mileva@rtrkw1016-mcs:~/mmyolo/tools$ python3 train.py ../configs/yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco.py --mode l-surgery 1 INFO:albumentations.check_version:A new version of Albumentations is available: 1.4.13 (you have 1.4.11). Upgrade using: pip install --upgrade albumentations 08/07 13:02:56 - mmengine - WARNING - Failed to search registry with scope "mmyolo" in the "log_processor" registry tree. As a workaround, the current "log_processor" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmyolo" is a correct scope, or whether the registry is initialized. 08/07 13:02:56 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0] CUDA available: False MUSA available: False numpy_random_seed: 1904510369 GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 PyTorch: 2.0.0+cu117 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, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, 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_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=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.15.1+cu117 OpenCV: 4.10.0 MMEngine: 0.10.4 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 1904510369 Distributed launcher: none Distributed training: False GPU number: 1 ------------------------------------------------------------ 08/07 13:02:56 - mmengine - INFO - Config: _backend_args = None _multiscale_resize_transforms = [ dict( transforms=[ dict(scale=( 1280, 1280, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1280, 1280, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 1024, 1024, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1024, 1024, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 1536, 1536, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1536, 1536, ), type='LetterResize'), ], type='Compose'), ] affine_scale = 0.9 albu_train_transforms = [ dict(p=0.01, type='Blur'), dict(p=0.01, type='MedianBlur'), dict(p=0.01, type='ToGray'), dict(p=0.01, type='CLAHE'), ] anchors = [ [ ( 19, 27, ), ( 44, 40, ), ( 38, 94, ), ], [ ( 96, 68, ), ( 86, 152, ), ( 180, 137, ), ], [ ( 140, 301, ), ( 303, 264, ), ( 238, 542, ), ], [ ( 436, 615, ), ( 739, 380, ), ( 925, 792, ), ], ] backend_args = None base_lr = 0.01 batch_shapes_cfg = dict( batch_size=1, extra_pad_ratio=0.5, img_size=1280, size_divisor=64, type='BatchShapePolicy') custom_hooks = [ dict( ema_type='ExpMomentumEMA', momentum=0.0001, priority=49, strict_load=False, type='EMAHook', update_buffers=True), ] data_root = 'data/coco/' dataset_type = 'YOLOv5CocoDataset' deepen_factor = 0.67 default_hooks = dict( checkpoint=dict( interval=10, max_keep_ckpts=3, save_best='auto', type='CheckpointHook'), logger=dict(interval=50, type='LoggerHook'), param_scheduler=dict( lr_factor=0.1, max_epochs=300, scheduler_type='linear', type='YOLOv5ParamSchedulerHook'), sampler_seed=dict(type='DistSamplerSeedHook'), timer=dict(type='IterTimerHook'), visualization=dict(type='mmdet.DetVisualizationHook')) default_scope = 'mmyolo' env_cfg = dict( cudnn_benchmark=True, dist_cfg=dict(backend='nccl'), mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) img_scale = ( 1280, 1280, ) img_scales = [ ( 640, 640, ), ( 320, 320, ), ( 960, 960, ), ] launcher = 'none' load_from = None log_level = 'INFO' log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50) loss_bbox_weight = 0.05 loss_cls_weight = 0.3 loss_obj_weight = 0.7 lr_factor = 0.1 max_epochs = 300 max_keep_ckpts = 3 mixup_prob = 0.1 model = dict( backbone=dict( act_cfg=dict(inplace=True, type='SiLU'), arch='P6', deepen_factor=0.67, norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), out_indices=( 2, 3, 4, 5, ), type='YOLOv5CSPDarknet', widen_factor=0.75), bbox_head=dict( head_module=dict( featmap_strides=[ 8, 16, 32, 64, ], in_channels=[ 256, 512, 768, 1024, ], num_base_priors=3, num_classes=80, type='YOLOv5HeadModule', widen_factor=0.75), loss_bbox=dict( bbox_format='xywh', eps=1e-07, iou_mode='ciou', loss_weight=0.037500000000000006, reduction='mean', return_iou=True, type='IoULoss'), loss_cls=dict( loss_weight=0.22499999999999998, reduction='mean', type='mmdet.CrossEntropyLoss', use_sigmoid=True), loss_obj=dict( loss_weight=2.0999999999999996, reduction='mean', type='mmdet.CrossEntropyLoss', use_sigmoid=True), obj_level_weights=[ 4.0, 1.0, 0.25, 0.06, ], prior_generator=dict( base_sizes=[ [ ( 19, 27, ), ( 44, 40, ), ( 38, 94, ), ], [ ( 96, 68, ), ( 86, 152, ), ( 180, 137, ), ], [ ( 140, 301, ), ( 303, 264, ), ( 238, 542, ), ], [ ( 436, 615, ), ( 739, 380, ), ( 925, 792, ), ], ], strides=[ 8, 16, 32, 64, ], type='mmdet.YOLOAnchorGenerator'), prior_match_thr=4.0, type='YOLOv5Head'), data_preprocessor=dict( bgr_to_rgb=True, mean=[ 0.0, 0.0, 0.0, ], std=[ 255.0, 255.0, 255.0, ], type='YOLOv5DetDataPreprocessor'), neck=dict( act_cfg=dict(inplace=True, type='SiLU'), deepen_factor=0.67, in_channels=[ 256, 512, 768, 1024, ], norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), num_csp_blocks=3, out_channels=[ 256, 512, 768, 1024, ], type='YOLOv5PAFPN', widen_factor=0.75), test_cfg=dict( max_per_img=300, multi_label=True, nms=dict(iou_threshold=0.65, type='nms'), nms_pre=30000, score_thr=0.001), type='YOLODetector') model_test_cfg = dict( max_per_img=300, multi_label=True, nms=dict(iou_threshold=0.65, type='nms'), nms_pre=30000, score_thr=0.001) mosaic_affine_pipeline = [ dict( img_scale=( 1280, 1280, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='Mosaic'), dict( border=( -640, -640, ), border_val=( 114, 114, 114, ), max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ] norm_cfg = dict(eps=0.001, momentum=0.03, type='BN') num_classes = 80 num_det_layers = 4 obj_level_weights = [ 4.0, 1.0, 0.25, 0.06, ] optim_wrapper = dict( constructor='YOLOv5OptimizerConstructor', optimizer=dict( batch_size_per_gpu=16, lr=0.01, momentum=0.937, nesterov=True, type='SGD', weight_decay=0.0005), type='OptimWrapper') param_scheduler = None persistent_workers = True pre_transform = [ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ] prior_match_thr = 4.0 resume = False save_checkpoint_intervals = 10 strides = [ 8, 16, 32, 64, ] test_cfg = dict(type='TestLoop') test_dataloader = dict( batch_size=1, dataset=dict( ann_file='annotations/instances_val2017.json', batch_shapes_cfg=dict( batch_size=1, extra_pad_ratio=0.5, img_size=1280, size_divisor=64, type='BatchShapePolicy'), data_prefix=dict(img='val2017/'), data_root='data/coco/', pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 1280, 1280, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1280, 1280, ), type='LetterResize'), dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', ), type='mmdet.PackDetInputs'), ], test_mode=True, type='YOLOv5CocoDataset'), drop_last=False, num_workers=2, persistent_workers=True, pin_memory=True, sampler=dict(shuffle=False, type='DefaultSampler')) test_evaluator = dict( ann_file='data/coco/annotations/instances_val2017.json', metric='bbox', proposal_nums=( 100, 1, 10, ), type='mmdet.CocoMetric') test_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 1280, 1280, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1280, 1280, ), type='LetterResize'), dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', ), type='mmdet.PackDetInputs'), ] train_ann_file = 'annotations/instances_train2017.json' train_batch_size_per_gpu = 16 train_cfg = dict(max_epochs=300, type='EpochBasedTrainLoop', val_interval=10) train_data_prefix = 'train2017/' train_dataloader = dict( batch_size=16, collate_fn=dict(type='yolov5_collate'), dataset=dict( ann_file='annotations/instances_train2017.json', data_prefix=dict(img='train2017/'), data_root='data/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 1280, 1280, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='Mosaic'), dict( border=( -640, -640, ), border_val=( 114, 114, 114, ), max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), dict( pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 1280, 1280, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='Mosaic'), dict( border=( -640, -640, ), border_val=( 114, 114, 114, ), max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ], prob=0.1, type='YOLOv5MixUp'), dict( bbox_params=dict( format='pascal_voc', label_fields=[ 'gt_bboxes_labels', 'gt_ignore_flags', ], type='BboxParams'), keymap=dict(gt_bboxes='bboxes', img='image'), transforms=[ dict(p=0.01, type='Blur'), dict(p=0.01, type='MedianBlur'), dict(p=0.01, type='ToGray'), dict(p=0.01, type='CLAHE'), ], type='mmdet.Albu'), dict(type='YOLOv5HSVRandomAug'), dict(prob=0.5, type='mmdet.RandomFlip'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', ), type='mmdet.PackDetInputs'), ], type='YOLOv5CocoDataset'), num_workers=8, persistent_workers=True, pin_memory=True, sampler=dict(shuffle=True, type='DefaultSampler')) train_num_workers = 8 train_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 1280, 1280, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='Mosaic'), dict( border=( -640, -640, ), border_val=( 114, 114, 114, ), max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), dict( pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 1280, 1280, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='Mosaic'), dict( border=( -640, -640, ), border_val=( 114, 114, 114, ), max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ], prob=0.1, type='YOLOv5MixUp'), dict( bbox_params=dict( format='pascal_voc', label_fields=[ 'gt_bboxes_labels', 'gt_ignore_flags', ], type='BboxParams'), keymap=dict(gt_bboxes='bboxes', img='image'), transforms=[ dict(p=0.01, type='Blur'), dict(p=0.01, type='MedianBlur'), dict(p=0.01, type='ToGray'), dict(p=0.01, type='CLAHE'), ], type='mmdet.Albu'), dict(type='YOLOv5HSVRandomAug'), dict(prob=0.5, type='mmdet.RandomFlip'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', ), type='mmdet.PackDetInputs'), ] tta_img_scales = [ ( 1280, 1280, ), ( 1024, 1024, ), ( 1536, 1536, ), ] tta_model = dict( tta_cfg=dict(max_per_img=300, nms=dict(iou_threshold=0.65, type='nms')), type='mmdet.DetTTAModel') tta_pipeline = [ dict(backend_args=None, type='LoadImageFromFile'), dict( transforms=[ [ dict( transforms=[ dict( scale=( 1280, 1280, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1280, 1280, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict( scale=( 1024, 1024, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1024, 1024, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict( scale=( 1536, 1536, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1536, 1536, ), type='LetterResize'), ], type='Compose'), ], [ dict(prob=1.0, type='mmdet.RandomFlip'), dict(prob=0.0, type='mmdet.RandomFlip'), ], [ dict(type='mmdet.LoadAnnotations', with_bbox=True), ], [ dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', 'flip', 'flip_direction', ), type='mmdet.PackDetInputs'), ], ], type='TestTimeAug'), ] val_ann_file = 'annotations/instances_val2017.json' val_batch_size_per_gpu = 1 val_cfg = dict(type='ValLoop') val_data_prefix = 'val2017/' val_dataloader = dict( batch_size=1, dataset=dict( ann_file='annotations/instances_val2017.json', batch_shapes_cfg=dict( batch_size=1, extra_pad_ratio=0.5, img_size=1280, size_divisor=64, type='BatchShapePolicy'), data_prefix=dict(img='val2017/'), data_root='data/coco/', pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 1280, 1280, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 1280, 1280, ), type='LetterResize'), dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', ), type='mmdet.PackDetInputs'), ], test_mode=True, type='YOLOv5CocoDataset'), drop_last=False, num_workers=2, persistent_workers=True, pin_memory=True, sampler=dict(shuffle=False, type='DefaultSampler')) val_evaluator = dict( ann_file='data/coco/annotations/instances_val2017.json', metric='bbox', proposal_nums=( 100, 1, 10, ), type='mmdet.CocoMetric') val_num_workers = 2 vis_backends = [ dict(type='LocalVisBackend'), ] visualizer = dict( name='visualizer', type='mmdet.DetLocalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), ]) weight_decay = 0.0005 widen_factor = 0.75 work_dir = './work_dirs/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco' 08/07 13:02:57 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used. 08/07 13:02:57 - 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: (9 ) YOLOv5ParamSchedulerHook (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (9 ) YOLOv5ParamSchedulerHook (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (9 ) YOLOv5ParamSchedulerHook (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (9 ) YOLOv5ParamSchedulerHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_val: (VERY_HIGH ) RuntimeInfoHook -------------------- before_val_epoch: (49 ) EMAHook (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) DetVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (9 ) YOLOv5ParamSchedulerHook (VERY_HIGH ) RuntimeInfoHook (49 ) EMAHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (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/mileva/.local/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") 08/07 13:02:58 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used. model summary : YOLODetector( (data_preprocessor): YOLOv5DetDataPreprocessor() (backbone): YOLOv5CSPDarknet( (stem): ConvModule( (conv): Conv2d(3, 48, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (stage1): Sequential( (0): ConvModule( (conv): Conv2d(48, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(96, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(96, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(48, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(48, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (stage2): Sequential( (0): ConvModule( (conv): Conv2d(96, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (2): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (3): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (stage3): Sequential( (0): ConvModule( (conv): Conv2d(192, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (2): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (3): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (4): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (5): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (stage4): Sequential( (0): ConvModule( (conv): Conv2d(384, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(576, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(576, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(576, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (stage5): Sequential( (0): ConvModule( (conv): Conv2d(576, 768, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (2): SPPFBottleneck( (conv1): ConvModule( (conv): Conv2d(768, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (poolings): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False) (conv2): ConvModule( (conv): Conv2d(1536, 768, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (neck): YOLOv5PAFPN( (reduce_layers): ModuleList( (0-2): 3 x Identity() (3): ConvModule( (conv): Conv2d(768, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (upsample_layers): ModuleList( (0-2): 3 x Upsample(scale_factor=2.0, mode='nearest') ) (top_down_layers): ModuleList( (0): Sequential( (0): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(1152, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(1152, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(576, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (1): ConvModule( (conv): Conv2d(576, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): Sequential( (0): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(768, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (1): ConvModule( (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (2): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(96, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(96, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (downsample_layers): ModuleList( (0): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (1): ConvModule( (conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (2): ConvModule( (conv): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (bottom_up_layers): ModuleList( (0): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(384, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (1): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(768, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(768, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(576, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(576, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(288, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(288, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(288, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) (2): CSPLayer( (main_conv): ConvModule( (conv): Conv2d(1152, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (short_conv): ConvModule( (conv): Conv2d(1152, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (final_conv): ConvModule( (conv): Conv2d(768, 768, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(768, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (blocks): Sequential( (0): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) (1): DarknetBottleneck( (conv1): ConvModule( (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) (conv2): ConvModule( (conv): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True) (activate): ReLU() ) ) ) ) ) (out_layers): ModuleList( (0-3): 4 x Identity() ) ) (bbox_head): YOLOv5Head( (head_module): YOLOv5HeadModule( (convs_pred): ModuleList( (0): Conv2d(192, 255, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(384, 255, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(576, 255, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(768, 255, kernel_size=(1, 1), stride=(1, 1)) ) ) (loss_cls): CrossEntropyLoss(avg_non_ignore=False) (loss_bbox): IoULoss() (loss_obj): CrossEntropyLoss(avg_non_ignore=False) ) ) /home/mileva/.local/lib/python3.10/site-packages/albumentations/core/composition.py:156: UserWarning: Got processor for bboxes, but no transform to process it. self._set_keys() loading annotations into memory... Traceback (most recent call last): File "/home/mileva/mmyolo/tools/train.py", line 155, in main() File "/home/mileva/mmyolo/tools/train.py", line 151, in main runner.train() File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1728, in train self._train_loop = self.build_train_loop( File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1520, in build_train_loop loop = LOOPS.build( File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(**args) # type: ignore File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/runner/loops.py", line 44, in __init__ super().__init__(runner, dataloader) File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/runner/base_loop.py", line 26, in __init__ self.dataloader = runner.build_dataloader( File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1370, in build_dataloader dataset = DATASETS.build(dataset_cfg) File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(**args) # type: ignore File "/home/mileva/.local/lib/python3.10/site-packages/mmyolo/datasets/yolov5_coco.py", line 19, in __init__ super().__init__(*args, **kwargs) File "/home/mileva/.local/lib/python3.10/site-packages/mmdet/datasets/base_det_dataset.py", line 51, in __init__ super().__init__(*args, **kwargs) File "/home/mileva/.local/lib/python3.10/site-packages/mmengine/dataset/base_dataset.py", line 247, in __init__ self.full_init() File "/home/mileva/.local/lib/python3.10/site-packages/mmyolo/datasets/yolov5_coco.py", line 27, in full_init self.data_list = self.load_data_list() File "/home/mileva/.local/lib/python3.10/site-packages/mmdet/datasets/coco.py", line 67, in load_data_list self.coco = self.COCOAPI(local_path) File "/home/mileva/.local/lib/python3.10/site-packages/mmdet/datasets/api_wrappers/coco_api.py", line 25, in __init__ super().__init__(annotation_file=annotation_file) File "/home/mileva/.local/lib/python3.10/site-packages/pycocotools/coco.py", line 81, in __init__ with open(annotation_file, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: 'data/coco/annotations/instances_train2017.json'