Intellindust-AI-Lab
Most of the indicators are 0 during training, and all of the indicators are -1 during verification.
Hello, thank you and your team for your contribution. I have a question now. When I was training my own dataset (only one category), I modified the num_classes in coco_detection.yml to 1, and also modified the training set and verification machine images and json to my own dataset.
After running the code (python train.py -c /home/wangchengkun/dzt/DEIM/DEIM-main/configs/deim_dfine/deim_hgnetv2_m_mydataset.yml), the model can be trained normally, but I found something wrong, as follows:Not init distributed mode.
cfg: {'task': 'detection', '_model': None, '_postprocessor': None, '_criterion': None, '_optimizer': None, '_lr_scheduler': None, '_lr_warmup_scheduler': None, '_train_dataloader': None, '_val_dataloader': None, '_ema': None, '_scaler': None, '_train_dataset': None, '_val_dataset': None, '_collate_fn': None, '_evaluator': None, '_writer': None, 'num_workers': 0, 'batch_size': None, '_train_batch_size': None, '_val_batch_size': None, '_train_shuffle': None, '_val_shuffle': None, 'resume': None, 'tuning': None, 'epoches': 102, 'last_epoch': -1, 'lrsheduler': 'flatcosine', 'lr_gamma': 0.5, 'no_aug_epoch': 12, 'warmup_iter': 2000, 'flat_epoch': 49, 'use_amp': False, 'use_ema': True, 'ema_decay': 0.9999, 'ema_warmups': 2000, 'sync_bn': True, 'clip_max_norm': 0.1, 'find_unused_parameters': False, 'seed': None, 'print_freq': 100, 'checkpoint_freq': 4, 'output_dir': './outputs/deim_hgnetv2_m_yaogan', 'summary_dir': None, 'device': '', 'yaml_cfg': {'task': 'detection', 'evaluator': {'type': 'CocoEvaluator', 'iou_types': ['bbox']}, 'num_classes': 1, 'remap_mscoco_category': False, 'train_dataloader': {'type': 'DataLoader', 'dataset': {'type': 'CocoDetection', 'img_folder': '/home/wangchengkun/dzt/DEIM/pre_Dataset/yaogan/train/images/', 'ann_file': '/home/wangchengkun/dzt/DEIM/pre_Dataset/yaogan/train/annotations/train.json', 'return_masks': False, 'transforms': {'type': 'Compose', 'ops': [{'type': 'Mosaic', 'output_size': 320, 'rotation_range': 10, 'translation_range': [0.1, 0.1], 'scaling_range': [0.5, 1.5], 'probability': 1.0, 'fill_value': 0, 'use_cache': False, 'max_cached_images': 50, 'random_pop': True}, {'type': 'RandomPhotometricDistort', 'p': 0.5}, {'type': 'RandomZoomOut', 'fill': 0}, {'type': 'RandomIoUCrop', 'p': 0.8}, {'type': 'SanitizeBoundingBoxes', 'min_size': 1}, {'type': 'RandomHorizontalFlip'}, {'type': 'Resize', 'size': [640, 640]}, {'type': 'SanitizeBoundingBoxes', 'min_size': 1}, {'type': 'ConvertPILImage', 'dtype': 'float32', 'scale': True}, {'type': 'ConvertBoxes', 'fmt': 'cxcywh', 'normalize': True}], 'policy': {'name': 'stop_epoch', 'epoch': [4, 49, 90], 'ops': ['Mosaic', 'RandomPhotometricDistort', 'RandomZoomOut', 'RandomIoUCrop']}, 'mosaic_prob': 0.5}}, 'shuffle': True, 'num_workers': 4, 'drop_last': True, 'collate_fn': {'type': 'BatchImageCollateFunction', 'base_size': 640, 'base_size_repeat': 6, 'stop_epoch': 90, 'ema_restart_decay': 0.9999, 'mixup_prob': 0.5, 'mixup_epochs': [4, 49]}, 'total_batch_size': 4}, 'val_dataloader': {'type': 'DataLoader', 'dataset': {'type': 'CocoDetection', 'img_folder': '/home/wangchengkun/dzt/DEIM/pre_Dataset/yaogan/val/images/', 'ann_file': '/home/wangchengkun/dzt/DEIM/pre_Dataset/yaogan/val/annotations/val.json', 'return_masks': False, 'transforms': {'type': 'Compose', 'ops': [{'type': 'Resize', 'size': [640, 640]}, {'type': 'ConvertPILImage', 'dtype': 'float32', 'scale': True}]}}, 'shuffle': False, 'num_workers': 4, 'drop_last': False, 'collate_fn': {'type': 'BatchImageCollateFunction'}, 'total_batch_size': 4}, 'print_freq': 100, 'output_dir': './outputs/deim_hgnetv2_m_yaogan', 'checkpoint_freq': 4, 'sync_bn': True, 'find_unused_parameters': False, 'use_amp': False, 'scaler': {'type': 'GradScaler', 'enabled': True}, 'use_ema': True, 'ema': {'type': 'ModelEMA', 'decay': 0.9999, 'warmups': 1000, 'start': 0}, 'epoches': 102, 'clip_max_norm': 0.1, 'optimizer': {'type': 'AdamW', 'params': [{'params': '^(?=.backbone)(?!.bn).$', 'lr': 4e-05}, {'params': '^(?=.(?:norm|bn)).*$', 'weight_decay': 0.0}], 'lr': 0.0004, 'betas': [0.9, 0.999], 'weight_decay': 0.0001}, 'lr_scheduler': {'type': 'MultiStepLR', 'milestones': [500], 'gamma': 0.1}, 'lr_warmup_scheduler': {'type': 'LinearWarmup', 'warmup_duration': 500}, 'model': 'DEIM', 'criterion': 'DEIMCriterion', 'postprocessor': 'PostProcessor', 'use_focal_loss': True, 'eval_spatial_size': [640, 640], 'DEIM': {'backbone': 'HGNetv2', 'encoder': 'HybridEncoder', 'decoder': 'DFINETransformer'}, 'lrsheduler': 'flatcosine', 'lr_gamma': 0.5, 'warmup_iter': 2000, 'flat_epoch': 49, 'no_aug_epoch': 12, 'HGNetv2': {'pretrained': True, 'local_model_dir': '../RT-DETR-main/D-FINE/weight/hgnetv2/', 'name': 'B2', 'return_idx': [1, 2, 3], 'freeze_at': -1, 'freeze_norm': False, 'use_lab': True}, 'HybridEncoder': {'in_channels': [384, 768, 1536], 'feat_strides': [8, 16, 32], 'hidden_dim': 256, 'use_encoder_idx': [2], 'num_encoder_layers': 1, 'nhead': 8, 'dim_feedforward': 1024, 'dropout': 0.0, 'enc_act': 'gelu', 'expansion': 1.0, 'depth_mult': 0.67, 'act': 'silu'}, 'DFINETransformer': {'feat_channels': [256, 256, 256], 'feat_strides': [8, 16, 32], 'hidden_dim': 256, 'num_levels': 3, 'num_layers': 4, 'eval_idx': -1, 'num_queries': 300, 'num_denoising': 100, 'label_noise_ratio': 0.5, 'box_noise_scale': 1.0, 'reg_max': 32, 'reg_scale': 4, 'layer_scale': 1, 'num_points': [3, 6, 3], 'cross_attn_method': 'default', 'query_select_method': 'default', 'activation': 'silu', 'mlp_act': 'silu'}, 'PostProcessor': {'num_top_queries': 300}, 'DEIMCriterion': {'weight_dict': {'loss_vfl': 1, 'loss_bbox': 5, 'loss_giou': 2, 'loss_fgl': 0.15, 'loss_ddf': 1.5, 'loss_mal': 1}, 'losses': ['mal', 'boxes', 'local'], 'alpha': 0.75, 'gamma': 1.5, 'reg_max': 32, 'matcher': {'type': 'HungarianMatcher', 'weight_dict': {'cost_class': 2, 'cost_bbox': 5, 'cost_giou': 2}, 'alpha': 0.25, 'gamma': 2.0}}, 'include': ['./dfine_hgnetv2_m_coco.yml', '../base/deim.yml'], 'config': '/home/wangchengkun/dzt/DEIM/DEIM-main/configs/deim_dfine/deim_hgnetv2_m_mydataset.yml', 'test_only': False, 'print_method': 'builtin', 'print_rank': 0}}
Loaded stage1 B2 HGNetV2 from local file.
Initial lr: [4e-05, 0.0004, 0.0004]
building train_dataloader with batch_size=4...
### Transform @Mosaic ###
### Transform @RandomPhotometricDistort ###
### Transform @RandomZoomOut ###
### Transform @RandomIoUCrop ###
### Transform @SanitizeBoundingBoxes ###
### Transform @RandomHorizontalFlip ###
### Transform @Resize ###
### Transform @SanitizeBoundingBoxes ###
### Transform @ConvertPILImage ###
### Transform @ConvertBoxes ###
### Mosaic with [email protected] and ZoomOut/IoUCrop existed ###
### ImgTransforms Epochs: [4, 49, 90] ###
### Policy_ops@['Mosaic', 'RandomPhotometricDistort', 'RandomZoomOut', 'RandomIoUCrop'] ###
### Using MixUp with [email protected] in [4, 49] epochs ###
### Multi-scale Training until 90 epochs ###
### Multi-scales@ [480, 512, 544, 576, 608, 640, 640, 640, 640, 640, 640, 800, 768, 736, 704, 672] ###
building val_dataloader with batch_size=4...
### Transform @Resize ###
### Transform @ConvertPILImage ###
------------------------------------- Calculate Flops Results ------------------------------------- Notations: number of parameters (Params), number of multiply-accumulate operations(MACs), number of floating-point operations (FLOPs), floating-point operations per second (FLOPS), fwd FLOPs (model forward propagation FLOPs), bwd FLOPs (model backward propagation FLOPs), default model backpropagation takes 2.00 times as much computation as forward propagation.
Total Training Params: 19.19 M fwd MACs: 28.0804 GMACs fwd FLOPs: 56.3325 GFLOPS fwd+bwd MACs: 84.2412 GMACs fwd+bwd FLOPs: 168.998 GFLOPS
{'Model FLOPs:56.3325 GFLOPS MACs:28.0804 GMACs Params:19187359'} ------------------------------------------Start training------------------------------------------- ## Using Self-defined Scheduler-flatcosine ## [4e-05, 0.0004, 0.0004] [2e-05, 0.0002, 0.0002] 60486 2000 29057 7116 number of trainable parameters: 19468323 Epoch: [0] [ 0/593] eta: 0:24:47 lr: 0.000000 loss: 0.5525 (0.5525) loss_mal: 0.0176 (0.0176) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0409 (0.0409) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0182 (0.0182) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0105 (0.0105) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0409 (0.0409) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.4243 (0.4243) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) time: 2.5086 data: 0.6290 max mem: 3911 Epoch: [0] [100/593] eta: 0:03:17 lr: 0.000000 loss: 0.4465 (0.5089) loss_mal: 0.0117 (0.0153) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0355 (0.0400) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0146 (0.0165) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0090 (0.0104) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0355 (0.0400) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.3477 (0.3868) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: -0.0000 (-0.0000) loss_ddf_aux_2: -0.0000 (-0.0000) time: 0.3480 data: 0.0069 max mem: 6053 Epoch: [0] [200/593] eta: 0:02:27 lr: 0.000000 loss: 0.1453 (0.3843) loss_mal: 0.0018 (0.0103) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0085 (0.0294) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0039 (0.0124) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0018 (0.0075) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0085 (0.0294) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.1195 (0.2953) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) time: 0.3563 data: 0.0072 max mem: 6053 Epoch: [0] [300/593] eta: 0:01:47 lr: 0.000001 loss: 0.0175 (0.2717) loss_mal: 0.0000 (0.0070) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0002 (0.0202) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0001 (0.0085) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0000 (0.0051) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0002 (0.0203) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.0169 (0.2106) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) time: 0.3528 data: 0.0072 max mem: 6053 Epoch: [0] [400/593] eta: 0:01:09 lr: 0.000002 loss: 0.0025 (0.2055) loss_mal: 0.0000 (0.0052) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0000 (0.0152) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0000 (0.0064) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0000 (0.0038) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0000 (0.0152) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.0025 (0.1596) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) time: 0.3391 data: 0.0068 max mem: 6053 Epoch: [0] [500/593] eta: 0:00:33 lr: 0.000003 loss: 0.0009 (0.1647) loss_mal: 0.0000 (0.0042) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0000 (0.0122) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0000 (0.0051) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0000 (0.0031) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0000 (0.0122) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.0009 (0.1280) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) time: 0.3520 data: 0.0071 max mem: 6053 Epoch: [0] [592/593] eta: 0:00:00 lr: 0.000004 loss: 0.0005 (0.1393) loss_mal: 0.0000 (0.0035) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0000 (0.0103) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0000 (0.0043) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0000 (0.0026) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0000 (0.0103) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.0005 (0.1082) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) time: 0.3429 data: 0.0072 max mem: 6053 Epoch: [0] Total time: 0:03:31 (0.3565 s / it) Averaged stats: lr: 0.000004 loss: 0.0005 (0.1393) loss_mal: 0.0000 (0.0035) loss_bbox: 0.0000 (0.0000) loss_giou: 0.0000 (0.0000) loss_fgl: 0.0000 (0.0000) loss_mal_aux_0: 0.0000 (0.0103) loss_bbox_aux_0: 0.0000 (0.0000) loss_giou_aux_0: 0.0000 (0.0000) loss_fgl_aux_0: 0.0000 (0.0000) loss_mal_aux_1: 0.0000 (0.0043) loss_bbox_aux_1: 0.0000 (0.0000) loss_giou_aux_1: 0.0000 (0.0000) loss_fgl_aux_1: 0.0000 (0.0000) loss_mal_aux_2: 0.0000 (0.0026) loss_bbox_aux_2: 0.0000 (0.0000) loss_giou_aux_2: 0.0000 (0.0000) loss_fgl_aux_2: 0.0000 (0.0000) loss_mal_pre: 0.0000 (0.0103) loss_bbox_pre: 0.0000 (0.0000) loss_giou_pre: 0.0000 (0.0000) loss_mal_enc_0: 0.0005 (0.1082) loss_bbox_enc_0: 0.0000 (0.0000) loss_giou_enc_0: 0.0000 (0.0000) loss_ddf_aux_0: 0.0000 (0.0000) loss_ddf_aux_1: 0.0000 (-0.0000) loss_ddf_aux_2: 0.0000 (-0.0000) Test: [ 0/75] eta: 0:00:52 time: 0.6972 data: 0.6087 max mem: 6053 Test: [10/75] eta: 0:00:10 time: 0.1619 data: 0.0640 max mem: 6053 Test: [20/75] eta: 0:00:06 time: 0.0959 data: 0.0097 max mem: 6053 Test: [30/75] eta: 0:00:05 time: 0.0917 data: 0.0099 max mem: 6053 Test: [40/75] eta: 0:00:03 time: 0.0929 data: 0.0101 max mem: 6053 Test: [50/75] eta: 0:00:02 time: 0.0853 data: 0.0101 max mem: 6053 Test: [60/75] eta: 0:00:01 time: 0.0907 data: 0.0096 max mem: 6053 Test: [70/75] eta: 0:00:00 time: 0.0911 data: 0.0097 max mem: 6053 Test: [74/75] eta: 0:00:00 time: 0.0903 data: 0.0095 max mem: 6053 Test: Total time: 0:00:07 (0.1036 s / it) Averaged stats: Accumulating evaluation results... COCOeval_opt.accumulate() finished... DONE (t=0.02s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50 | area= all | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.75 | area= all | maxDets=100 ] = -1.000 best_stat: {'epoch': -1, 'coco_eval_bbox': 0}
Excuse me, could you please take the time to help me answer this question?
