backbone_stage4_2_short_conv_bn_running_mean, ema_backbone_stage4_2_short_conv_bn_running_var, ema_backbone_stage4_2_short_conv_bn_num_batches_tracked, ema_backbone_stage4_2_final_conv_conv_weight, ema_backbone_stage4_2_final_conv_bn_weight, ema_backbone_stage4_2_final_conv_bn_bias, ema_backbone_stage4_2_final_conv_bn_running_mean, ema_backbone_stage4_2_final_conv_bn_running_var, ema_backbone_stage4_2_final_conv_bn_num_batches_tracked, ema_backbone_stage4_2_blocks_0_conv1_conv_weight, ema_backbone_stage4_2_blocks_0_conv1_bn_weight, ema_backbone_stage4_2_blocks_0_conv1_bn_bias, ema_backbone_stage4_2_blocks_0_conv1_bn_running_mean, ema_backbone_stage4_2_blocks_0_conv1_bn_running_var, ema_backbone_stage4_2_blocks_0_conv1_bn_num_batches_tracked, ema_backbone_stage4_2_blocks_0_conv2_conv_weight, ema_backbone_stage4_2_blocks_0_conv2_bn_weight, ema_backbone_stage4_2_blocks_0_conv2_bn_bias, ema_backbone_stage4_2_blocks_0_conv2_bn_running_mean, ema_backbone_stage4_2_blocks_0_conv2_bn_running_var, ema_backbone_stage4_2_blocks_0_conv2_bn_num_batches_tracked, ema_neck_reduce_layers_0_conv_weight, ema_neck_reduce_layers_0_bn_weight, ema_neck_reduce_layers_0_bn_bias, ema_neck_reduce_layers_0_bn_running_mean, ema_neck_reduce_layers_0_bn_running_var, ema_neck_reduce_layers_0_bn_num_batches_tracked, ema_neck_reduce_layers_1_conv_weight, ema_neck_reduce_layers_1_bn_weight, ema_neck_reduce_layers_1_bn_bias, ema_neck_reduce_layers_1_bn_running_mean, ema_neck_reduce_layers_1_bn_running_var, ema_neck_reduce_layers_1_bn_num_batches_tracked, ema_neck_top_down_blocks_0_main_conv_conv_weight, ema_neck_top_down_blocks_0_main_conv_bn_weight, ema_neck_top_down_blocks_0_main_conv_bn_bias, ema_neck_top_down_blocks_0_main_conv_bn_running_mean, ema_neck_top_down_blocks_0_main_conv_bn_running_var, ema_neck_top_down_blocks_0_main_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_short_conv_conv_weight, ema_neck_top_down_blocks_0_short_conv_bn_weight, ema_neck_top_down_blocks_0_short_conv_bn_bias, ema_neck_top_down_blocks_0_short_conv_bn_running_mean, ema_neck_top_down_blocks_0_short_conv_bn_running_var, ema_neck_top_down_blocks_0_short_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_final_conv_conv_weight, ema_neck_top_down_blocks_0_final_conv_bn_weight, ema_neck_top_down_blocks_0_final_conv_bn_bias, ema_neck_top_down_blocks_0_final_conv_bn_running_mean, ema_neck_top_down_blocks_0_final_conv_bn_running_var, ema_neck_top_down_blocks_0_final_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_0_blocks_0_conv1_conv_weight, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_weight, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_bias, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_running_mean, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_running_var, ema_neck_top_down_blocks_0_blocks_0_conv1_bn_num_batches_tracked, ema_neck_top_down_blocks_0_blocks_0_conv2_conv_weight, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_weight, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_bias, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_running_mean, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_running_var, ema_neck_top_down_blocks_0_blocks_0_conv2_bn_num_batches_tracked, ema_neck_top_down_blocks_1_main_conv_conv_weight, ema_neck_top_down_blocks_1_main_conv_bn_weight, ema_neck_top_down_blocks_1_main_conv_bn_bias, ema_neck_top_down_blocks_1_main_conv_bn_running_mean, ema_neck_top_down_blocks_1_main_conv_bn_running_var, ema_neck_top_down_blocks_1_main_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_short_conv_conv_weight, ema_neck_top_down_blocks_1_short_conv_bn_weight, ema_neck_top_down_blocks_1_short_conv_bn_bias, ema_neck_top_down_blocks_1_short_conv_bn_running_mean, ema_neck_top_down_blocks_1_short_conv_bn_running_var, ema_neck_top_down_blocks_1_short_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_final_conv_conv_weight, ema_neck_top_down_blocks_1_final_conv_bn_weight, ema_neck_top_down_blocks_1_final_conv_bn_bias, ema_neck_top_down_blocks_1_final_conv_bn_running_mean, ema_neck_top_down_blocks_1_final_conv_bn_running_var, ema_neck_top_down_blocks_1_final_conv_bn_num_batches_tracked, ema_neck_top_down_blocks_1_blocks_0_conv1_conv_weight, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_weight, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_bias, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_running_mean, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_running_var, ema_neck_top_down_blocks_1_blocks_0_conv1_bn_num_batches_tracked, ema_neck_top_down_blocks_1_blocks_0_conv2_conv_weight, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_weight, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_bias, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_running_mean, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_running_var, ema_neck_top_down_blocks_1_blocks_0_conv2_bn_num_batches_tracked, ema_neck_downsamples_0_conv_weight, ema_neck_downsamples_0_bn_weight, ema_neck_downsamples_0_bn_bias, ema_neck_downsamples_0_bn_running_mean, ema_neck_downsamples_0_bn_running_var, ema_neck_downsamples_0_bn_num_batches_tracked, ema_neck_downsamples_1_conv_weight, ema_neck_downsamples_1_bn_weight, ema_neck_downsamples_1_bn_bias, ema_neck_downsamples_1_bn_running_mean, ema_neck_downsamples_1_bn_running_var, ema_neck_downsamples_1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_main_conv_conv_weight, ema_neck_bottom_up_blocks_0_main_conv_bn_weight, ema_neck_bottom_up_blocks_0_main_conv_bn_bias, ema_neck_bottom_up_blocks_0_main_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_main_conv_bn_running_var, ema_neck_bottom_up_blocks_0_main_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_short_conv_conv_weight, ema_neck_bottom_up_blocks_0_short_conv_bn_weight, ema_neck_bottom_up_blocks_0_short_conv_bn_bias, ema_neck_bottom_up_blocks_0_short_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_short_conv_bn_running_var, ema_neck_bottom_up_blocks_0_short_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_final_conv_conv_weight, ema_neck_bottom_up_blocks_0_final_conv_bn_weight, ema_neck_bottom_up_blocks_0_final_conv_bn_bias, ema_neck_bottom_up_blocks_0_final_conv_bn_running_mean, ema_neck_bottom_up_blocks_0_final_conv_bn_running_var, ema_neck_bottom_up_blocks_0_final_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_blocks_0_conv1_conv_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_bias, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_running_mean, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_running_var, ema_neck_bottom_up_blocks_0_blocks_0_conv1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_0_blocks_0_conv2_conv_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_weight, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_bias, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_running_mean, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_running_var, ema_neck_bottom_up_blocks_0_blocks_0_conv2_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_main_conv_conv_weight, ema_neck_bottom_up_blocks_1_main_conv_bn_weight, ema_neck_bottom_up_blocks_1_main_conv_bn_bias, ema_neck_bottom_up_blocks_1_main_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_main_conv_bn_running_var, ema_neck_bottom_up_blocks_1_main_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_short_conv_conv_weight, ema_neck_bottom_up_blocks_1_short_conv_bn_weight, ema_neck_bottom_up_blocks_1_short_conv_bn_bias, ema_neck_bottom_up_blocks_1_short_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_short_conv_bn_running_var, ema_neck_bottom_up_blocks_1_short_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_final_conv_conv_weight, ema_neck_bottom_up_blocks_1_final_conv_bn_weight, ema_neck_bottom_up_blocks_1_final_conv_bn_bias, ema_neck_bottom_up_blocks_1_final_conv_bn_running_mean, ema_neck_bottom_up_blocks_1_final_conv_bn_running_var, ema_neck_bottom_up_blocks_1_final_conv_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_blocks_0_conv1_conv_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_bias, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_running_mean, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_running_var, ema_neck_bottom_up_blocks_1_blocks_0_conv1_bn_num_batches_tracked, ema_neck_bottom_up_blocks_1_blocks_0_conv2_conv_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_weight, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_bias, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_running_mean, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_running_var, ema_neck_bottom_up_blocks_1_blocks_0_conv2_bn_num_batches_tracked, ema_neck_out_convs_0_conv_weight, ema_neck_out_convs_0_bn_weight, ema_neck_out_convs_0_bn_bias, ema_neck_out_convs_0_bn_running_mean, ema_neck_out_convs_0_bn_running_var, ema_neck_out_convs_0_bn_num_batches_tracked, ema_neck_out_convs_1_conv_weight, ema_neck_out_convs_1_bn_weight, ema_neck_out_convs_1_bn_bias, ema_neck_out_convs_1_bn_running_mean, ema_neck_out_convs_1_bn_running_var, ema_neck_out_convs_1_bn_num_batches_tracked, ema_neck_out_convs_2_conv_weight, ema_neck_out_convs_2_bn_weight, ema_neck_out_convs_2_bn_bias, ema_neck_out_convs_2_bn_running_mean, ema_neck_out_convs_2_bn_running_var, ema_neck_out_convs_2_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_0_0_conv_weight, ema_bbox_head_multi_level_cls_convs_0_0_bn_weight, ema_bbox_head_multi_level_cls_convs_0_0_bn_bias, ema_bbox_head_multi_level_cls_convs_0_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_0_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_0_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_0_1_conv_weight, ema_bbox_head_multi_level_cls_convs_0_1_bn_weight, ema_bbox_head_multi_level_cls_convs_0_1_bn_bias, ema_bbox_head_multi_level_cls_convs_0_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_0_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_0_1_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_1_0_conv_weight, ema_bbox_head_multi_level_cls_convs_1_0_bn_weight, ema_bbox_head_multi_level_cls_convs_1_0_bn_bias, ema_bbox_head_multi_level_cls_convs_1_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_1_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_1_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_1_1_conv_weight, ema_bbox_head_multi_level_cls_convs_1_1_bn_weight, ema_bbox_head_multi_level_cls_convs_1_1_bn_bias, ema_bbox_head_multi_level_cls_convs_1_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_1_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_1_1_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_2_0_conv_weight, ema_bbox_head_multi_level_cls_convs_2_0_bn_weight, ema_bbox_head_multi_level_cls_convs_2_0_bn_bias, ema_bbox_head_multi_level_cls_convs_2_0_bn_running_mean, ema_bbox_head_multi_level_cls_convs_2_0_bn_running_var, ema_bbox_head_multi_level_cls_convs_2_0_bn_num_batches_tracked, ema_bbox_head_multi_level_cls_convs_2_1_conv_weight, ema_bbox_head_multi_level_cls_convs_2_1_bn_weight, ema_bbox_head_multi_level_cls_convs_2_1_bn_bias, ema_bbox_head_multi_level_cls_convs_2_1_bn_running_mean, ema_bbox_head_multi_level_cls_convs_2_1_bn_running_var, ema_bbox_head_multi_level_cls_convs_2_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_0_0_conv_weight, ema_bbox_head_multi_level_reg_convs_0_0_bn_weight, ema_bbox_head_multi_level_reg_convs_0_0_bn_bias, ema_bbox_head_multi_level_reg_convs_0_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_0_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_0_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_0_1_conv_weight, ema_bbox_head_multi_level_reg_convs_0_1_bn_weight, ema_bbox_head_multi_level_reg_convs_0_1_bn_bias, ema_bbox_head_multi_level_reg_convs_0_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_0_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_0_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_1_0_conv_weight, ema_bbox_head_multi_level_reg_convs_1_0_bn_weight, ema_bbox_head_multi_level_reg_convs_1_0_bn_bias, ema_bbox_head_multi_level_reg_convs_1_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_1_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_1_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_1_1_conv_weight, ema_bbox_head_multi_level_reg_convs_1_1_bn_weight, ema_bbox_head_multi_level_reg_convs_1_1_bn_bias, ema_bbox_head_multi_level_reg_convs_1_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_1_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_1_1_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_2_0_conv_weight, ema_bbox_head_multi_level_reg_convs_2_0_bn_weight, ema_bbox_head_multi_level_reg_convs_2_0_bn_bias, ema_bbox_head_multi_level_reg_convs_2_0_bn_running_mean, ema_bbox_head_multi_level_reg_convs_2_0_bn_running_var, ema_bbox_head_multi_level_reg_convs_2_0_bn_num_batches_tracked, ema_bbox_head_multi_level_reg_convs_2_1_conv_weight, ema_bbox_head_multi_level_reg_convs_2_1_bn_weight, ema_bbox_head_multi_level_reg_convs_2_1_bn_bias, ema_bbox_head_multi_level_reg_convs_2_1_bn_running_mean, ema_bbox_head_multi_level_reg_convs_2_1_bn_running_var, ema_bbox_head_multi_level_reg_convs_2_1_bn_num_batches_tracked, ema_bbox_head_multi_level_conv_cls_0_weight, ema_bbox_head_multi_level_conv_cls_0_bias, ema_bbox_head_multi_level_conv_cls_1_weight, ema_bbox_head_multi_level_conv_cls_1_bias, ema_bbox_head_multi_level_conv_cls_2_weight, ema_bbox_head_multi_level_conv_cls_2_bias, ema_bbox_head_multi_level_conv_reg_0_weight, ema_bbox_head_multi_level_conv_reg_0_bias, ema_bbox_head_multi_level_conv_reg_1_weight, ema_bbox_head_multi_level_conv_reg_1_bias, ema_bbox_head_multi_level_conv_reg_2_weight, ema_bbox_head_multi_level_conv_reg_2_bias, ema_bbox_head_multi_level_conv_obj_0_weight, ema_bbox_head_multi_level_conv_obj_0_bias, ema_bbox_head_multi_level_conv_obj_1_weight, ema_bbox_head_multi_level_conv_obj_1_bias, ema_bbox_head_multi_level_conv_obj_2_weight, ema_bbox_head_multi_level_conv_obj_2_bias 12/17 16:55:48 - mmengine - INFO - Load checkpoint from ./data/downloads/pretrained/yolox_nano_lite/yolox_nano_lite_416x416_20220214_checkpoint.pth 12/17 16:55:48 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 12/17 16:55:48 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 12/17 16:55:48 - mmengine - INFO - Checkpoints will be saved to /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241217-165534/yolox_nano_lite/training. 12/17 16:55:48 - mmengine - INFO - No mosaic and mixup aug now! 12/17 16:55:48 - mmengine - INFO - Add additional L1 loss now! /home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/functional.py:513: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3609.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 12/17 16:55:56 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:55:56 - mmengine - INFO - Epoch(train) [1][50/50] base_lr: 8.0000e-05 lr: 8.0000e-05 eta: 0:01:53 time: 0.1624 data_time: 0.0163 memory: 1337 loss: 6.9276 loss_cls: 1.6174 loss_bbox: 2.4908 loss_obj: 2.0069 loss_l1: 0.8125 12/17 16:55:56 - mmengine - INFO - Saving checkpoint at 1 epochs 12/17 16:55:59 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.80s). Accumulating evaluation results... DONE (t=0.11s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.132 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.249 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.121 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.107 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.449 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.189 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.189 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.189 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.011 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.210 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.571 12/17 16:56:00 - mmengine - INFO - bbox_mAP_copypaste: 0.132 0.249 0.121 0.004 0.107 0.449 12/17 16:56:00 - mmengine - INFO - Epoch(val) [1][14/14] coco/bbox_mAP: 0.1320 coco/bbox_mAP_50: 0.2490 coco/bbox_mAP_75: 0.1210 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.1070 coco/bbox_mAP_l: 0.4490 data_time: 0.0183 time: 0.0435 12/17 16:56:07 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:07 - mmengine - INFO - Epoch(train) [2][50/50] base_lr: 3.2000e-04 lr: 3.2000e-04 eta: 0:01:36 time: 0.1332 data_time: 0.0147 memory: 1094 loss: 5.7837 loss_cls: 0.8748 loss_bbox: 2.5140 loss_obj: 1.6313 loss_l1: 0.7636 12/17 16:56:07 - mmengine - INFO - Saving checkpoint at 2 epochs 12/17 16:56:09 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.89s). Accumulating evaluation results... DONE (t=0.14s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.139 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.263 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.129 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.113 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.515 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.199 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.199 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.199 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.019 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.234 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.601 12/17 16:56:10 - mmengine - INFO - bbox_mAP_copypaste: 0.139 0.263 0.129 0.004 0.113 0.515 12/17 16:56:10 - mmengine - INFO - Epoch(val) [2][14/14] coco/bbox_mAP: 0.1390 coco/bbox_mAP_50: 0.2630 coco/bbox_mAP_75: 0.1290 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.1130 coco/bbox_mAP_l: 0.5150 data_time: 0.0087 time: 0.0299 12/17 16:56:17 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:17 - mmengine - INFO - Epoch(train) [3][50/50] base_lr: 7.2000e-04 lr: 7.2000e-04 eta: 0:01:25 time: 0.1303 data_time: 0.0145 memory: 1094 loss: 5.5659 loss_cls: 0.7354 loss_bbox: 2.5761 loss_obj: 1.4968 loss_l1: 0.7576 12/17 16:56:17 - mmengine - INFO - Saving checkpoint at 3 epochs 12/17 16:56:19 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.56s). Accumulating evaluation results... DONE (t=0.08s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.140 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.269 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.131 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.112 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.511 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.200 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.200 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.200 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.021 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.236 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.591 12/17 16:56:20 - mmengine - INFO - bbox_mAP_copypaste: 0.140 0.269 0.131 0.004 0.112 0.511 12/17 16:56:20 - mmengine - INFO - Epoch(val) [3][14/14] coco/bbox_mAP: 0.1400 coco/bbox_mAP_50: 0.2690 coco/bbox_mAP_75: 0.1310 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.1120 coco/bbox_mAP_l: 0.5110 data_time: 0.0087 time: 0.0292 12/17 16:56:26 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:26 - mmengine - INFO - Epoch(train) [4][50/50] base_lr: 1.2800e-03 lr: 1.2800e-03 eta: 0:01:14 time: 0.1194 data_time: 0.0147 memory: 609 loss: 5.6082 loss_cls: 0.7181 loss_bbox: 2.6776 loss_obj: 1.4421 loss_l1: 0.7704 12/17 16:56:26 - mmengine - INFO - Saving checkpoint at 4 epochs 12/17 16:56:28 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.56s). Accumulating evaluation results... DONE (t=0.08s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.115 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.257 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.089 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.100 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.453 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.018 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.213 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.550 12/17 16:56:29 - mmengine - INFO - bbox_mAP_copypaste: 0.115 0.257 0.089 0.004 0.100 0.453 12/17 16:56:29 - mmengine - INFO - Epoch(val) [4][14/14] coco/bbox_mAP: 0.1150 coco/bbox_mAP_50: 0.2570 coco/bbox_mAP_75: 0.0890 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.1000 coco/bbox_mAP_l: 0.4530 data_time: 0.0084 time: 0.0279 12/17 16:56:36 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:36 - mmengine - INFO - Epoch(train) [5][50/50] base_lr: 2.0000e-03 lr: 2.0000e-03 eta: 0:01:08 time: 0.1401 data_time: 0.0145 memory: 1320 loss: 5.3090 loss_cls: 0.6865 loss_bbox: 2.4785 loss_obj: 1.4186 loss_l1: 0.7254 12/17 16:56:36 - mmengine - INFO - Saving checkpoint at 5 epochs 12/17 16:56:38 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.73s). Accumulating evaluation results... DONE (t=0.11s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.123 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.259 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.117 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.003 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.105 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.486 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.013 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.212 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.568 12/17 16:56:39 - mmengine - INFO - bbox_mAP_copypaste: 0.123 0.259 0.117 0.003 0.105 0.486 12/17 16:56:39 - mmengine - INFO - Epoch(val) [5][14/14] coco/bbox_mAP: 0.1230 coco/bbox_mAP_50: 0.2590 coco/bbox_mAP_75: 0.1170 coco/bbox_mAP_s: 0.0030 coco/bbox_mAP_m: 0.1050 coco/bbox_mAP_l: 0.4860 data_time: 0.0084 time: 0.0282 12/17 16:56:46 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:46 - mmengine - INFO - Epoch(train) [6][50/50] base_lr: 1.9843e-03 lr: 1.9843e-03 eta: 0:01:01 time: 0.1341 data_time: 0.0149 memory: 1325 loss: 5.3557 loss_cls: 0.6781 loss_bbox: 2.5510 loss_obj: 1.3934 loss_l1: 0.7332 12/17 16:56:46 - mmengine - INFO - Saving checkpoint at 6 epochs 12/17 16:56:48 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.50s). Accumulating evaluation results... DONE (t=0.08s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.120 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.256 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.102 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.097 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.470 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.176 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.176 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.176 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.008 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.205 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.565 12/17 16:56:49 - mmengine - INFO - bbox_mAP_copypaste: 0.120 0.256 0.102 0.004 0.097 0.470 12/17 16:56:49 - mmengine - INFO - Epoch(val) [6][14/14] coco/bbox_mAP: 0.1200 coco/bbox_mAP_50: 0.2560 coco/bbox_mAP_75: 0.1020 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.0970 coco/bbox_mAP_l: 0.4700 data_time: 0.0090 time: 0.0294 12/17 16:56:56 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:56:56 - mmengine - INFO - Epoch(train) [7][50/50] base_lr: 1.9364e-03 lr: 1.9364e-03 eta: 0:00:54 time: 0.1306 data_time: 0.0149 memory: 1215 loss: 5.2018 loss_cls: 0.6615 loss_bbox: 2.4991 loss_obj: 1.3394 loss_l1: 0.7018 12/17 16:56:56 - mmengine - INFO - Saving checkpoint at 7 epochs 12/17 16:56:58 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.88s). Accumulating evaluation results... DONE (t=0.13s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.124 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.253 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.114 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.002 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.091 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.490 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.179 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.024 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.195 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.547 12/17 16:56:59 - mmengine - INFO - bbox_mAP_copypaste: 0.124 0.253 0.114 0.002 0.091 0.490 12/17 16:56:59 - mmengine - INFO - Epoch(val) [7][14/14] coco/bbox_mAP: 0.1240 coco/bbox_mAP_50: 0.2530 coco/bbox_mAP_75: 0.1140 coco/bbox_mAP_s: 0.0020 coco/bbox_mAP_m: 0.0910 coco/bbox_mAP_l: 0.4900 data_time: 0.0089 time: 0.0292 12/17 16:57:05 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:05 - mmengine - INFO - Epoch(train) [8][50/50] base_lr: 1.8586e-03 lr: 1.8586e-03 eta: 0:00:47 time: 0.1270 data_time: 0.0152 memory: 1090 loss: 5.1525 loss_cls: 0.6580 loss_bbox: 2.5073 loss_obj: 1.2839 loss_l1: 0.7032 12/17 16:57:05 - mmengine - INFO - Saving checkpoint at 8 epochs 12/17 16:57:08 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.57s). Accumulating evaluation results... DONE (t=0.09s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.135 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.282 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.117 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.122 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.501 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.190 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.190 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.190 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.016 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.232 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.558 12/17 16:57:09 - mmengine - INFO - bbox_mAP_copypaste: 0.135 0.282 0.117 0.005 0.122 0.501 12/17 16:57:09 - mmengine - INFO - Epoch(val) [8][14/14] coco/bbox_mAP: 0.1350 coco/bbox_mAP_50: 0.2820 coco/bbox_mAP_75: 0.1170 coco/bbox_mAP_s: 0.0050 coco/bbox_mAP_m: 0.1220 coco/bbox_mAP_l: 0.5010 data_time: 0.0083 time: 0.0286 12/17 16:57:15 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:15 - mmengine - INFO - Epoch(train) [9][50/50] base_lr: 1.7542e-03 lr: 1.7542e-03 eta: 0:00:40 time: 0.1232 data_time: 0.0146 memory: 1089 loss: 5.2235 loss_cls: 0.6729 loss_bbox: 2.5531 loss_obj: 1.2935 loss_l1: 0.7039 12/17 16:57:15 - mmengine - INFO - Saving checkpoint at 9 epochs 12/17 16:57:17 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.71s). Accumulating evaluation results... DONE (t=0.11s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.120 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.267 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.101 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.113 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.465 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.183 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.183 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.183 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.019 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.234 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.535 12/17 16:57:18 - mmengine - INFO - bbox_mAP_copypaste: 0.120 0.267 0.101 0.005 0.113 0.465 12/17 16:57:18 - mmengine - INFO - Epoch(val) [9][14/14] coco/bbox_mAP: 0.1200 coco/bbox_mAP_50: 0.2670 coco/bbox_mAP_75: 0.1010 coco/bbox_mAP_s: 0.0050 coco/bbox_mAP_m: 0.1130 coco/bbox_mAP_l: 0.4650 data_time: 0.0087 time: 0.0283 12/17 16:57:25 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:25 - mmengine - INFO - Epoch(train) [10][50/50] base_lr: 1.6277e-03 lr: 1.6277e-03 eta: 0:00:33 time: 0.1284 data_time: 0.0145 memory: 1094 loss: 5.2149 loss_cls: 0.6809 loss_bbox: 2.5414 loss_obj: 1.2870 loss_l1: 0.7056 12/17 16:57:25 - mmengine - INFO - Saving checkpoint at 10 epochs 12/17 16:57:27 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.67s). Accumulating evaluation results... DONE (t=0.10s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.121 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.256 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.099 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.004 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.093 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.498 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.184 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.184 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.184 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.024 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.572 12/17 16:57:28 - mmengine - INFO - bbox_mAP_copypaste: 0.121 0.256 0.099 0.004 0.093 0.498 12/17 16:57:28 - mmengine - INFO - Epoch(val) [10][14/14] coco/bbox_mAP: 0.1210 coco/bbox_mAP_50: 0.2560 coco/bbox_mAP_75: 0.0990 coco/bbox_mAP_s: 0.0040 coco/bbox_mAP_m: 0.0930 coco/bbox_mAP_l: 0.4980 data_time: 0.0089 time: 0.0296 12/17 16:57:34 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:34 - mmengine - INFO - Epoch(train) [11][50/50] base_lr: 1.4847e-03 lr: 1.4847e-03 eta: 0:00:26 time: 0.1259 data_time: 0.0150 memory: 1083 loss: 5.0543 loss_cls: 0.6510 loss_bbox: 2.5018 loss_obj: 1.2199 loss_l1: 0.6815 12/17 16:57:34 - mmengine - INFO - Saving checkpoint at 11 epochs 12/17 16:57:37 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.60s). Accumulating evaluation results... DONE (t=0.09s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.139 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.278 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.124 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.006 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.119 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.544 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.196 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.196 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.196 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.029 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.231 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.606 12/17 16:57:37 - mmengine - INFO - bbox_mAP_copypaste: 0.139 0.278 0.124 0.006 0.119 0.544 12/17 16:57:37 - mmengine - INFO - Epoch(val) [11][14/14] coco/bbox_mAP: 0.1390 coco/bbox_mAP_50: 0.2780 coco/bbox_mAP_75: 0.1240 coco/bbox_mAP_s: 0.0060 coco/bbox_mAP_m: 0.1190 coco/bbox_mAP_l: 0.5440 data_time: 0.0087 time: 0.0285 12/17 16:57:44 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:44 - mmengine - INFO - Epoch(train) [12][50/50] base_lr: 1.3315e-03 lr: 1.3315e-03 eta: 0:00:19 time: 0.1277 data_time: 0.0145 memory: 1201 loss: 5.0301 loss_cls: 0.6456 loss_bbox: 2.4941 loss_obj: 1.2136 loss_l1: 0.6768 12/17 16:57:44 - mmengine - INFO - Saving checkpoint at 12 epochs 12/17 16:57:46 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.01s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.71s). Accumulating evaluation results... DONE (t=0.11s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.146 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.306 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.129 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.147 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.505 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.203 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.203 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.203 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.031 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.260 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.552 12/17 16:57:47 - mmengine - INFO - bbox_mAP_copypaste: 0.146 0.306 0.129 0.005 0.147 0.505 12/17 16:57:47 - mmengine - INFO - Epoch(val) [12][14/14] coco/bbox_mAP: 0.1460 coco/bbox_mAP_50: 0.3060 coco/bbox_mAP_75: 0.1290 coco/bbox_mAP_s: 0.0050 coco/bbox_mAP_m: 0.1470 coco/bbox_mAP_l: 0.5050 data_time: 0.0088 time: 0.0307 12/17 16:57:53 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:57:53 - mmengine - INFO - Epoch(train) [13][50/50] base_lr: 1.1747e-03 lr: 1.1747e-03 eta: 0:00:13 time: 0.1272 data_time: 0.0147 memory: 992 loss: 4.8668 loss_cls: 0.6273 loss_bbox: 2.4190 loss_obj: 1.1695 loss_l1: 0.6510 12/17 16:57:53 - mmengine - INFO - Saving checkpoint at 13 epochs 12/17 16:57:56 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.61s). Accumulating evaluation results... DONE (t=0.10s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.161 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.317 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.144 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.006 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.164 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.574 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.216 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.216 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.216 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.022 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.279 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.635 12/17 16:57:57 - mmengine - INFO - bbox_mAP_copypaste: 0.161 0.317 0.144 0.006 0.164 0.574 12/17 16:57:57 - mmengine - INFO - Epoch(val) [13][14/14] coco/bbox_mAP: 0.1610 coco/bbox_mAP_50: 0.3170 coco/bbox_mAP_75: 0.1440 coco/bbox_mAP_s: 0.0060 coco/bbox_mAP_m: 0.1640 coco/bbox_mAP_l: 0.5740 data_time: 0.0086 time: 0.0285 12/17 16:58:03 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:58:03 - mmengine - INFO - Epoch(train) [14][50/50] base_lr: 1.0212e-03 lr: 1.0212e-03 eta: 0:00:06 time: 0.1358 data_time: 0.0149 memory: 1336 loss: 4.7083 loss_cls: 0.6216 loss_bbox: 2.3221 loss_obj: 1.1408 loss_l1: 0.6237 12/17 16:58:03 - mmengine - INFO - Saving checkpoint at 14 epochs 12/17 16:58:06 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.10s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.60s). Accumulating evaluation results... DONE (t=0.09s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.160 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.310 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.142 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.164 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.022 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.272 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.610 12/17 16:58:07 - mmengine - INFO - bbox_mAP_copypaste: 0.160 0.310 0.142 0.005 0.164 0.552 12/17 16:58:07 - mmengine - INFO - Epoch(val) [14][14/14] coco/bbox_mAP: 0.1600 coco/bbox_mAP_50: 0.3100 coco/bbox_mAP_75: 0.1420 coco/bbox_mAP_s: 0.0050 coco/bbox_mAP_m: 0.1640 coco/bbox_mAP_l: 0.5520 data_time: 0.0086 time: 0.0279 12/17 16:58:13 - mmengine - INFO - Exp name: yolox_nano_lite_20241217_165538 12/17 16:58:13 - mmengine - INFO - Epoch(train) [15][50/50] base_lr: 8.7772e-04 lr: 8.7772e-04 eta: 0:00:00 time: 0.1264 data_time: 0.0150 memory: 1094 loss: 4.8821 loss_cls: 0.6271 loss_bbox: 2.4404 loss_obj: 1.1629 loss_l1: 0.6517 12/17 16:58:13 - mmengine - INFO - Saving checkpoint at 15 epochs 12/17 16:58:15 - mmengine - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.58s). Accumulating evaluation results... DONE (t=0.09s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.161 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.313 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.150 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.157 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.573 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.214 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.021 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.270 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.622 12/17 16:58:16 - mmengine - INFO - bbox_mAP_copypaste: 0.161 0.313 0.150 0.005 0.157 0.573 12/17 16:58:16 - mmengine - INFO - Epoch(val) [15][14/14] coco/bbox_mAP: 0.1610 coco/bbox_mAP_50: 0.3130 coco/bbox_mAP_75: 0.1500 coco/bbox_mAP_s: 0.0050 coco/bbox_mAP_m: 0.1570 coco/bbox_mAP_l: 0.5730 data_time: 0.0086 time: 0.0289 12/17 16:58:17 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. 12/17 16:58:17 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "mmdet_tasks" registry tree. As a workaround, the current "mmdet_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. 12/17 16:58:17 - mmengine - WARNING - DeprecationWarning: get_onnx_config will be deprecated in the future. 12/17 16:58:17 - mmengine - INFO - Export PyTorch model to ONNX: /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241217-165534/yolox_nano_lite/training/model.onnx. [rank0]: Traceback (most recent call last): [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/tools/train.py", line 290, in [rank0]: main() [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/tools/train.py", line 265, in main [rank0]: torch2onnx(img='../edgeai-mmdetection/demo/demo.jpg', work_dir=cfg.work_dir, save_file=save_file, model_cfg = cfg, \ [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 356, in _wrap [rank0]: return self.call_function(func_name_, *args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 326, in call_function [rank0]: return self.call_function_local(func_name, *args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 275, in call_function_local [rank0]: return pipe_caller(*args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 107, in __call__ [rank0]: ret = func(*args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/pytorch2onnx.py", line 122, in torch2onnx [rank0]: export( [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 356, in _wrap [rank0]: return self.call_function(func_name_, *args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 326, in call_function [rank0]: return self.call_function_local(func_name, *args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 275, in call_function_local [rank0]: return pipe_caller(*args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/core/pipeline_manager.py", line 107, in __call__ [rank0]: ret = func(*args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/onnx/export.py", line 159, in export [rank0]: torch.onnx.export( [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/utils.py", line 551, in export [rank0]: _export( [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1648, in _export [rank0]: graph, params_dict, torch_out = _model_to_graph( [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/onnx/optimizer.py", line 27, in model_to_graph__custom_optimizer [rank0]: graph, params_dict, torch_out = ctx.origin_func(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1170, in _model_to_graph [rank0]: graph, params, torch_out, module = _create_jit_graph(model, args) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/utils.py", line 1046, in _create_jit_graph [rank0]: graph, torch_out = _trace_and_get_graph_from_model(model, args) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/utils.py", line 950, in _trace_and_get_graph_from_model [rank0]: trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph( [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/jit/_trace.py", line 1497, in _get_trace_graph [rank0]: outs = ONNXTracedModule( [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/jit/_trace.py", line 141, in forward [rank0]: graph, out = torch._C._create_graph_by_tracing( [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/jit/_trace.py", line 132, in wrapper [rank0]: outs.append(self.inner(*trace_inputs)) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/apis/onnx/export.py", line 124, in wrapper [rank0]: return forward(*arg, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward [rank0]: else self._run_ddp_forward(*inputs, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward [rank0]: return self.module(*inputs, **kwargs) # type: ignore[index] [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/codebase/mmdet/models/detectors/single_stage.py", line 85, in single_stage_detector__forward [rank0]: return __forward_impl(self, batch_inputs, data_samples=data_samples) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/core/optimizers/function_marker.py", line 268, in g [rank0]: rets = f(*args, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdeploy/mmdeploy/codebase/mmdet/models/detectors/single_stage.py", line 21, in __forward_impl [rank0]: x = self.extract_feat(batch_inputs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/mmdet/models/detectors/single_stage.py", line 146, in extract_feat [rank0]: x = self.backbone(batch_inputs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/mmdet/models/backbones/csp_darknet.py", line 409, in forward [rank0]: x = layer(x) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/mmdet/models/backbones/csp_darknet.py", line 131, in forward [rank0]: x = self.conv_in(x) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/mmcv/cnn/bricks/conv_module.py", line 281, in forward [rank0]: x = self.conv(x) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1543, in _slow_forward [rank0]: result = self.forward(*input, **kwargs) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 458, in forward [rank0]: return self._conv_forward(input, self.weight, self.bias) [rank0]: File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 454, in _conv_forward [rank0]: return F.conv2d(input, weight, bias, self.stride, [rank0]: RuntimeError: Input type (torch.cuda.ByteTensor) and weight type (torch.FloatTensor) should be the same [rank0]:[W1217 16:58:18.756827059 ProcessGroupNCCL.cpp:1168] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator()) E1217 16:58:19.981000 140141325098496 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 53769) of binary: /home/cjet/.pyenv/versions/py310/bin/python3 Traceback (most recent call last): File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/./scripts/run_modelmaker.py", line 149, in main(config) File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/./scripts/run_modelmaker.py", line 88, in main model_runner.run() File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/runner.py", line 166, in run self.model_training.run() File "/home/cjet/桌面/ti/edgeai-tensorlab/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/training/edgeai_mmdetection/detection.py", line 446, in run distributed_launch.main() File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/typing_extensions.py", line 2499, in wrapper return arg(*args, **kwargs) File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/distributed/launch.py", line 204, in main launch(args) File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/distributed/launch.py", line 189, in launch run(args) File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/home/cjet/.pyenv/versions/py310/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /home/cjet/桌面/ti/edgeai-tensorlab/edgeai-mmdetection/tools/train.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2024-12-17_16:58:19 host : cjet-B560M-HDV-A-R2-0 rank : 0 (local_rank: 0) exitcode : 1 (pid: 53769) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================