(py310) zxb@zxb-virtual-machine:~/Desktop/ti/edgeai-modelmaker$ ./run_modelmaker.sh AM62A ./config_detection.yaml Number of AVX cores detected in PC: 4 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'] --------------------------------------------------------------------- Run Name: 20241203-142720/yolox_nano_lite - Model: yolox_nano_lite - TargetDevices & Estimated Inference Times (ms): {'TDA4VM': 3.74, 'AM62A': 8.87, '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! Run params is at: /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/run.yaml /home/zxb/Desktop/ti/edgeai-mmdetection/mmdet/utils/setup_env.py:32: 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/zxb/Desktop/ti/edgeai-mmdetection/mmdet/utils/setup_env.py:42: 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( 2024-12-03 14:27:30,447 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.10.15 (main, Nov 25 2024, 21:41:02) [GCC 11.4.0] CUDA available: False GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 PyTorch: 2.0.1+cpu 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 v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -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 -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, USE_CUDA=0, USE_CUDNN=OFF, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.15.2+cpu OpenCV: 4.10.0 MMCV: 1.4.8 MMCV Compiler: GCC 11.4 MMCV CUDA Compiler: not available MMDetection: 2.22.0+b4e9b7f ------------------------------------------------------------ 2024-12-03 14:27:31,215 - mmdet - INFO - Distributed training: False 2024-12-03 14:27:31,988 - mmdet - INFO - Config: dataset_type = 'CocoDataset' data_root = '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset' data = dict( samples_per_gpu=8, workers_per_gpu=2, train=dict( type='MultiImageMixDataset', dataset=dict( type='ModelMakerDataset', ann_file= '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_train.json', img_prefix= '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/train', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True) ], filter_empty_gt=False, classes=['human', 'trafficsign', 'vehicle']), pipeline=[ dict(type='Mosaic', img_scale=(416, 416), pad_val=114.0), dict( type='RandomAffine', scaling_ratio_range=(0.5, 1.5), border=(-208, -208)), dict( type='MixUp', img_scale=(416, 416), ratio_range=(0.8, 1.6), pad_val=114.0), dict(type='YOLOXHSVRandomAug'), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Resize', img_scale=(416, 416), keep_ratio=True), dict( type='Pad', pad_to_square=True, pad_val=dict(img=(114.0, 114.0, 114.0))), dict( type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ]), val=dict( type='ModelMakerDataset', ann_file= '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/annotations/instances_val.json', img_prefix= '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/dataset/val', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(416, 416), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Pad', pad_to_square=True, pad_val=dict(img=(114.0, 114.0, 114.0))), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ], classes=['human', 'trafficsign', 'vehicle']), test=dict( type='CocoDataset', ann_file='data/coco/annotations/instances_val2017.json', img_prefix='data/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(416, 416), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Pad', pad_to_square=True, pad_val=dict(img=(114.0, 114.0, 114.0))), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ]), persistent_workers=True) evaluation = dict(interval=1, metric='bbox') cudnn_benchmark = True resize_with_scale_factor = True max_epochs = 300 num_last_epochs = 15 interval = 10 dist_params = dict(backend='nccl') log_level = 'INFO' load_from = './data/downloads/pretrained/yolox_nano_lite/yolox_nano_lite_416x416_20220214_checkpoint.pth' resume_from = None workflow = [('train', 1)] print_model_complexity = True optimizer = dict( type='SGD', lr=0.002, momentum=0.9, weight_decay=0.0005, nesterov=True, paramwise_cfg=dict(norm_decay_mult=0.0, bias_decay_mult=0.0)) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='YOLOX', warmup='exp', by_epoch=False, warmup_by_epoch=True, warmup_ratio=1, warmup_iters=1, num_last_epochs=5, min_lr_ratio=0.05) runner = dict(type='EpochBasedRunner', max_epochs=1) custom_hooks = [ dict(type='YOLOXModeSwitchHook', num_last_epochs=15, priority=48), dict(type='SyncNormHook', num_last_epochs=15, interval=10, priority=48), dict( type='ExpMomentumEMAHook', resume_from=None, momentum=0.0001, priority=49) ] checkpoint_config = dict(interval=10) log_config = dict(interval=100, hooks=[dict(type='TextLoggerHook')]) img_scale = (416, 416) input_size = (416, 416) samples_per_gpu = 16 num_classes_dict = dict( CocoDataset=80, VOCDataset=20, CityscapesDataset=8, WIDERFaceDataset=1) dataset_root_dict = dict( CocoDataset='data/coco/', VOCDataset='data/VOCdevkit/', CityscapesDataset='data/cityscapes/', WIDERFaceDataset='data/WIDERFace/') num_classes = 80 img_norm_cfg = dict(mean=[0.0, 0.0, 0.0], std=[1.0, 1.0, 1.0], to_rgb=False) convert_to_lite_model = dict(group_size_dw=None) quantize = False initial_learning_rate = 0.01 model = dict( type='YOLOX', input_size=(416, 416), random_size_range=(10, 20), random_size_interval=10, backbone=dict( type='CSPDarknet', deepen_factor=0.33, widen_factor=0.25, use_depthwise=False), neck=dict( type='YOLOXPAFPN', in_channels=[64, 128, 256], out_channels=64, num_csp_blocks=1, use_depthwise=False), bbox_head=dict( type='YOLOXHead', num_classes=3, in_channels=64, feat_channels=64, use_depthwise=False), train_cfg=dict(assigner=dict(type='SimOTAAssigner', center_radius=2.5)), test_cfg=dict(score_thr=0.01, nms=dict(type='nms', iou_threshold=0.65))) train_pipeline = [ dict(type='Mosaic', img_scale=(416, 416), pad_val=114.0), dict( type='RandomAffine', scaling_ratio_range=(0.5, 1.5), border=(-208, -208)), dict( type='MixUp', img_scale=(416, 416), ratio_range=(0.8, 1.6), pad_val=114.0), dict(type='YOLOXHSVRandomAug'), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Resize', img_scale=(416, 416), keep_ratio=True), dict( type='Pad', pad_to_square=True, pad_val=dict(img=(114.0, 114.0, 114.0))), dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(416, 416), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Pad', pad_to_square=True, pad_val=dict(img=(114.0, 114.0, 114.0))), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img']) ]) ] work_dir = '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/training' total_epochs = 1 export_model = True auto_resume = False gpu_ids = [0] 2024-12-03 14:27:31,989 - mmdet - INFO - Set random seed to 1662312320, deterministic: False 2024-12-03 14:27:32,042 - mmdet - INFO - initialize CSPDarknet with init_cfg {'type': 'Kaiming', 'layer': 'Conv2d', 'a': 2.23606797749979, 'distribution': 'uniform', 'mode': 'fan_in', 'nonlinearity': 'leaky_relu'} 2024-12-03 14:27:32,055 - mmdet - INFO - initialize YOLOXPAFPN with init_cfg {'type': 'Kaiming', 'layer': 'Conv2d', 'a': 2.23606797749979, 'distribution': 'uniform', 'mode': 'fan_in', 'nonlinearity': 'leaky_relu'} 2024-12-03 14:27:32,067 - mmdet - INFO - initialize YOLOXHead with init_cfg {'type': 'Kaiming', 'layer': 'Conv2d', 'a': 2.23606797749979, 'distribution': 'uniform', 'mode': 'fan_in', 'nonlinearity': 'leaky_relu'} /home/zxb/.pyenv/versions/py310/lib/python3.10/site-packages/edgeai_torchmodelopt/xmodelopt/surgery/v1/convert_to_lite.py:166: UserWarning: WARNING - xnn.surgery is based on the modules. For superior functionality, please use the torch.fx based xmodelopt.surgery instead warnings.warn("WARNING - xnn.surgery is based on the modules. For superior functionality, please use the torch.fx based xmodelopt.surgery instead") 2024-12-03 14:27:32,264 - mmdet - INFO - ========================================================================================================= Layer (type:depth-idx) Output Shape Param # ========================================================================================================= YOLOX [1, 3, 52, 52] -- ├─CSPDarknet: 1-1 [1, 64, 52, 52] -- │ └─FocusLite: 2-1 [1, 16, 208, 208] -- │ │ └─ConvModule: 3-1 [1, 12, 208, 208] -- │ │ │ └─Conv2d: 4-1 [1, 12, 208, 208] 324 │ │ │ └─BatchNorm2d: 4-2 [1, 12, 208, 208] 24 │ │ └─ConvModule: 3-2 [1, 16, 208, 208] -- │ │ │ └─Conv2d: 4-3 [1, 16, 208, 208] 1,728 │ │ │ └─BatchNorm2d: 4-4 [1, 16, 208, 208] 32 │ │ │ └─ReLU: 4-5 [1, 16, 208, 208] -- │ └─Sequential: 2-2 [1, 32, 104, 104] -- │ │ └─ConvModule: 3-3 [1, 32, 104, 104] -- │ │ │ └─Conv2d: 4-6 [1, 32, 104, 104] 4,608 │ │ │ └─BatchNorm2d: 4-7 [1, 32, 104, 104] 64 │ │ │ └─ReLU: 4-8 [1, 32, 104, 104] -- │ │ └─CSPLayer: 3-4 [1, 32, 104, 104] -- │ │ │ └─ConvModule: 4-9 [1, 16, 104, 104] -- │ │ │ │ └─Conv2d: 5-1 [1, 16, 104, 104] 512 │ │ │ │ └─BatchNorm2d: 5-2 [1, 16, 104, 104] 32 │ │ │ │ └─ReLU: 5-3 [1, 16, 104, 104] -- │ │ │ └─ConvModule: 4-10 [1, 16, 104, 104] -- │ │ │ │ └─Conv2d: 5-4 [1, 16, 104, 104] 512 │ │ │ │ └─BatchNorm2d: 5-5 [1, 16, 104, 104] 32 │ │ │ │ └─ReLU: 5-6 [1, 16, 104, 104] -- │ │ │ └─Sequential: 4-11 [1, 16, 104, 104] -- │ │ │ │ └─DarknetBottleneck: 5-7 [1, 16, 104, 104] -- │ │ │ │ │ └─ConvModule: 6-1 [1, 16, 104, 104] -- │ │ │ │ │ │ └─Conv2d: 7-1 [1, 16, 104, 104] 256 │ │ │ │ │ │ └─BatchNorm2d: 7-2 [1, 16, 104, 104] 32 │ │ │ │ │ │ └─ReLU: 7-3 [1, 16, 104, 104] -- │ │ │ │ │ └─ConvModule: 6-2 [1, 16, 104, 104] -- │ │ │ │ │ │ └─Conv2d: 7-4 [1, 16, 104, 104] 2,304 │ │ │ │ │ │ └─BatchNorm2d: 7-5 [1, 16, 104, 104] 32 │ │ │ │ │ │ └─ReLU: 7-6 [1, 16, 104, 104] -- │ │ │ └─ConvModule: 4-12 [1, 32, 104, 104] -- │ │ │ │ └─Conv2d: 5-8 [1, 32, 104, 104] 1,024 │ │ │ │ └─BatchNorm2d: 5-9 [1, 32, 104, 104] 64 │ │ │ │ └─ReLU: 5-10 [1, 32, 104, 104] -- │ └─Sequential: 2-3 [1, 64, 52, 52] -- │ │ └─ConvModule: 3-5 [1, 64, 52, 52] -- │ │ │ └─Conv2d: 4-13 [1, 64, 52, 52] 18,432 │ │ │ └─BatchNorm2d: 4-14 [1, 64, 52, 52] 128 │ │ │ └─ReLU: 4-15 [1, 64, 52, 52] -- │ │ └─CSPLayer: 3-6 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-16 [1, 32, 52, 52] -- │ │ │ │ └─Conv2d: 5-11 [1, 32, 52, 52] 2,048 │ │ │ │ └─BatchNorm2d: 5-12 [1, 32, 52, 52] 64 │ │ │ │ └─ReLU: 5-13 [1, 32, 52, 52] -- │ │ │ └─ConvModule: 4-17 [1, 32, 52, 52] -- │ │ │ │ └─Conv2d: 5-14 [1, 32, 52, 52] 2,048 │ │ │ │ └─BatchNorm2d: 5-15 [1, 32, 52, 52] 64 │ │ │ │ └─ReLU: 5-16 [1, 32, 52, 52] -- │ │ │ └─Sequential: 4-18 [1, 32, 52, 52] -- │ │ │ │ └─DarknetBottleneck: 5-17 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-3 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-7 [1, 32, 52, 52] 1,024 │ │ │ │ │ │ └─BatchNorm2d: 7-8 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-9 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-4 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-10 [1, 32, 52, 52] 9,216 │ │ │ │ │ │ └─BatchNorm2d: 7-11 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-12 [1, 32, 52, 52] -- │ │ │ │ └─DarknetBottleneck: 5-18 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-5 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-13 [1, 32, 52, 52] 1,024 │ │ │ │ │ │ └─BatchNorm2d: 7-14 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-15 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-6 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-16 [1, 32, 52, 52] 9,216 │ │ │ │ │ │ └─BatchNorm2d: 7-17 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-18 [1, 32, 52, 52] -- │ │ │ │ └─DarknetBottleneck: 5-19 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-7 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-19 [1, 32, 52, 52] 1,024 │ │ │ │ │ │ └─BatchNorm2d: 7-20 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-21 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-8 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-22 [1, 32, 52, 52] 9,216 │ │ │ │ │ │ └─BatchNorm2d: 7-23 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-24 [1, 32, 52, 52] -- │ │ │ └─ConvModule: 4-19 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-20 [1, 64, 52, 52] 4,096 │ │ │ │ └─BatchNorm2d: 5-21 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-22 [1, 64, 52, 52] -- │ └─Sequential: 2-4 [1, 128, 26, 26] -- │ │ └─ConvModule: 3-7 [1, 128, 26, 26] -- │ │ │ └─Conv2d: 4-20 [1, 128, 26, 26] 73,728 │ │ │ └─BatchNorm2d: 4-21 [1, 128, 26, 26] 256 │ │ │ └─ReLU: 4-22 [1, 128, 26, 26] -- │ │ └─CSPLayer: 3-8 [1, 128, 26, 26] -- │ │ │ └─ConvModule: 4-23 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-23 [1, 64, 26, 26] 8,192 │ │ │ │ └─BatchNorm2d: 5-24 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-25 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-24 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-26 [1, 64, 26, 26] 8,192 │ │ │ │ └─BatchNorm2d: 5-27 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-28 [1, 64, 26, 26] -- │ │ │ └─Sequential: 4-25 [1, 64, 26, 26] -- │ │ │ │ └─DarknetBottleneck: 5-29 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-9 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-25 [1, 64, 26, 26] 4,096 │ │ │ │ │ │ └─BatchNorm2d: 7-26 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-27 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-10 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-28 [1, 64, 26, 26] 36,864 │ │ │ │ │ │ └─BatchNorm2d: 7-29 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-30 [1, 64, 26, 26] -- │ │ │ │ └─DarknetBottleneck: 5-30 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-11 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-31 [1, 64, 26, 26] 4,096 │ │ │ │ │ │ └─BatchNorm2d: 7-32 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-33 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-12 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-34 [1, 64, 26, 26] 36,864 │ │ │ │ │ │ └─BatchNorm2d: 7-35 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-36 [1, 64, 26, 26] -- │ │ │ │ └─DarknetBottleneck: 5-31 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-13 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-37 [1, 64, 26, 26] 4,096 │ │ │ │ │ │ └─BatchNorm2d: 7-38 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-39 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-14 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-40 [1, 64, 26, 26] 36,864 │ │ │ │ │ │ └─BatchNorm2d: 7-41 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-42 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-26 [1, 128, 26, 26] -- │ │ │ │ └─Conv2d: 5-32 [1, 128, 26, 26] 16,384 │ │ │ │ └─BatchNorm2d: 5-33 [1, 128, 26, 26] 256 │ │ │ │ └─ReLU: 5-34 [1, 128, 26, 26] -- │ └─Sequential: 2-5 [1, 256, 13, 13] -- │ │ └─ConvModule: 3-9 [1, 256, 13, 13] -- │ │ │ └─Conv2d: 4-27 [1, 256, 13, 13] 294,912 │ │ │ └─BatchNorm2d: 4-28 [1, 256, 13, 13] 512 │ │ │ └─ReLU: 4-29 [1, 256, 13, 13] -- │ │ └─SPPBottleneck: 3-10 [1, 256, 13, 13] -- │ │ │ └─ConvModule: 4-30 [1, 128, 13, 13] -- │ │ │ │ └─Conv2d: 5-35 [1, 128, 13, 13] 32,768 │ │ │ │ └─BatchNorm2d: 5-36 [1, 128, 13, 13] 256 │ │ │ │ └─ReLU: 5-37 [1, 128, 13, 13] -- │ │ │ └─ModuleList: 4-31 -- -- │ │ │ │ └─SequentialMaxPool2d: 5-38 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-15 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-16 [1, 128, 13, 13] -- │ │ │ │ └─SequentialMaxPool2d: 5-39 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-17 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-18 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-19 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-20 [1, 128, 13, 13] -- │ │ │ │ └─SequentialMaxPool2d: 5-40 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-21 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-22 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-23 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-24 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-25 [1, 128, 13, 13] -- │ │ │ │ │ └─MaxPool2d: 6-26 [1, 128, 13, 13] -- │ │ │ └─ConvModule: 4-32 [1, 256, 13, 13] -- │ │ │ │ └─Conv2d: 5-41 [1, 256, 13, 13] 131,072 │ │ │ │ └─BatchNorm2d: 5-42 [1, 256, 13, 13] 512 │ │ │ │ └─ReLU: 5-43 [1, 256, 13, 13] -- │ │ └─CSPLayer: 3-11 [1, 256, 13, 13] -- │ │ │ └─ConvModule: 4-33 [1, 128, 13, 13] -- │ │ │ │ └─Conv2d: 5-44 [1, 128, 13, 13] 32,768 │ │ │ │ └─BatchNorm2d: 5-45 [1, 128, 13, 13] 256 │ │ │ │ └─ReLU: 5-46 [1, 128, 13, 13] -- │ │ │ └─ConvModule: 4-34 [1, 128, 13, 13] -- │ │ │ │ └─Conv2d: 5-47 [1, 128, 13, 13] 32,768 │ │ │ │ └─BatchNorm2d: 5-48 [1, 128, 13, 13] 256 │ │ │ │ └─ReLU: 5-49 [1, 128, 13, 13] -- │ │ │ └─Sequential: 4-35 [1, 128, 13, 13] -- │ │ │ │ └─DarknetBottleneck: 5-50 [1, 128, 13, 13] -- │ │ │ │ │ └─ConvModule: 6-27 [1, 128, 13, 13] -- │ │ │ │ │ │ └─Conv2d: 7-43 [1, 128, 13, 13] 16,384 │ │ │ │ │ │ └─BatchNorm2d: 7-44 [1, 128, 13, 13] 256 │ │ │ │ │ │ └─ReLU: 7-45 [1, 128, 13, 13] -- │ │ │ │ │ └─ConvModule: 6-28 [1, 128, 13, 13] -- │ │ │ │ │ │ └─Conv2d: 7-46 [1, 128, 13, 13] 147,456 │ │ │ │ │ │ └─BatchNorm2d: 7-47 [1, 128, 13, 13] 256 │ │ │ │ │ │ └─ReLU: 7-48 [1, 128, 13, 13] -- │ │ │ └─ConvModule: 4-36 [1, 256, 13, 13] -- │ │ │ │ └─Conv2d: 5-51 [1, 256, 13, 13] 65,536 │ │ │ │ └─BatchNorm2d: 5-52 [1, 256, 13, 13] 512 │ │ │ │ └─ReLU: 5-53 [1, 256, 13, 13] -- ├─YOLOXPAFPN: 1-2 [1, 64, 52, 52] -- │ └─ModuleList: 2-9 -- (recursive) │ │ └─ConvModule: 3-12 [1, 128, 13, 13] -- │ │ │ └─Conv2d: 4-37 [1, 128, 13, 13] 32,768 │ │ │ └─BatchNorm2d: 4-38 [1, 128, 13, 13] 256 │ │ │ └─ReLU: 4-39 [1, 128, 13, 13] -- │ └─Upsample: 2-7 [1, 128, 26, 26] -- │ └─ModuleList: 2-11 -- (recursive) │ │ └─CSPLayer: 3-13 [1, 128, 26, 26] -- │ │ │ └─ConvModule: 4-40 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-54 [1, 64, 26, 26] 16,384 │ │ │ │ └─BatchNorm2d: 5-55 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-56 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-41 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-57 [1, 64, 26, 26] 16,384 │ │ │ │ └─BatchNorm2d: 5-58 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-59 [1, 64, 26, 26] -- │ │ │ └─Sequential: 4-42 [1, 64, 26, 26] -- │ │ │ │ └─DarknetBottleneck: 5-60 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-29 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-49 [1, 64, 26, 26] 4,096 │ │ │ │ │ │ └─BatchNorm2d: 7-50 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-51 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-30 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-52 [1, 64, 26, 26] 36,864 │ │ │ │ │ │ └─BatchNorm2d: 7-53 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-54 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-43 [1, 128, 26, 26] -- │ │ │ │ └─Conv2d: 5-61 [1, 128, 26, 26] 16,384 │ │ │ │ └─BatchNorm2d: 5-62 [1, 128, 26, 26] 256 │ │ │ │ └─ReLU: 5-63 [1, 128, 26, 26] -- │ └─ModuleList: 2-9 -- (recursive) │ │ └─ConvModule: 3-14 [1, 64, 26, 26] -- │ │ │ └─Conv2d: 4-44 [1, 64, 26, 26] 8,192 │ │ │ └─BatchNorm2d: 4-45 [1, 64, 26, 26] 128 │ │ │ └─ReLU: 4-46 [1, 64, 26, 26] -- │ └─Upsample: 2-10 [1, 64, 52, 52] -- │ └─ModuleList: 2-11 -- (recursive) │ │ └─CSPLayer: 3-15 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-47 [1, 32, 52, 52] -- │ │ │ │ └─Conv2d: 5-64 [1, 32, 52, 52] 4,096 │ │ │ │ └─BatchNorm2d: 5-65 [1, 32, 52, 52] 64 │ │ │ │ └─ReLU: 5-66 [1, 32, 52, 52] -- │ │ │ └─ConvModule: 4-48 [1, 32, 52, 52] -- │ │ │ │ └─Conv2d: 5-67 [1, 32, 52, 52] 4,096 │ │ │ │ └─BatchNorm2d: 5-68 [1, 32, 52, 52] 64 │ │ │ │ └─ReLU: 5-69 [1, 32, 52, 52] -- │ │ │ └─Sequential: 4-49 [1, 32, 52, 52] -- │ │ │ │ └─DarknetBottleneck: 5-70 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-31 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-55 [1, 32, 52, 52] 1,024 │ │ │ │ │ │ └─BatchNorm2d: 7-56 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-57 [1, 32, 52, 52] -- │ │ │ │ │ └─ConvModule: 6-32 [1, 32, 52, 52] -- │ │ │ │ │ │ └─Conv2d: 7-58 [1, 32, 52, 52] 9,216 │ │ │ │ │ │ └─BatchNorm2d: 7-59 [1, 32, 52, 52] 64 │ │ │ │ │ │ └─ReLU: 7-60 [1, 32, 52, 52] -- │ │ │ └─ConvModule: 4-50 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-71 [1, 64, 52, 52] 4,096 │ │ │ │ └─BatchNorm2d: 5-72 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-73 [1, 64, 52, 52] -- │ └─ModuleList: 2-14 -- (recursive) │ │ └─ConvModule: 3-16 [1, 64, 26, 26] -- │ │ │ └─Conv2d: 4-51 [1, 64, 26, 26] 36,864 │ │ │ └─BatchNorm2d: 4-52 [1, 64, 26, 26] 128 │ │ │ └─ReLU: 4-53 [1, 64, 26, 26] -- │ └─ModuleList: 2-15 -- (recursive) │ │ └─CSPLayer: 3-17 [1, 128, 26, 26] -- │ │ │ └─ConvModule: 4-54 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-74 [1, 64, 26, 26] 8,192 │ │ │ │ └─BatchNorm2d: 5-75 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-76 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-55 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-77 [1, 64, 26, 26] 8,192 │ │ │ │ └─BatchNorm2d: 5-78 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-79 [1, 64, 26, 26] -- │ │ │ └─Sequential: 4-56 [1, 64, 26, 26] -- │ │ │ │ └─DarknetBottleneck: 5-80 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-33 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-61 [1, 64, 26, 26] 4,096 │ │ │ │ │ │ └─BatchNorm2d: 7-62 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-63 [1, 64, 26, 26] -- │ │ │ │ │ └─ConvModule: 6-34 [1, 64, 26, 26] -- │ │ │ │ │ │ └─Conv2d: 7-64 [1, 64, 26, 26] 36,864 │ │ │ │ │ │ └─BatchNorm2d: 7-65 [1, 64, 26, 26] 128 │ │ │ │ │ │ └─ReLU: 7-66 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-57 [1, 128, 26, 26] -- │ │ │ │ └─Conv2d: 5-81 [1, 128, 26, 26] 16,384 │ │ │ │ └─BatchNorm2d: 5-82 [1, 128, 26, 26] 256 │ │ │ │ └─ReLU: 5-83 [1, 128, 26, 26] -- │ └─ModuleList: 2-14 -- (recursive) │ │ └─ConvModule: 3-18 [1, 128, 13, 13] -- │ │ │ └─Conv2d: 4-58 [1, 128, 13, 13] 147,456 │ │ │ └─BatchNorm2d: 4-59 [1, 128, 13, 13] 256 │ │ │ └─ReLU: 4-60 [1, 128, 13, 13] -- │ └─ModuleList: 2-15 -- (recursive) │ │ └─CSPLayer: 3-19 [1, 256, 13, 13] -- │ │ │ └─ConvModule: 4-61 [1, 128, 13, 13] -- │ │ │ │ └─Conv2d: 5-84 [1, 128, 13, 13] 32,768 │ │ │ │ └─BatchNorm2d: 5-85 [1, 128, 13, 13] 256 │ │ │ │ └─ReLU: 5-86 [1, 128, 13, 13] -- │ │ │ └─ConvModule: 4-62 [1, 128, 13, 13] -- │ │ │ │ └─Conv2d: 5-87 [1, 128, 13, 13] 32,768 │ │ │ │ └─BatchNorm2d: 5-88 [1, 128, 13, 13] 256 │ │ │ │ └─ReLU: 5-89 [1, 128, 13, 13] -- │ │ │ └─Sequential: 4-63 [1, 128, 13, 13] -- │ │ │ │ └─DarknetBottleneck: 5-90 [1, 128, 13, 13] -- │ │ │ │ │ └─ConvModule: 6-35 [1, 128, 13, 13] -- │ │ │ │ │ │ └─Conv2d: 7-67 [1, 128, 13, 13] 16,384 │ │ │ │ │ │ └─BatchNorm2d: 7-68 [1, 128, 13, 13] 256 │ │ │ │ │ │ └─ReLU: 7-69 [1, 128, 13, 13] -- │ │ │ │ │ └─ConvModule: 6-36 [1, 128, 13, 13] -- │ │ │ │ │ │ └─Conv2d: 7-70 [1, 128, 13, 13] 147,456 │ │ │ │ │ │ └─BatchNorm2d: 7-71 [1, 128, 13, 13] 256 │ │ │ │ │ │ └─ReLU: 7-72 [1, 128, 13, 13] -- │ │ │ └─ConvModule: 4-64 [1, 256, 13, 13] -- │ │ │ │ └─Conv2d: 5-91 [1, 256, 13, 13] 65,536 │ │ │ │ └─BatchNorm2d: 5-92 [1, 256, 13, 13] 512 │ │ │ │ └─ReLU: 5-93 [1, 256, 13, 13] -- │ └─ModuleList: 2-16 -- -- │ │ └─ConvModule: 3-20 [1, 64, 52, 52] -- │ │ │ └─Conv2d: 4-65 [1, 64, 52, 52] 4,096 │ │ │ └─BatchNorm2d: 4-66 [1, 64, 52, 52] 128 │ │ │ └─ReLU: 4-67 [1, 64, 52, 52] -- │ │ └─ConvModule: 3-21 [1, 64, 26, 26] -- │ │ │ └─Conv2d: 4-68 [1, 64, 26, 26] 8,192 │ │ │ └─BatchNorm2d: 4-69 [1, 64, 26, 26] 128 │ │ │ └─ReLU: 4-70 [1, 64, 26, 26] -- │ │ └─ConvModule: 3-22 [1, 64, 13, 13] -- │ │ │ └─Conv2d: 4-71 [1, 64, 13, 13] 16,384 │ │ │ └─BatchNorm2d: 4-72 [1, 64, 13, 13] 128 │ │ │ └─ReLU: 4-73 [1, 64, 13, 13] -- ├─YOLOXHead: 1-3 [1, 3, 52, 52] -- │ └─ModuleList: 2-27 -- (recursive) │ │ └─Sequential: 3-23 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-74 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-94 [1, 64, 52, 52] 36,864 │ │ │ │ └─BatchNorm2d: 5-95 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-96 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-75 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-97 [1, 64, 52, 52] 36,864 │ │ │ │ └─BatchNorm2d: 5-98 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-99 [1, 64, 52, 52] -- │ └─ModuleList: 2-28 -- (recursive) │ │ └─Sequential: 3-24 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-76 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-100 [1, 64, 52, 52] 36,864 │ │ │ │ └─BatchNorm2d: 5-101 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-102 [1, 64, 52, 52] -- │ │ │ └─ConvModule: 4-77 [1, 64, 52, 52] -- │ │ │ │ └─Conv2d: 5-103 [1, 64, 52, 52] 36,864 │ │ │ │ └─BatchNorm2d: 5-104 [1, 64, 52, 52] 128 │ │ │ │ └─ReLU: 5-105 [1, 64, 52, 52] -- │ └─ModuleList: 2-29 -- (recursive) │ │ └─Conv2d: 3-25 [1, 3, 52, 52] 195 │ └─ModuleList: 2-30 -- (recursive) │ │ └─Conv2d: 3-26 [1, 4, 52, 52] 260 │ └─ModuleList: 2-31 -- (recursive) │ │ └─Conv2d: 3-27 [1, 1, 52, 52] 65 │ └─ModuleList: 2-27 -- (recursive) │ │ └─Sequential: 3-28 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-78 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-106 [1, 64, 26, 26] 36,864 │ │ │ │ └─BatchNorm2d: 5-107 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-108 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-79 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-109 [1, 64, 26, 26] 36,864 │ │ │ │ └─BatchNorm2d: 5-110 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-111 [1, 64, 26, 26] -- │ └─ModuleList: 2-28 -- (recursive) │ │ └─Sequential: 3-29 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-80 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-112 [1, 64, 26, 26] 36,864 │ │ │ │ └─BatchNorm2d: 5-113 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-114 [1, 64, 26, 26] -- │ │ │ └─ConvModule: 4-81 [1, 64, 26, 26] -- │ │ │ │ └─Conv2d: 5-115 [1, 64, 26, 26] 36,864 │ │ │ │ └─BatchNorm2d: 5-116 [1, 64, 26, 26] 128 │ │ │ │ └─ReLU: 5-117 [1, 64, 26, 26] -- │ └─ModuleList: 2-29 -- (recursive) │ │ └─Conv2d: 3-30 [1, 3, 26, 26] 195 │ └─ModuleList: 2-30 -- (recursive) │ │ └─Conv2d: 3-31 [1, 4, 26, 26] 260 │ └─ModuleList: 2-31 -- (recursive) │ │ └─Conv2d: 3-32 [1, 1, 26, 26] 65 │ └─ModuleList: 2-27 -- (recursive) │ │ └─Sequential: 3-33 [1, 64, 13, 13] -- │ │ │ └─ConvModule: 4-82 [1, 64, 13, 13] -- │ │ │ │ └─Conv2d: 5-118 [1, 64, 13, 13] 36,864 │ │ │ │ └─BatchNorm2d: 5-119 [1, 64, 13, 13] 128 │ │ │ │ └─ReLU: 5-120 [1, 64, 13, 13] -- │ │ │ └─ConvModule: 4-83 [1, 64, 13, 13] -- │ │ │ │ └─Conv2d: 5-121 [1, 64, 13, 13] 36,864 │ │ │ │ └─BatchNorm2d: 5-122 [1, 64, 13, 13] 128 │ │ │ │ └─ReLU: 5-123 [1, 64, 13, 13] -- │ └─ModuleList: 2-28 -- (recursive) │ │ └─Sequential: 3-34 [1, 64, 13, 13] -- │ │ │ └─ConvModule: 4-84 [1, 64, 13, 13] -- │ │ │ │ └─Conv2d: 5-124 [1, 64, 13, 13] 36,864 │ │ │ │ └─BatchNorm2d: 5-125 [1, 64, 13, 13] 128 │ │ │ │ └─ReLU: 5-126 [1, 64, 13, 13] -- │ │ │ └─ConvModule: 4-85 [1, 64, 13, 13] -- │ │ │ │ └─Conv2d: 5-127 [1, 64, 13, 13] 36,864 │ │ │ │ └─BatchNorm2d: 5-128 [1, 64, 13, 13] 128 │ │ │ │ └─ReLU: 5-129 [1, 64, 13, 13] -- │ └─ModuleList: 2-29 -- (recursive) │ │ └─Conv2d: 3-35 [1, 3, 13, 13] 195 │ └─ModuleList: 2-30 -- (recursive) │ │ └─Conv2d: 3-36 [1, 4, 13, 13] 260 │ └─ModuleList: 2-31 -- (recursive) │ │ └─Conv2d: 3-37 [1, 1, 13, 13] 65 ========================================================================================================= Total params: 2,242,388 Trainable params: 2,242,388 Non-trainable params: 0 Total mult-adds (G): 1.45 ========================================================================================================= Input size (MB): 2.08 Forward/backward pass size (MB): 109.43 Params size (MB): 8.97 Estimated Total Size (MB): 120.47 ========================================================================================================= 2024-12-03 14:27:32,267 - mmdet - INFO - loading annotations into memory... Done (t=0.06s) creating index... index created! loading annotations into memory... Done (t=0.01s) creating index... index created! 2024-12-03 14:27:32,366 - mmdet - INFO - load checkpoint from local path: ./data/downloads/pretrained/yolox_nano_lite/yolox_nano_lite_416x416_20220214_checkpoint.pth 2024-12-03 14:27:32,444 - mmdet - WARNING - 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 2024-12-03 14:27:32,445 - mmdet - INFO - Start running, host: zxb@zxb-virtual-machine, work_dir: /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/training 2024-12-03 14:27:32,445 - mmdet - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) YOLOXLrUpdaterHook (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) YOLOXLrUpdaterHook (48 ) YOLOXModeSwitchHook (48 ) SyncNormHook (49 ) ExpMomentumEMAHook (LOW ) IterTimerHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) YOLOXLrUpdaterHook (LOW ) IterTimerHook (LOW ) EvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) IterTimerHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (48 ) SyncNormHook (49 ) ExpMomentumEMAHook (NORMAL ) CheckpointHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook -------------------- after_run: (VERY_LOW ) TextLoggerHook -------------------- 2024-12-03 14:27:32,446 - mmdet - INFO - workflow: [('train', 1)], max: 1 epochs 2024-12-03 14:27:32,453 - mmdet - INFO - Checkpoints will be saved to /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/training by HardDiskBackend. /home/zxb/.pyenv/versions/py310/lib/python3.10/site-packages/torch/functional.py:504: 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:3483.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 2024-12-03 14:28:32,734 - mmdet - INFO - Saving checkpoint at 1 epochs [ ] 0/107, elapsed: 0s, ETA:/home/zxb/Desktop/ti/edgeai-mmdetection/mmdet/models/dense_heads/yolox_head.py:307: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:245.) flatten_bboxes[..., :4] /= flatten_bboxes.new_tensor( [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 107/107, 18.6 task/s, elapsed: 6s, ETA: 0s2024-12-03 14:28:38,683 - mmdet - INFO - Evaluating bbox... Loading and preparing results... DONE (t=0.21s) creating index... index created! Running per image evaluation... Evaluate annotation type *bbox* DONE (t=0.68s). Accumulating evaluation results... DONE (t=0.11s). 2024-12-03 14:28:39,689 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.113 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.241 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.096 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 ] = 0.094 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.432 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.161 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.161 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.161 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.003 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.185 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.531 2024-12-03 14:28:39,693 - mmdet - INFO - Exp name: yolox_nano_lite.py 2024-12-03 14:28:39,693 - mmdet - INFO - Epoch(val) [1][107] bbox_mAP: 0.1130, bbox_mAP_50: 0.2410, bbox_mAP_75: 0.0960, bbox_mAP_s: 0.0020, bbox_mAP_m: 0.0940, bbox_mAP_l: 0.4320, bbox_mAP_copypaste: 0.113 0.241 0.096 0.002 0.094 0.432 /home/zxb/.pyenv/versions/py310/lib/python3.10/site-packages/mmcv/onnx/info.py:20: UserWarning: DeprecationWarning: This function will be deprecated in future. Welcome to use the unified model deployment toolbox MMDeploy: https://github.com/open-mmlab/mmdeploy warnings.warn(msg) /home/zxb/.pyenv/versions/py310/lib/python3.10/site-packages/mmcv/tensorrt/init_plugins.py:51: UserWarning: DeprecationWarning: This function will be deprecated in future. Welcome to use the unified model deployment toolbox MMDeploy: https://github.com/open-mmlab/mmdeploy warnings.warn(msg) /home/zxb/.pyenv/versions/py310/lib/python3.10/site-packages/torch/onnx/symbolic_opset9.py:1248: UserWarning: This model contains a squeeze operation on dimension 1. If the model is intended to be used with dynamic input shapes, please use opset version 11 to export the model. warnings.warn( ============== Diagnostic Run torch.onnx.export version 2.0.1+cpu ============== verbose: False, log level: Level.ERROR ======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ======================== Successfully exported ONNX model: /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/training/model.onnx Trained model is at: /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/training SUCCESS: ModelMaker - Training completed. INFO:20241203-142844: model import is in progress - please see the log file for status. configs to run: ['od-8200'] number of configs: 1 INFO:20241203-142844: parallel_run - parallel_processes:1 parallel_devices=[0] TASKS | | 0% 0/1| [< ] INFO:20241203-142844: starting process on parallel_device - 0 0%| || 0/1 [00:00, 'input_dataset': , 'preprocess': , 'session': , 'postprocess': , 'metric': {'label_offset_pred': 1}, 'model_info': {'metric_reference': {'accuracy_ap[.5:.95]%': None}, 'model_shortlist': 10}} TASKS | 100%|██████████|| 1/1 [00:00<00:00, 1.37it/s] INFO:20241203-142844: model inference is in progress - please see the log file for status. configs to run: ['od-8200'] number of configs: 1 INFO:20241203-142844: parallel_run - parallel_processes:1 parallel_devices=[0] TASKS | | 0% 0/1| [< ] INFO:20241203-142844: starting process on parallel_device - 0 0%| || 0/1 [00:00, 'input_dataset': , 'preprocess': , 'session': , 'postprocess': , 'metric': {'label_offset_pred': 1}, 'model_info': {'metric_reference': {'accuracy_ap[.5:.95]%': None}, 'model_shortlist': 10}} TASKS | 100%|██████████|| 1/1 [00:00<00:00, 1.86it/s] packaging artifacts to /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/compilation/AM62A/pkg please wait... WARNING:20241203-142845: could not package - /home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/compilation/AM62A/work/od-8200 Traceback (most recent call last): File "/home/zxb/Desktop/ti/edgeai-modelmaker/./scripts/run_modelmaker.py", line 141, in main(config) File "/home/zxb/Desktop/ti/edgeai-modelmaker/./scripts/run_modelmaker.py", line 80, in main model_runner.run() File "/home/zxb/Desktop/ti/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/runner.py", line 187, in run self.model_compilation.run() File "/home/zxb/Desktop/ti/edgeai-modelmaker/edgeai_modelmaker/ai_modules/vision/compilation/edgeai_benchmark.py", line 269, in run edgeai_benchmark.interfaces.package_artifacts(self.settings, self.work_dir, out_dir=self.package_dir, custom_model=True) File "/home/zxb/Desktop/ti/edgeai-tidl-tools/examples/edgeai-benchmark/edgeai_benchmark/interfaces/run_package.py", line 271, in package_artifacts with open(os.path.join(out_dir,'artifacts.yaml'), 'w') as fp: FileNotFoundError: [Errno 2] No such file or directory: '/home/zxb/Desktop/ti/edgeai-modelmaker/data/projects/tiscapes2017_driving/run/20241203-142720/yolox_nano_lite/compilation/AM62A/pkg/artifacts.yaml' (py310) zxb@zxb-virtual-machine:~/Desktop/ti/edgeai-modelmaker$