训练结果中的bbox_mAP_s一直为 0.00 ?

[Vireakdara]

2024/12/22 02:04:23 - mmengine - INFO - Config: _backend_args = None _multiscale_resize_transforms = [ dict( transforms=[ dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 320, 320, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 320, 320, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 960, 960, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 960, 960, ), 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'), ] backend_args = None base_lr = 2e-05 batch_shapes_cfg = None classnames = [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'TV', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush', ] close_mosaic_epochs = 30 coco_train_dataset = dict( delete=True, class_text_path='data/texts/coco_class_texts.json', dataset=dict( ann_file='annotations/instances_train2017.json', data_prefix=dict(img='images/train2017/'), data_root='/home/wrf/Dara/coco2017label/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), type='YOLOv5CocoDataset'), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, 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=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ], prob=0.15, type='YOLOv5MultiModalMixUp'), 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( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ], type='MultiModalDataset') coco_val_dataset = dict( delete=True, class_text_path='data/texts/coco_class_texts.json', dataset=dict( ann_file='annotations/instances_val2017.json', data_prefix=dict(img='images/val2017/'), data_root='/home/wrf/Dara/coco2017label/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), type='YOLOv5CocoDataset'), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), dict(scope='mmdet', type='LoadAnnotations', with_bbox=True), dict(type='LoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', 'texts', ), type='mmdet.PackDetInputs'), ], type='MultiModalDataset') custom_hooks = [ dict( ema_type='ExpMomentumEMA', momentum=0.0001, priority=49, strict_load=False, type='EMAHook', update_buffers=True), dict( switch_epoch=10, switch_pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=True, pad_val=dict(img=114.0), scale=( 640, 640, ), type='LetterResize'), dict( border_val=( 114, 114, 114, ), max_aspect_ratio=100, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), 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( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ], type='mmdet.PipelineSwitchHook'), ] custom_imports = dict( allow_failed_imports=False, imports=[ 'yolo_world', ]) data_root = 'data/coco/' dataset_type = 'YOLOv5CocoDataset' deepen_factor = 1.0 default_hooks = dict( checkpoint=dict( interval=5, max_keep_ckpts=-1, save_best=None, type='CheckpointHook'), logger=dict(interval=50, type='LoggerHook'), param_scheduler=dict( lr_factor=0.01, max_epochs=40, 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 = ( 640, 640, ) img_scales = [ ( 640, 640, ), ( 320, 320, ), ( 960, 960, ), ] last_stage_out_channels = 512 last_transform = [ 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'), ] launcher = 'none' load_from = None log_level = 'INFO' log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50) loss_bbox_weight = 7.5 loss_cls_weight = 0.5 loss_dfl_weight = 0.375 lr_factor = 0.01 max_aspect_ratio = 100 max_epochs = 40 max_keep_ckpts = 2 mixup_prob = 0.15 model = dict( backbone=dict( image_model=dict( act_cfg=dict(inplace=True, type='SiLU'), arch='P5', deepen_factor=1.0, last_stage_out_channels=512, norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), type='YOLOv8CSPDarknet', widen_factor=1.0), text_model=dict( classnames=[ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'TV', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush', ], frozen_modules=[ 'all', ], model_name='pretrained/clip-vit-base-patch32', type='HuggingCLIPCocoOpLanguageBackbone'), type='MultiModalYOLOBackbone'), bbox_head=dict( bbox_coder=dict(type='DistancePointBBoxCoder'), head_module=dict( act_cfg=dict(inplace=True, type='SiLU'), embed_dims=512, featmap_strides=[ 8, 16, 32, ], in_channels=[ 256, 512, 512, ], norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), num_classes=80, reg_max=16, type='YOLOWorldHeadModule', use_bn_head=True, widen_factor=1.0), loss_bbox=dict( bbox_format='xyxy', iou_mode='ciou', loss_weight=7.5, reduction='sum', return_iou=False, type='IoULoss'), loss_cls=dict( loss_weight=0.5, reduction='none', type='mmdet.CrossEntropyLoss', use_sigmoid=True), loss_dfl=dict( loss_weight=0.375, reduction='mean', type='mmdet.DistributionFocalLoss'), prior_generator=dict( offset=0.5, strides=[ 8, 16, 32, ], type='mmdet.MlvlPointGenerator'), type='YOLOWorldHead'), data_preprocessor=dict( bgr_to_rgb=True, mean=[ 0.0, 0.0, 0.0, ], std=[ 255.0, 255.0, 255.0, ], type='YOLOWDetDataPreprocessor'), mm_neck=True, neck=dict( act_cfg=dict(inplace=True, type='SiLU'), block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv'), deepen_factor=1.0, embed_channels=[ 128, 256, 256, ], guide_channels=512, in_channels=[ 256, 512, 512, ], norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), num_csp_blocks=3, num_heads=[ 4, 8, 8, ], out_channels=[ 256, 512, 512, ], type='YOLOWorldPAFPN', widen_factor=1.0), num_test_classes=80, num_train_classes=80, test_cfg=dict( max_per_img=300, multi_label=True, nms=dict(iou_threshold=0.7, type='nms'), nms_pre=30000, score_thr=0.001), train_cfg=dict( assigner=dict( alpha=0.5, beta=6.0, eps=1e-09, num_classes=80, topk=10, type='BatchTaskAlignedAssigner', use_ciou=True)), type='YOLOWorldDetector') model_test_cfg = dict( max_per_img=300, multi_label=True, nms=dict(iou_threshold=0.7, type='nms'), nms_pre=30000, score_thr=0.001) mosaic_affine_transform = [ dict( img_scale=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ] neck_embed_channels = [ 128, 256, 256, ] neck_num_heads = [ 4, 8, 8, ] norm_cfg = dict(eps=0.001, momentum=0.03, type='BN') num_classes = 80 num_det_layers = 3 num_training_classes = 80 optim_wrapper = dict( clip_grad=dict(max_norm=10.0), constructor='YOLOWv5OptimizerConstructor', loss_scale='dynamic', optimizer=dict( batch_size_per_gpu=16, lr=2e-05, type='AdamW', weight_decay=0.05), paramwise_cfg=dict( custom_keys=dict({ 'backbone.text_model': dict(lr_mult=0.01), 'logit_scale': dict(weight_decay=0.0) })), type='AmpOptimWrapper') param_scheduler = None persistent_workers = False pre_transform = [ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ] resume = True save_epoch_intervals = 5 strides = [ 8, 16, 32, ] tal_alpha = 0.5 tal_beta = 6.0 tal_topk = 10 test_cfg = dict(type='TestLoop') test_dataloader = dict( batch_size=1, dataset=dict( class_text_path='data/texts/coco_class_texts.json', dataset=dict( ann_file='annotations/instances_val2017.json', data_prefix=dict(img='images/val2017/'), data_root='/home/wrf/Dara/coco2017label/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), type='YOLOv5CocoDataset'), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), dict(scope='mmdet', type='LoadAnnotations', with_bbox=True), dict(type='LoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', 'texts', ), type='mmdet.PackDetInputs'), ], type='MultiModalDataset'), 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=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), dict(scope='mmdet', type='LoadAnnotations', with_bbox=True), dict(type='LoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', 'texts', ), type='mmdet.PackDetInputs'), ] text_channels = 512 text_model_name = 'pretrained/clip-vit-base-patch32' text_transform = [ dict( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ] train_ann_file = 'annotations/instances_train2017.json' train_batch_size_per_gpu = 16 train_cfg = dict( dynamic_intervals=[ ( 10, 1, ), ], max_epochs=40, type='EpochBasedTrainLoop', val_interval=5) train_data_prefix = 'train2017/' train_dataloader = dict( batch_size=16, collate_fn=dict(type='yolow_collate'), dataset=dict( class_text_path='data/texts/coco_class_texts.json', dataset=dict( ann_file='annotations/instances_train2017.json', data_prefix=dict(img='images/train2017/'), data_root='/home/wrf/Dara/coco2017label/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), type='YOLOv5CocoDataset'), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( img_scale=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, 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=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ], prob=0.15, type='YOLOv5MultiModalMixUp'), 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( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ], type='MultiModalDataset'), num_workers=8, persistent_workers=False, 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=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, 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=( 640, 640, ), pad_val=114.0, pre_transform=[ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), ], type='MultiModalMosaic'), dict( border=( -320, -320, ), border_val=( 114, 114, 114, ), max_aspect_ratio=100.0, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), ], prob=0.15, type='YOLOv5MultiModalMixUp'), 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( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ] train_pipeline_stage2 = [ dict(backend_args=None, type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=True, pad_val=dict(img=114.0), scale=( 640, 640, ), type='LetterResize'), dict( border_val=( 114, 114, 114, ), max_aspect_ratio=100, max_rotate_degree=0.0, max_shear_degree=0.0, scaling_ratio_range=( 0.09999999999999998, 1.9, ), type='YOLOv5RandomAffine'), 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( max_num_samples=80, num_neg_samples=( 80, 80, ), padding_to_max=True, padding_value='', type='RandomLoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction', 'texts', ), type='mmdet.PackDetInputs'), ] 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=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 320, 320, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 320, 320, ), type='LetterResize'), ], type='Compose'), dict( transforms=[ dict(scale=( 960, 960, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 960, 960, ), 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( class_text_path='data/texts/coco_class_texts.json', dataset=dict( ann_file='annotations/instances_val2017.json', data_prefix=dict(img='images/val2017/'), data_root='/home/wrf/Dara/coco2017label/coco/', filter_cfg=dict(filter_empty_gt=False, min_size=32), type='YOLOv5CocoDataset'), pipeline=[ dict(backend_args=None, type='LoadImageFromFile'), dict(scale=( 640, 640, ), type='YOLOv5KeepRatioResize'), dict( allow_scale_up=False, pad_val=dict(img=114), scale=( 640, 640, ), type='LetterResize'), dict(scope='mmdet', type='LoadAnnotations', with_bbox=True), dict(type='LoadText'), dict( meta_keys=( 'img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'pad_param', 'texts', ), type='mmdet.PackDetInputs'), ], type='MultiModalDataset'), drop_last=False, num_workers=2, persistent_workers=True, pin_memory=True, sampler=dict(shuffle=False, type='DefaultSampler')) val_evaluator = dict( ann_file= '/home/wrf/Dara/coco2017label/coco/annotations/instances_val2017.json', metric='bbox', proposal_nums=( 100, 1, 10, ), type='mmdet.CocoMetric') val_interval_stage2 = 1 val_num_workers = 2 vis_backends = [ dict(type='LocalVisBackend'), ] visualizer = dict( name='visualizer', type='mmdet.DetLocalVisualizer', vis_backends=[ dict(type='LocalVisBackend'), ]) weight_decay = 0.05 widen_factor = 1.0 work_dir = 'log'

2024/12/22 02:04:26 - 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. 2024/12/22 02:04:26 - 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
(NORMAL ) PipelineSwitchHook

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

2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.weight:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.weight:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.weight:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.bias:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.bias:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.context_to_text_projection.bias:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.ctx:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.ctx:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.ctx:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.weight:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.weight:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.weight:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.bias:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.bias:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.0.bias:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.weight:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.weight:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.weight:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.bias:lr=2.0000000000000002e-07 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.bias:weight_decay=0.05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- backbone.text_model.prompt_learner.meta_net.2.bias:lr_mult=0.01 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.0.logit_scale:lr=2e-05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.0.logit_scale:weight_decay=0.0 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.1.logit_scale:lr=2e-05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.1.logit_scale:weight_decay=0.0 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.2.logit_scale:lr=2e-05 2024/12/22 02:04:42 - mmengine - INFO - paramwise_options -- bbox_head.head_module.cls_contrasts.2.logit_scale:weight_decay=0.0 Name of parameter - Initialization information

backbone.image_model.stem.conv.weight - torch.Size([64, 3, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stem.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stem.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.0.conv.weight - torch.Size([128, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.0.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.0.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.main_conv.conv.weight - torch.Size([128, 128, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.main_conv.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.main_conv.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.final_conv.conv.weight - torch.Size([128, 320, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.final_conv.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.final_conv.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.0.conv1.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.0.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.0.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.0.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.0.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.0.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.1.conv1.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.1.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.1.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.1.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.1.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.1.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.2.conv1.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.2.conv1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.2.conv1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.2.conv2.conv.weight - torch.Size([64, 64, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage1.1.blocks.2.conv2.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage1.1.blocks.2.conv2.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.0.conv.weight - torch.Size([256, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.0.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.0.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.main_conv.conv.weight - torch.Size([256, 256, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.main_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.main_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.final_conv.conv.weight - torch.Size([256, 1024, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.final_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.final_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.0.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.0.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.0.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.0.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.0.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.0.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.1.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.1.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.1.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.1.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.1.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.1.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.2.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.2.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.2.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.2.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.2.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.2.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.3.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.3.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.3.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.3.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.3.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.3.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.4.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.4.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.4.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.4.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.4.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.4.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.5.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.5.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.5.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.5.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage2.1.blocks.5.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage2.1.blocks.5.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.0.conv.weight - torch.Size([512, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.0.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.0.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.main_conv.conv.weight - torch.Size([512, 512, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.main_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.main_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.final_conv.conv.weight - torch.Size([512, 2048, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.final_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.final_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.0.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.1.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.2.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.3.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.3.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.3.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.3.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.3.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.3.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.4.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.4.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.4.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.4.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.4.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.4.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.5.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.5.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.5.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.5.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage3.1.blocks.5.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage3.1.blocks.5.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.0.conv.weight - torch.Size([512, 512, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.0.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.0.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.main_conv.conv.weight - torch.Size([512, 512, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.main_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.main_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.final_conv.conv.weight - torch.Size([512, 1280, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.final_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.final_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.0.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.1.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.2.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.1.blocks.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.1.blocks.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.2.conv1.conv.weight - torch.Size([256, 512, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.2.conv2.conv.weight - torch.Size([512, 1024, 1, 1]): Initialized by user-defined init_weights in YOLOv8CSPDarknet

backbone.image_model.stage4.2.conv2.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.image_model.stage4.2.conv2.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.embeddings.token_embedding.weight - torch.Size([49408, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.embeddings.position_embedding.weight - torch.Size([77, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.0.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.1.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.2.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.3.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.4.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.5.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.6.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.7.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.8.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.9.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.10.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.k_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.k_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.v_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.v_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.q_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.q_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.self_attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.layer_norm1.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.layer_norm1.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.mlp.fc1.weight - torch.Size([2048, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.mlp.fc1.bias - torch.Size([2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.mlp.fc2.weight - torch.Size([512, 2048]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.mlp.fc2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.layer_norm2.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.encoder.layers.11.layer_norm2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.final_layer_norm.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_model.final_layer_norm.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.model.text_projection.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.context_to_text_projection.weight - torch.Size([512, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.context_to_text_projection.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.prompt_learner.ctx - torch.Size([16, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.prompt_learner.meta_net.0.weight - torch.Size([256, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.prompt_learner.meta_net.0.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.prompt_learner.meta_net.2.weight - torch.Size([512, 256]): The value is the same before and after calling init_weights of YOLOWorldDetector

backbone.text_model.prompt_learner.meta_net.2.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.main_conv.conv.weight - torch.Size([512, 1024, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.main_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.main_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.final_conv.conv.weight - torch.Size([512, 1536, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.final_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.final_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.0.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.1.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.2.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.blocks.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.blocks.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.attn_block.bias - torch.Size([8]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.attn_block.guide_fc.weight - torch.Size([256, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.attn_block.guide_fc.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.attn_block.project_conv.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.0.attn_block.project_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.0.attn_block.project_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.main_conv.conv.weight - torch.Size([256, 768, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.main_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.main_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.final_conv.conv.weight - torch.Size([256, 768, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.final_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.final_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.0.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.0.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.0.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.0.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.0.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.0.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.1.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.1.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.1.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.1.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.1.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.1.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.2.conv1.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.2.conv1.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.2.conv1.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.2.conv2.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.blocks.2.conv2.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.blocks.2.conv2.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.attn_block.bias - torch.Size([4]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.attn_block.guide_fc.weight - torch.Size([128, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.attn_block.guide_fc.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.attn_block.project_conv.conv.weight - torch.Size([128, 128, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.top_down_layers.1.attn_block.project_conv.bn.weight - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.top_down_layers.1.attn_block.project_conv.bn.bias - torch.Size([128]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.downsample_layers.0.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.downsample_layers.0.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.downsample_layers.0.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.downsample_layers.1.conv.weight - torch.Size([512, 512, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.downsample_layers.1.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.downsample_layers.1.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.main_conv.conv.weight - torch.Size([512, 768, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.main_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.main_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.final_conv.conv.weight - torch.Size([512, 1536, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.final_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.final_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.0.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.1.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.2.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.blocks.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.blocks.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.attn_block.bias - torch.Size([8]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.attn_block.guide_fc.weight - torch.Size([256, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.attn_block.guide_fc.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.attn_block.project_conv.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.0.attn_block.project_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.0.attn_block.project_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.main_conv.conv.weight - torch.Size([512, 1024, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.main_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.main_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.final_conv.conv.weight - torch.Size([512, 1536, 1, 1]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.final_conv.bn.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.final_conv.bn.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.0.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.0.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.0.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.0.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.0.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.0.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.1.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.1.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.1.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.1.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.1.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.1.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.2.conv1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.2.conv1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.2.conv1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.2.conv2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.blocks.2.conv2.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.blocks.2.conv2.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.attn_block.bias - torch.Size([8]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.attn_block.guide_fc.weight - torch.Size([256, 512]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.attn_block.guide_fc.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.attn_block.project_conv.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined init_weights in YOLOWorldPAFPN

neck.bottom_up_layers.1.attn_block.project_conv.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

neck.bottom_up_layers.1.attn_block.project_conv.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.0.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.0.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.0.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.1.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.2.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.0.2.bias - torch.Size([512]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_preds.1.0.conv.weight - torch.Size([256, 512, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.0.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.0.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.1.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.2.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.1.2.bias - torch.Size([512]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_preds.2.0.conv.weight - torch.Size([256, 512, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.0.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.0.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.1.conv.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.1.bn.weight - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.1.bn.bias - torch.Size([256]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.2.weight - torch.Size([512, 256, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_preds.2.2.bias - torch.Size([512]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.reg_preds.0.0.conv.weight - torch.Size([64, 256, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.0.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.0.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.1.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.0.2.bias - torch.Size([64]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.reg_preds.1.0.conv.weight - torch.Size([64, 512, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.0.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.0.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.1.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.1.2.bias - torch.Size([64]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.reg_preds.2.0.conv.weight - torch.Size([64, 512, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.0.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.0.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.1.conv.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.1.bn.weight - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.1.bn.bias - torch.Size([64]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.reg_preds.2.2.bias - torch.Size([64]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_contrasts.0.bias - torch.Size([]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_contrasts.0.logit_scale - torch.Size([]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.0.norm.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.0.norm.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.1.bias - torch.Size([]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_contrasts.1.logit_scale - torch.Size([]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.1.norm.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.1.norm.bias - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.2.bias - torch.Size([]): Initialized by user-defined init_weights in YOLOWorldHeadModule

bbox_head.head_module.cls_contrasts.2.logit_scale - torch.Size([]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.2.norm.weight - torch.Size([512]): The value is the same before and after calling init_weights of YOLOWorldDetector

bbox_head.head_module.cls_contrasts.2.norm.bias - torch.Size([512]):

[Vireakdara]

The value is the same before and after calling init_weights of YOLOWorldDetector
2024/12/22 02:04:44 - mmengine - INFO - Auto resumed from the latest checkpoint None. 2024/12/22 02:04:44 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2024/12/22 02:04:44 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2024/12/22 02:04:44 - mmengine - INFO - Checkpoints will be saved to /home/wrf/Dara/YOLO-World/log. 2024/12/22 02:05:07 - mmengine - INFO - Epoch(train) [1][ 50/7393] base_lr: 2.0000e-05 lr: 4.4186e-08 eta: 1 day, 13:02:47 time: 0.4511 data_time: 0.0204 memory: 17268 grad_norm: nan loss: 227.5976 loss_cls: 84.4697 loss_bbox: 75.6345 loss_dfl: 67.4934 2024/12/22 02:05:23 - mmengine - INFO - Epoch(train) [1][ 100/7393] base_lr: 2.0000e-05 lr: 8.9274e-08 eta: 1 day, 7:56:36 time: 0.3269 data_time: 0.0021 memory: 11084 grad_norm: 6342.2549 loss: 229.3823 loss_cls: 85.4327 loss_bbox: 76.6748 loss_dfl: 67.2748 2024/12/22 02:05:39 - mmengine - INFO - Epoch(train) [1][ 150/7393] base_lr: 2.0000e-05 lr: 1.3436e-07 eta: 1 day, 6:11:56 time: 0.3255 data_time: 0.0020 memory: 10617 grad_norm: inf loss: 230.8602 loss_cls: 86.8725 loss_bbox: 76.1613 loss_dfl: 67.8265 2024/12/22 02:05:56 - mmengine - INFO - Epoch(train) [1][ 200/7393] base_lr: 2.0000e-05 lr: 1.7945e-07 eta: 1 day, 5:22:15 time: 0.3277 data_time: 0.0019 memory: 10938 grad_norm: 5437.4611 loss: 229.6131 loss_cls: 84.6716 loss_bbox: 77.2413 loss_dfl: 67.7002 2024/12/22 02:06:12 - mmengine - INFO - Epoch(train) [1][ 250/7393] base_lr: 2.0000e-05 lr: 2.2454e-07 eta: 1 day, 4:54:20 time: 0.3298 data_time: 0.0020 memory: 10737 grad_norm: 6875.9662 loss: 230.0067 loss_cls: 85.1926 loss_bbox: 77.1760 loss_dfl: 67.6381 2024/12/22 02:06:29 - mmengine - INFO - Epoch(train) [1][ 300/7393] base_lr: 2.0000e-05 lr: 2.6962e-07 eta: 1 day, 4:36:18 time: 0.3306 data_time: 0.0020 memory: 10804 grad_norm: 4195.8064 loss: 226.0061 loss_cls: 83.8628 loss_bbox: 74.7284 loss_dfl: 67.4150 2024/12/22 02:06:45 - mmengine - INFO - Epoch(train) [1][ 350/7393] base_lr: 2.0000e-05 lr: 3.1471e-07 eta: 1 day, 4:23:02 time: 0.3301 data_time: 0.0020 memory: 11337 grad_norm: 5145.1625 loss: 229.5156 loss_cls: 85.8967 loss_bbox: 76.2065 loss_dfl: 67.4123 2024/12/22 02:07:02 - mmengine - INFO - Epoch(train) [1][ 400/7393] base_lr: 2.0000e-05 lr: 3.5980e-07 eta: 1 day, 4:13:38 time: 0.3311 data_time: 0.0021 memory: 10644 grad_norm: 5283.6558 loss: 229.6874 loss_cls: 85.0685 loss_bbox: 76.6569 loss_dfl: 67.9620 2024/12/22 02:07:18 - mmengine - INFO - Epoch(train) [1][ 450/7393] base_lr: 2.0000e-05 lr: 4.0489e-07 eta: 1 day, 4:06:09 time: 0.3309 data_time: 0.0020 memory: 10711 grad_norm: 3935.3781 loss: 228.3512 loss_cls: 84.7763 loss_bbox: 76.2252 loss_dfl: 67.3497 2024/12/22 02:07:35 - mmengine - INFO - Epoch(train) [1][ 500/7393] base_lr: 2.0000e-05 lr: 4.4998e-07 eta: 1 day, 4:01:02 time: 0.3328 data_time: 0.0021 memory: 11071 grad_norm: 3720.8120 loss: 231.8476 loss_cls: 86.1656 loss_bbox: 78.3838 loss_dfl: 67.2983 2024/12/22 02:07:52 - mmengine - INFO - Epoch(train) [1][ 550/7393] base_lr: 2.0000e-05 lr: 4.9506e-07 eta: 1 day, 3:56:12 time: 0.3315 data_time: 0.0021 memory: 11191 grad_norm: 4462.1433 loss: 230.6035 loss_cls: 84.9792 loss_bbox: 77.8353 loss_dfl: 67.7889 2024/12/22 02:08:08 - mmengine - INFO - Epoch(train) [1][ 600/7393] base_lr: 2.0000e-05 lr: 5.4015e-07 eta: 1 day, 3:52:28 time: 0.3323 data_time: 0.0021 memory: 11004 grad_norm: 4922.6265 loss: 228.4033 loss_cls: 84.7271 loss_bbox: 75.8747 loss_dfl: 67.8015 2024/12/22 02:08:25 - mmengine - INFO - Epoch(train) [1][ 650/7393] base_lr: 2.0000e-05 lr: 5.8524e-07 eta: 1 day, 3:48:59 time: 0.3316 data_time: 0.0021 memory: 10725 grad_norm: 3704.7143 loss: 227.7244 loss_cls: 84.4357 loss_bbox: 75.7557 loss_dfl: 67.5330 2024/12/22 02:08:41 - mmengine - INFO - Epoch(train) [1][ 700/7393] base_lr: 2.0000e-05 lr: 6.3033e-07 eta: 1 day, 3:45:57 time: 0.3316 data_time: 0.0021 memory: 11045 grad_norm: 3095.3749 loss: 229.7249 loss_cls: 84.7045 loss_bbox: 77.6094 loss_dfl: 67.4109 2024/12/22 02:08:58 - mmengine - INFO - Epoch(train) [1][ 750/7393] base_lr: 2.0000e-05 lr: 6.7541e-07 eta: 1 day, 3:42:53 time: 0.3303 data_time: 0.0021 memory: 10831 grad_norm: 3618.8694 loss: 226.0645 loss_cls: 83.8560 loss_bbox: 74.3576 loss_dfl: 67.8509 2024/12/22 02:09:14 - mmengine - INFO - Epoch(train) [1][ 800/7393] base_lr: 2.0000e-05 lr: 7.2050e-07 eta: 1 day, 3:40:15 time: 0.3306 data_time: 0.0021 memory: 10764 grad_norm: 3051.7382 loss: 226.5847 loss_cls: 83.5236 loss_bbox: 75.6917 loss_dfl: 67.3694 2024/12/22 02:09:31 - mmengine - INFO - Epoch(train) [1][ 850/7393] base_lr: 2.0000e-05 lr: 7.6559e-07 eta: 1 day, 3:38:04 time: 0.3312 data_time: 0.0021 memory: 11004 grad_norm: 3460.8376 loss: 226.6176 loss_cls: 83.7923 loss_bbox: 75.3965 loss_dfl: 67.4288 2024/12/22 02:09:48 - mmengine - INFO - Epoch(train) [1][ 900/7393] base_lr: 2.0000e-05 lr: 8.1068e-07 eta: 1 day, 3:36:11 time: 0.3315 data_time: 0.0021 memory: 11004 grad_norm: 2999.9362 loss: 227.5483 loss_cls: 82.7600 loss_bbox: 77.6120 loss_dfl: 67.1763 2024/12/22 02:10:04 - mmengine - INFO - Epoch(train) [1][ 950/7393] base_lr: 2.0000e-05 lr: 8.5576e-07 eta: 1 day, 3:34:28 time: 0.3315 data_time: 0.0021 memory: 11191 grad_norm: 3579.9888 loss: 227.3843 loss_cls: 84.5163 loss_bbox: 75.4736 loss_dfl: 67.3944 2024/12/22 02:10:21 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 02:10:21 - mmengine - INFO - Epoch(train) [1][1000/7393] base_lr: 2.0000e-05 lr: 9.0085e-07 eta: 1 day, 3:33:09 time: 0.3325 data_time: 0.0020 memory: 10938 grad_norm: 3219.3433 loss: 225.8352 loss_cls: 82.6835 loss_bbox: 75.6205 loss_dfl: 67.5312 2024/12/22 02:10:37 - mmengine - INFO - Epoch(train) [1][1050/7393] base_lr: 2.0000e-05 lr: 9.4594e-07 eta: 1 day, 3:31:50 time: 0.3321 data_time: 0.0021 memory: 10737 grad_norm: 2508.7966 loss: 228.4523 loss_cls: 83.7992 loss_bbox: 77.7431 loss_dfl: 66.9100 2024/12/22 02:10:54 - mmengine - INFO - Epoch(train) [1][1100/7393] base_lr: 2.0000e-05 lr: 9.9103e-07 eta: 1 day, 3:30:16 time: 0.3306 data_time: 0.0021 memory: 10831 grad_norm: 3482.7033 loss: 225.8350 loss_cls: 82.2201 loss_bbox: 76.4226 loss_dfl: 67.1923 2024/12/22 02:11:10 - mmengine - INFO - Epoch(train) [1][1150/7393] base_lr: 2.0000e-05 lr: 1.0361e-06 eta: 1 day, 3:29:00 time: 0.3315 data_time: 0.0020 memory: 10831 grad_norm: 2677.8257 loss: 225.7534 loss_cls: 82.4643 loss_bbox: 76.3669 loss_dfl: 66.9222 2024/12/22 02:11:27 - mmengine - INFO - Epoch(train) [1][1200/7393] base_lr: 2.0000e-05 lr: 1.0812e-06 eta: 1 day, 3:28:01 time: 0.3324 data_time: 0.0021 memory: 11045 grad_norm: 4055.8259 loss: 223.9616 loss_cls: 82.0265 loss_bbox: 74.4044 loss_dfl: 67.5307 2024/12/22 02:11:44 - mmengine - INFO - Epoch(train) [1][1250/7393] base_lr: 2.0000e-05 lr: 1.1263e-06 eta: 1 day, 3:27:03 time: 0.3322 data_time: 0.0021 memory: 10711 grad_norm: 2932.6942 loss: 224.2349 loss_cls: 81.9264 loss_bbox: 75.3179 loss_dfl: 66.9906 2024/12/22 02:12:00 - mmengine - INFO - Epoch(train) [1][1300/7393] base_lr: 2.0000e-05 lr: 1.1714e-06 eta: 1 day, 3:26:28 time: 0.3340 data_time: 0.0021 memory: 11378 grad_norm: 2802.0213 loss: 225.5923 loss_cls: 82.4882 loss_bbox: 76.2795 loss_dfl: 66.8246 2024/12/22 02:12:17 - mmengine - INFO - Epoch(train) [1][1350/7393] base_lr: 2.0000e-05 lr: 1.2165e-06 eta: 1 day, 3:25:38 time: 0.3324 data_time: 0.0020 memory: 11444 grad_norm: 2263.2086 loss: 225.5786 loss_cls: 82.0082 loss_bbox: 77.1531 loss_dfl: 66.4173 2024/12/22 02:12:34 - mmengine - INFO - Epoch(train) [1][1400/7393] base_lr: 2.0000e-05 lr: 1.2616e-06 eta: 1 day, 3:24:43 time: 0.3318 data_time: 0.0020 memory: 11404 grad_norm: 2484.2847 loss: 226.8933 loss_cls: 82.9827 loss_bbox: 77.2595 loss_dfl: 66.6511 2024/12/22 02:12:50 - mmengine - INFO - Epoch(train) [1][1450/7393] base_lr: 2.0000e-05 lr: 1.3066e-06 eta: 1 day, 3:23:29 time: 0.3297 data_time: 0.0021 memory: 10725 grad_norm: 3682.7107 loss: 225.6326 loss_cls: 83.8326 loss_bbox: 74.8890 loss_dfl: 66.9110 2024/12/22 02:13:07 - mmengine - INFO - Epoch(train) [1][1500/7393] base_lr: 2.0000e-05 lr: 1.3517e-06 eta: 1 day, 3:22:25 time: 0.3302 data_time: 0.0020 memory: 10871 grad_norm: 2586.9472 loss: 224.5953 loss_cls: 82.3053 loss_bbox: 75.9460 loss_dfl: 66.3440 2024/12/22 02:13:23 - mmengine - INFO - Epoch(train) [1][1550/7393] base_lr: 2.0000e-05 lr: 1.3968e-06 eta: 1 day, 3:21:28 time: 0.3308 data_time: 0.0020 memory: 10964 grad_norm: 2105.2493 loss: 223.3332 loss_cls: 81.8392 loss_bbox: 75.3502 loss_dfl: 66.1438 2024/12/22 02:13:40 - mmengine - INFO - Epoch(train) [1][1600/7393] base_lr: 2.0000e-05 lr: 1.4419e-06 eta: 1 day, 3:20:30 time: 0.3303 data_time: 0.0020 memory: 10804 grad_norm: 2115.2637 loss: 224.1799 loss_cls: 82.7911 loss_bbox: 75.5525 loss_dfl: 65.8363 2024/12/22 02:13:56 - mmengine - INFO - Epoch(train) [1][1650/7393] base_lr: 2.0000e-05 lr: 1.4870e-06 eta: 1 day, 3:19:39 time: 0.3307 data_time: 0.0020 memory: 10884 grad_norm: 2368.7809 loss: 224.1376 loss_cls: 82.1029 loss_bbox: 76.0298 loss_dfl: 66.0048 2024/12/22 02:14:13 - mmengine - INFO - Epoch(train) [1][1700/7393] base_lr: 2.0000e-05 lr: 1.5321e-06 eta: 1 day, 3:18:46 time: 0.3305 data_time: 0.0021 memory: 11004 grad_norm: 2588.7326 loss: 221.6713 loss_cls: 81.6670 loss_bbox: 74.3314 loss_dfl: 65.6729 2024/12/22 02:14:29 - mmengine - INFO - Epoch(train) [1][1750/7393] base_lr: 2.0000e-05 lr: 1.5772e-06 eta: 1 day, 3:18:08 time: 0.3319 data_time: 0.0021 memory: 11151 grad_norm: 2298.4319 loss: 219.1775 loss_cls: 81.9302 loss_bbox: 73.0775 loss_dfl: 64.1698 2024/12/22 02:14:46 - mmengine - INFO - Epoch(train) [1][1800/7393] base_lr: 2.0000e-05 lr: 1.6223e-06 eta: 1 day, 3:17:23 time: 0.3308 data_time: 0.0021 memory: 11124 grad_norm: 1849.7832 loss: 213.3179 loss_cls: 80.9543 loss_bbox: 72.8513 loss_dfl: 59.5123 2024/12/22 02:15:02 - mmengine - INFO - Epoch(train) [1][1850/7393] base_lr: 2.0000e-05 lr: 1.6673e-06 eta: 1 day, 3:16:40 time: 0.3310 data_time: 0.0021 memory: 11004 grad_norm: 1799.6727 loss: 209.8311 loss_cls: 80.9251 loss_bbox: 69.5448 loss_dfl: 59.3612 2024/12/22 02:15:19 - mmengine - INFO - Epoch(train) [1][1900/7393] base_lr: 2.0000e-05 lr: 1.7124e-06 eta: 1 day, 3:16:20 time: 0.3338 data_time: 0.0022 memory: 10764 grad_norm: 2535.2378 loss: 212.3219 loss_cls: 82.4163 loss_bbox: 70.3847 loss_dfl: 59.5209 2024/12/22 02:15:36 - mmengine - INFO - Epoch(train) [1][1950/7393] base_lr: 2.0000e-05 lr: 1.7575e-06 eta: 1 day, 3:15:52 time: 0.3326 data_time: 0.0020 memory: 10858 grad_norm: 2383.6654 loss: 211.4634 loss_cls: 82.6508 loss_bbox: 69.3644 loss_dfl: 59.4481 2024/12/22 02:15:52 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 02:15:52 - mmengine - INFO - Epoch(train) [1][2000/7393] base_lr: 2.0000e-05 lr: 1.8026e-06 eta: 1 day, 3:15:29 time: 0.3332 data_time: 0.0021 memory: 10857 grad_norm: 1982.7543 loss: 209.7819 loss_cls: 81.5232 loss_bbox: 68.9586 loss_dfl: 59.3001 2024/12/22 02:16:09 - mmengine - INFO - Epoch(train) [1][2050/7393] base_lr: 2.0000e-05 lr: 1.8477e-06 eta: 1 day, 3:14:59 time: 0.3323 data_time: 0.0021 memory: 11071 grad_norm: 1835.1815 loss: 210.6732 loss_cls: 82.2967 loss_bbox: 69.7766 loss_dfl: 58.5999 2024/12/22 02:16:26 - mmengine - INFO - Epoch(train) [1][2100/7393] base_lr: 2.0000e-05 lr: 1.8928e-06 eta: 1 day, 3:14:33 time: 0.3328 data_time: 0.0021 memory: 10911 grad_norm: 2273.7927 loss: 207.5663 loss_cls: 80.9352 loss_bbox: 67.7293 loss_dfl: 58.9018 2024/12/22 02:16:42 - mmengine - INFO - Epoch(train) [1][2150/7393] base_lr: 2.0000e-05 lr: 1.9379e-06 eta: 1 day, 3:14:13 time: 0.3335 data_time: 0.0021 memory: 11004 grad_norm: 1725.3272 loss: 203.7103 loss_cls: 80.0885 loss_bbox: 65.9965 loss_dfl: 57.6253 2024/12/22 02:16:59 - mmengine - INFO - Epoch(train) [1][2200/7393] base_lr: 2.0000e-05 lr: 1.9830e-06 eta: 1 day, 3:13:38 time: 0.3312 data_time: 0.0021 memory: 10911 grad_norm: 1990.9262 loss: 205.9876 loss_cls: 81.1622 loss_bbox: 67.6284 loss_dfl: 57.1970 2024/12/22 02:17:16 - mmengine - INFO - Epoch(train) [1][2250/7393] base_lr: 2.0000e-05 lr: 2.0280e-06 eta: 1 day, 3:12:59 time: 0.3306 data_time: 0.0021 memory: 10791 grad_norm: 1979.5896 loss: 205.5884 loss_cls: 80.8625 loss_bbox: 68.0942 loss_dfl: 56.6317 2024/12/22 02:17:32 - mmengine - INFO - Epoch(train) [1][2300/7393] base_lr: 2.0000e-05 lr: 2.0731e-06 eta: 1 day, 3:12:23 time: 0.3309 data_time: 0.0020 memory: 10697 grad_norm: 1843.3351 loss: 204.5671 loss_cls: 80.3483 loss_bbox: 67.4082 loss_dfl: 56.8105 2024/12/22 02:17:49 - mmengine - INFO - Epoch(train) [1][2350/7393] base_lr: 2.0000e-05 lr: 2.1182e-06 eta: 1 day, 3:11:52 time: 0.3314 data_time: 0.0020 memory: 10777 grad_norm: 1711.1847 loss: 204.4147 loss_cls: 80.6146 loss_bbox: 65.6720 loss_dfl: 58.1280 2024/12/22 02:18:05 - mmengine - INFO - Epoch(train) [1][2400/7393] base_lr: 2.0000e-05 lr: 2.1633e-06 eta: 1 day, 3:11:28 time: 0.3326 data_time: 0.0021 memory: 10884 grad_norm: 2131.2200 loss: 208.9559 loss_cls: 82.8184 loss_bbox: 68.3314 loss_dfl: 57.8061 2024/12/22 02:18:22 - mmengine - INFO - Epoch(train) [1][2450/7393] base_lr: 2.0000e-05 lr: 2.2084e-06 eta: 1 day, 3:11:04 time: 0.3325 data_time: 0.0020 memory: 10725 grad_norm: 2135.6754 loss: 204.8007 loss_cls: 80.3264 loss_bbox: 68.0100 loss_dfl: 56.4643 2024/12/22 02:18:39 - mmengine - INFO - Epoch(train) [1][2500/7393] base_lr: 2.0000e-05 lr: 2.2535e-06 eta: 1 day, 3:10:42 time: 0.3328 data_time: 0.0020 memory: 11111 grad_norm: 1855.4146 loss: 201.7877 loss_cls: 80.8918 loss_bbox: 63.8660 loss_dfl: 57.0299 2024/12/22 02:18:55 - mmengine - INFO - Epoch(train) [1][2550/7393] base_lr: 2.0000e-05 lr: 2.2986e-06 eta: 1 day, 3:10:18 time: 0.3325 data_time: 0.0020 memory: 10671 grad_norm: 1908.4909 loss: 203.8810 loss_cls: 82.2803 loss_bbox: 65.9139 loss_dfl: 55.6868 2024/12/22 02:19:12 - mmengine - INFO - Epoch(train) [1][2600/7393] base_lr: 2.0000e-05 lr: 2.3437e-06 eta: 1 day, 3:10:02 time: 0.3337 data_time: 0.0020 memory: 11084 grad_norm: 1708.0859 loss: 202.8741 loss_cls: 81.6419 loss_bbox: 64.4215 loss_dfl: 56.8108 2024/12/22 02:19:28 - mmengine - INFO - Epoch(train) [1][2650/7393] base_lr: 2.0000e-05 lr: 2.3887e-06 eta: 1 day, 3:09:35 time: 0.3318 data_time: 0.0021 memory: 11271 grad_norm: 1709.4796 loss: 200.1778 loss_cls: 80.9006 loss_bbox: 64.1141 loss_dfl: 55.1630 2024/12/22 02:19:45 - mmengine - INFO - Epoch(train) [1][2700/7393] base_lr: 2.0000e-05 lr: 2.4338e-06 eta: 1 day, 3:09:01 time: 0.3304 data_time: 0.0021 memory: 10951 grad_norm: 1722.7786 loss: 202.7663 loss_cls: 82.0634 loss_bbox: 65.2151 loss_dfl: 55.4878 2024/12/22 02:20:02 - mmengine - INFO - Epoch(train) [1][2750/7393] base_lr: 2.0000e-05 lr: 2.4789e-06 eta: 1 day, 3:08:34 time: 0.3317 data_time: 0.0022 memory: 10857 grad_norm: 1624.2238 loss: 200.2241 loss_cls: 80.4383 loss_bbox: 64.8667 loss_dfl: 54.9191 2024/12/22 02:20:18 - mmengine - INFO - Epoch(train) [1][2800/7393] base_lr: 2.0000e-05 lr: 2.5240e-06 eta: 1 day, 3:08:03 time: 0.3307 data_time: 0.0020 memory: 10791 grad_norm: 2084.4588 loss: 202.2110 loss_cls: 82.7597 loss_bbox: 63.7609 loss_dfl: 55.6904 2024/12/22 02:20:35 - mmengine - INFO - Epoch(train) [1][2850/7393] base_lr: 2.0000e-05 lr: 2.5691e-06 eta: 1 day, 3:07:35 time: 0.3313 data_time: 0.0021 memory: 10804 grad_norm: 1688.2451 loss: 200.7796 loss_cls: 81.1979 loss_bbox: 63.3880 loss_dfl: 56.1937 2024/12/22 02:20:51 - mmengine - INFO - Epoch(train) [1][2900/7393] base_lr: 2.0000e-05 lr: 2.6142e-06 eta: 1 day, 3:07:04 time: 0.3308 data_time: 0.0020 memory: 11111 grad_norm: 1666.0263 loss: 198.5188 loss_cls: 80.5829 loss_bbox: 64.3370 loss_dfl: 53.5989 2024/12/22 02:21:08 - mmengine - INFO - Epoch(train) [1][2950/7393] base_lr: 2.0000e-05 lr: 2.6593e-06 eta: 1 day, 3:06:34 time: 0.3307 data_time: 0.0021 memory: 10951 grad_norm: 1512.9920 loss: 198.6969 loss_cls: 80.9531 loss_bbox: 63.8034 loss_dfl: 53.9404 2024/12/22 02:21:24 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 02:21:24 - mmengine - INFO - Epoch(train) [1][3000/7393] base_lr: 2.0000e-05 lr: 2.7044e-06 eta: 1 day, 3:06:09 time: 0.3315 data_time: 0.0021 memory: 10924 grad_norm: 1886.5480 loss: 198.5989 loss_cls: 81.2458 loss_bbox: 62.1866 loss_dfl: 55.1664 2024/12/22 02:21:41 - mmengine - INFO - Epoch(train) [1][3050/7393] base_lr: 2.0000e-05 lr: 2.7494e-06 eta: 1 day, 3:05:50 time: 0.3328 data_time: 0.0021 memory: 10791 grad_norm: 1668.0699 loss: 198.9534 loss_cls: 81.5167 loss_bbox: 63.9881 loss_dfl: 53.4486 2024/12/22 02:21:58 - mmengine - INFO - Epoch(train) [1][3100/7393] base_lr: 2.0000e-05 lr: 2.7945e-06 eta: 1 day, 3:05:33 time: 0.3333 data_time: 0.0021 memory: 10884 grad_norm: 1559.4512 loss: 198.7496 loss_cls: 81.0054 loss_bbox: 63.1867 loss_dfl: 54.5574 2024/12/22 02:22:14 - mmengine - INFO - Epoch(train) [1][3150/7393] base_lr: 2.0000e-05 lr: 2.8396e-06 eta: 1 day, 3:05:14 time: 0.3329 data_time: 0.0021 memory: 11164 grad_norm: 1467.3551 loss: 198.4601 loss_cls: 81.6162 loss_bbox: 63.5808 loss_dfl: 53.2631 2024/12/22 02:22:31 - mmengine - INFO - Epoch(train) [1][3200/7393] base_lr: 2.0000e-05 lr: 2.8847e-06 eta: 1 day, 3:04:55 time: 0.3327 data_time: 0.0020 memory: 11057 grad_norm: 1513.6005 loss: 202.7838 loss_cls: 85.2018 loss_bbox: 62.6829 loss_dfl: 54.8991 2024/12/22 02:22:48 - mmengine - INFO - Epoch(train) [1][3250/7393] base_lr: 2.0000e-05 lr: 2.9298e-06 eta: 1 day, 3:04:36 time: 0.3329 data_time: 0.0021 memory: 10897 grad_norm: 1515.5001 loss: 197.0824 loss_cls: 80.2620 loss_bbox: 62.7894 loss_dfl: 54.0310 2024/12/22 02:23:04 - mmengine - INFO - Epoch(train) [1][3300/7393] base_lr: 2.0000e-05 lr: 2.9749e-06 eta: 1 day, 3:04:19 time: 0.3332 data_time: 0.0021 memory: 10951 grad_norm: 1546.9805 loss: 194.0314 loss_cls: 79.8462 loss_bbox: 61.4248 loss_dfl: 52.7604 2024/12/22 02:23:21 - mmengine - INFO - Epoch(train) [1][3350/7393] base_lr: 2.0000e-05 lr: 3.0200e-06 eta: 1 day, 3:03:57 time: 0.3321 data_time: 0.0020 memory: 10938 grad_norm: 1605.8047 loss: 194.2314 loss_cls: 80.9866 loss_bbox: 61.4474 loss_dfl: 51.7973 2024/12/22 02:23:38 - mmengine - INFO - Epoch(train) [1][3400/7393] base_lr: 2.0000e-05 lr: 3.0651e-06 eta: 1 day, 3:03:39 time: 0.3328 data_time: 0.0021 memory: 11004 grad_norm: 1634.1136 loss: 194.3646 loss_cls: 80.6825 loss_bbox: 61.3024 loss_dfl: 52.3797 2024/12/22 02:23:54 - mmengine - INFO - Epoch(train) [1][3450/7393] base_lr: 2.0000e-05 lr: 3.1101e-06 eta: 1 day, 3:03:18 time: 0.3323 data_time: 0.0021 memory: 10844 grad_norm: 1650.1961 loss: 195.2536 loss_cls: 81.4940 loss_bbox: 60.1606 loss_dfl: 53.5990 2024/12/22 02:24:11 - mmengine - INFO - Epoch(train) [1][3500/7393] base_lr: 2.0000e-05 lr: 3.1552e-06 eta: 1 day, 3:02:55 time: 0.3318 data_time: 0.0021 memory: 10884 grad_norm: 1416.6196 loss: 195.6273 loss_cls: 80.7711 loss_bbox: 62.4880 loss_dfl: 52.3682 2024/12/22 02:24:27 - mmengine - INFO - Epoch(train) [1][3550/7393] base_lr: 2.0000e-05 lr: 3.2003e-06 eta: 1 day, 3:02:33 time: 0.3319 data_time: 0.0021 memory: 10911 grad_norm: 1508.6765 loss: 194.7619 loss_cls: 80.8982 loss_bbox: 60.6302 loss_dfl: 53.2335 2024/12/22 02:24:44 - mmengine - INFO - Epoch(train) [1][3600/7393] base_lr: 2.0000e-05 lr: 3.2454e-06 eta: 1 day, 3:02:13 time: 0.3325 data_time: 0.0021 memory: 10684 grad_norm: 1311.3632 loss: 192.9495 loss_cls: 80.6177 loss_bbox: 59.1900 loss_dfl: 53.1418 2024/12/22 02:25:01 - mmengine - INFO - Epoch(train) [1][3650/7393] base_lr: 2.0000e-05 lr: 3.2905e-06 eta: 1 day, 3:01:54 time: 0.3326 data_time: 0.0020 memory: 10951 grad_norm: 1250.5658 loss: 195.2147 loss_cls: 80.5891 loss_bbox: 61.9206 loss_dfl: 52.7049 2024/12/22 02:25:17 - mmengine - INFO - Epoch(train) [1][3700/7393] base_lr: 2.0000e-05 lr: 3.3356e-06 eta: 1 day, 3:01:35 time: 0.3326 data_time: 0.0021 memory: 11231 grad_norm: 1475.5251 loss: 191.4226 loss_cls: 80.5258 loss_bbox: 59.9299 loss_dfl: 50.9669 2024/12/22 02:25:34 - mmengine - INFO - Epoch(train) [1][3750/7393] base_lr: 2.0000e-05 lr: 3.3807e-06 eta: 1 day, 3:01:15 time: 0.3322 data_time: 0.0020 memory: 10991 grad_norm: 1138.4882 loss: 193.4638 loss_cls: 79.8703 loss_bbox: 61.1772 loss_dfl: 52.4163 2024/12/22 02:25:50 - mmengine - INFO - Epoch(train) [1][3800/7393] base_lr: 2.0000e-05 lr: 3.4258e-06 eta: 1 day, 3:00:55 time: 0.3323 data_time: 0.0020 memory: 10844 grad_norm: 1066.2811 loss: 192.8543 loss_cls: 79.7846 loss_bbox: 60.9232 loss_dfl: 52.1464 2024/12/22 02:26:07 - mmengine - INFO - Epoch(train) [1][3850/7393] base_lr: 2.0000e-05 lr: 3.4709e-06 eta: 1 day, 3:00:34 time: 0.3322 data_time: 0.0020 memory: 10844 grad_norm: 1238.1206 loss: 192.5326 loss_cls: 80.3673 loss_bbox: 59.3571 loss_dfl: 52.8082 2024/12/22 02:26:24 - mmengine - INFO - Epoch(train) [1][3900/7393] base_lr: 2.0000e-05 lr: 3.5159e-06 eta: 1 day, 3:00:15 time: 0.3324 data_time: 0.0021 memory: 10991 grad_norm: 1176.2235 loss: 193.7142 loss_cls: 81.6259 loss_bbox: 59.8001 loss_dfl: 52.2881 2024/12/22 02:26:40 - mmengine - INFO - Epoch(train) [1][3950/7393] base_lr: 2.0000e-05 lr: 3.5610e-06 eta: 1 day, 2:59:55 time: 0.3322 data_time: 0.0020 memory: 10897 grad_norm: 1097.9676 loss: 191.7840 loss_cls: 80.8968 loss_bbox: 59.2651 loss_dfl: 51.6222 2024/12/22 02:26:57 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 02:26:57 - mmengine - INFO - Epoch(train) [1][4000/7393] base_lr: 2.0000e-05 lr: 3.6061e-06 eta: 1 day, 2:59:37 time: 0.3329 data_time: 0.0020 memory: 10857 grad_norm: 959.0095 loss: 190.2113 loss_cls: 79.9854 loss_bbox: 57.9425 loss_dfl: 52.2834 2024/12/22 02:27:14 - mmengine - INFO - Epoch(train) [1][4050/7393] base_lr: 2.0000e-05 lr: 3.6512e-06 eta: 1 day, 2:59:21 time: 0.3332 data_time: 0.0021 memory: 10777 grad_norm: 1159.6944 loss: 193.0529 loss_cls: 82.1441 loss_bbox: 60.6596 loss_dfl: 50.2491 2024/12/22 02:27:30 - mmengine - INFO - Epoch(train) [1][4100/7393] base_lr: 2.0000e-05 lr: 3.6963e-06 eta: 1 day, 2:59:03 time: 0.3328 data_time: 0.0021 memory: 10897 grad_norm: 1186.7308 loss: 191.9419 loss_cls: 80.7763 loss_bbox: 60.1611 loss_dfl: 51.0044 2024/12/22 02:27:47 - mmengine - INFO - Epoch(train) [1][4150/7393] base_lr: 2.0000e-05 lr: 3.7414e-06 eta: 1 day, 2:58:48 time: 0.3336 data_time: 0.0021 memory: 10791 grad_norm: 922.4930 loss: 191.4768 loss_cls: 81.0165 loss_bbox: 60.3677 loss_dfl: 50.0926 2024/12/22 02:28:03 - mmengine - INFO - Epoch(train) [1][4200/7393] base_lr: 2.0000e-05 lr: 3.7865e-06 eta: 1 day, 2:58:24 time: 0.3309 data_time: 0.0021 memory: 11271 grad_norm: 1209.5323 loss: 192.2158 loss_cls: 80.3406 loss_bbox: 59.3573 loss_dfl: 52.5179 2024/12/22 02:28:20 - mmengine - INFO - Epoch(train) [1][4250/7393] base_lr: 2.0000e-05 lr: 3.8316e-06 eta: 1 day, 2:58:00 time: 0.3310 data_time: 0.0021 memory: 10831 grad_norm: 1175.7538 loss: 190.0884 loss_cls: 80.4599 loss_bbox: 57.5674 loss_dfl: 52.0611 2024/12/22 02:28:37 - mmengine - INFO - Epoch(train) [1][4300/7393] base_lr: 2.0000e-05 lr: 3.8766e-06 eta: 1 day, 2:57:35 time: 0.3307 data_time: 0.0020 memory: 10725 grad_norm: 1077.2793 loss: 190.1158 loss_cls: 79.9043 loss_bbox: 59.8025 loss_dfl: 50.4089 2024/12/22 02:28:53 - mmengine - INFO - Epoch(train) [1][4350/7393] base_lr: 2.0000e-05 lr: 3.9217e-06 eta: 1 day, 2:57:13 time: 0.3314 data_time: 0.0021 memory: 11297 grad_norm: 1167.5190 loss: 190.9251 loss_cls: 79.9599 loss_bbox: 60.8756 loss_dfl: 50.0896 2024/12/22 02:29:10 - mmengine - INFO - Epoch(train) [1][4400/7393] base_lr: 2.0000e-05 lr: 3.9668e-06 eta: 1 day, 2:56:51 time: 0.3315 data_time: 0.0021 memory: 11045 grad_norm: 976.6406 loss: 190.6330 loss_cls: 80.2315 loss_bbox: 59.4568 loss_dfl: 50.9447 2024/12/22 02:29:26 - mmengine - INFO - Epoch(train) [1][4450/7393] base_lr: 2.0000e-05 lr: 4.0119e-06 eta: 1 day, 2:56:27 time: 0.3307 data_time: 0.0021 memory: 10964 grad_norm: 833.9081 loss: 193.8172 loss_cls: 81.9131 loss_bbox: 60.2706 loss_dfl: 51.6335 2024/12/22 02:29:43 - mmengine - INFO - Epoch(train) [1][4500/7393] base_lr: 2.0000e-05 lr: 4.0570e-06 eta: 1 day, 2:56:05 time: 0.3314 data_time: 0.0021 memory: 10804 grad_norm: 790.9243 loss: 189.6661 loss_cls: 80.4563 loss_bbox: 59.2819 loss_dfl: 49.9278 2024/12/22 02:30:00 - mmengine - INFO - Epoch(train) [1][4550/7393] base_lr: 2.0000e-05 lr: 4.1021e-06 eta: 1 day, 2:55:48 time: 0.3329 data_time: 0.0020 memory: 11097 grad_norm: 797.8231 loss: 191.0073 loss_cls: 81.0654 loss_bbox: 59.3487 loss_dfl: 50.5932 2024/12/22 02:30:16 - mmengine - INFO - Epoch(train) [1][4600/7393] base_lr: 2.0000e-05 lr: 4.1472e-06 eta: 1 day, 2:55:31 time: 0.3327 data_time: 0.0021 memory: 11031 grad_norm: 812.1104 loss: 188.7648 loss_cls: 80.4544 loss_bbox: 58.0714 loss_dfl: 50.2390 2024/12/22 02:30:33 - mmengine - INFO - Epoch(train) [1][4650/7393] base_lr: 2.0000e-05 lr: 4.1923e-06 eta: 1 day, 2:55:10 time: 0.3314 data_time: 0.0021 memory: 10697 grad_norm: 1026.0152 loss: 191.2947 loss_cls: 82.2385 loss_bbox: 58.5777 loss_dfl: 50.4786 2024/12/22 02:30:49 - mmengine - INFO - Epoch(train) [1][4700/7393] base_lr: 2.0000e-05 lr: 4.2373e-06 eta: 1 day, 2:54:53 time: 0.3329 data_time: 0.0021 memory: 10938 grad_norm: 802.5755 loss: 189.7904 loss_cls: 80.9877 loss_bbox: 58.2975 loss_dfl: 50.5052 2024/12/22 02:31:06 - mmengine - INFO - Epoch(train) [1][4750/7393] base_lr: 2.0000e-05 lr: 4.2824e-06 eta: 1 day, 2:54:36 time: 0.3328 data_time: 0.0021 memory: 10764 grad_norm: 769.3491 loss: 189.4393 loss_cls: 80.6267 loss_bbox: 59.2714 loss_dfl: 49.5412 2024/12/22 02:31:23 - mmengine - INFO - Epoch(train) [1][4800/7393] base_lr: 2.0000e-05 lr: 4.3275e-06 eta: 1 day, 2:54:19 time: 0.3330 data_time: 0.0021 memory: 11045 grad_norm: 963.3564 loss: 188.3040 loss_cls: 80.1638 loss_bbox: 59.3247 loss_dfl: 48.8156 2024/12/22 02:31:39 - mmengine - INFO - Epoch(train) [1][4850/7393] base_lr: 2.0000e-05 lr: 4.3726e-06 eta: 1 day, 2:54:05 time: 0.3337 data_time: 0.0021 memory: 10911 grad_norm: 893.3526 loss: 190.4773 loss_cls: 81.2331 loss_bbox: 58.9610 loss_dfl: 50.2832 2024/12/22 02:31:56 - mmengine - INFO - Epoch(train) [1][4900/7393] base_lr: 2.0000e-05 lr: 4.4177e-06 eta: 1 day, 2:53:47 time: 0.3326 data_time: 0.0021 memory: 10924 grad_norm: 738.7605 loss: 188.0946 loss_cls: 80.0925 loss_bbox: 58.6534 loss_dfl: 49.3487 2024/12/22 02:32:13 - mmengine - INFO - Epoch(train) [1][4950/7393] base_lr: 2.0000e-05 lr: 4.4628e-06 eta: 1 day, 2:53:31 time: 0.3331 data_time: 0.0021 memory: 11097 grad_norm: 829.6335 loss: 186.5377 loss_cls: 80.3070 loss_bbox: 57.1037 loss_dfl: 49.1269 2024/12/22 02:32:29 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 02:32:29 - mmengine - INFO - Epoch(train) [1][5000/7393] base_lr: 2.0000e-05 lr: 4.5079e-06 eta: 1 day, 2:53:15 time: 0.3332 data_time: 0.0021 memory: 11004 grad_norm: 788.5021 loss: 186.7487 loss_cls: 79.5116 loss_bbox: 57.7408 loss_dfl: 49.4963 2024/12/22 02:32:46 - mmengine - INFO - Epoch(train) [1][5050/7393] base_lr: 2.0000e-05 lr: 4.5530e-06 eta: 1 day, 2:52:52 time: 0.3307 data_time: 0.0020 memory: 10725 grad_norm: 749.7857 loss: 187.2431 loss_cls: 80.1263 loss_bbox: 59.1383 loss_dfl: 47.9786 2024/12/22 02:33:02 - mmengine - INFO - Epoch(train) [1][5100/7393] base_lr: 2.0000e-05 lr: 4.5980e-06 eta: 1 day, 2:52:32 time: 0.3316 data_time: 0.0021 memory: 10844 grad_norm: 719.1904 loss: 190.1660 loss_cls: 80.5627 loss_bbox: 60.3933 loss_dfl: 49.2101 2024/12/22 02:33:19 - mmengine - INFO - Epoch(train) [1][5150/7393] base_lr: 2.0000e-05 lr: 4.6431e-06 eta: 1 day, 2:52:11 time: 0.3313 data_time: 0.0021 memory: 10657 grad_norm: 683.7227 loss: 186.4765 loss_cls: 80.8792 loss_bbox: 56.8206 loss_dfl: 48.7766 2024/12/22 02:33:36 - mmengine - INFO - Epoch(train) [1][5200/7393] base_lr: 2.0000e-05 lr: 4.6882e-06 eta: 1 day, 2:51:48 time: 0.3307 data_time: 0.0021 memory: 10844 grad_norm: 747.9684 loss: 188.0868 loss_cls: 81.5853 loss_bbox: 58.0770 loss_dfl: 48.4245 2024/12/22 02:33:52 - mmengine - INFO - Epoch(train) [1][5250/7393] base_lr: 2.0000e-05 lr: 4.7333e-06 eta: 1 day, 2:51:26 time: 0.3310 data_time: 0.0021 memory: 10737 grad_norm: 697.0643 loss: 185.7754 loss_cls: 79.4756 loss_bbox: 57.7599 loss_dfl: 48.5399 2024/12/22 02:34:09 - mmengine - INFO - Epoch(train) [1][5300/7393] base_lr: 2.0000e-05 lr: 4.7784e-06 eta: 1 day, 2:51:05

2024/12/22 05:27:46 - mmengine - INFO - Epoch(train) [5][7100/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:53:38 time: 0.3311 data_time: 0.0008 memory: 10926 grad_norm: 338.3706 loss: 142.5298 loss_cls: 69.8546 loss_bbox: 42.1329 loss_dfl: 30.5423 2024/12/22 05:28:02 - mmengine - INFO - Epoch(train) [5][7150/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:53:21 time: 0.3310 data_time: 0.0007 memory: 10873 grad_norm: 334.9445 loss: 145.6780 loss_cls: 71.4241 loss_bbox: 41.9351 loss_dfl: 32.3188 2024/12/22 05:28:19 - mmengine - INFO - Epoch(train) [5][7200/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:53:04 time: 0.3314 data_time: 0.0008 memory: 10819 grad_norm: 316.0872 loss: 143.7141 loss_cls: 70.0146 loss_bbox: 42.6146 loss_dfl: 31.0850 2024/12/22 05:28:36 - mmengine - INFO - Epoch(train) [5][7250/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:52:48 time: 0.3313 data_time: 0.0008 memory: 10739 grad_norm: 349.7256 loss: 145.4753 loss_cls: 70.2169 loss_bbox: 42.4078 loss_dfl: 32.8505 2024/12/22 05:28:52 - mmengine - INFO - Epoch(train) [5][7300/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:52:31 time: 0.3313 data_time: 0.0008 memory: 11193 grad_norm: 336.5209 loss: 144.5216 loss_cls: 70.4595 loss_bbox: 42.3880 loss_dfl: 31.6741 2024/12/22 05:29:09 - mmengine - INFO - Epoch(train) [5][7350/7393] base_lr: 2.0000e-05 lr: 1.8515e-05 eta: 23:52:14 time: 0.3315 data_time: 0.0008 memory: 10847 grad_norm: 310.6853 loss: 142.6537 loss_cls: 69.5065 loss_bbox: 41.8613 loss_dfl: 31.2858 2024/12/22 05:29:23 - mmengine - INFO - Exp name: yolo_world_v2_l_vlpan_bn_sgd_1e-3_40e_8gpus_finetune_coco_20241222_020422 2024/12/22 05:29:23 - mmengine - INFO - Saving checkpoint at 5 epochs 2024/12/22 05:29:24 - mmengine - WARNING - save_param_scheduler is True but self.param_schedulers is None, so skip saving parameter schedulers 2024/12/22 05:29:29 - mmengine - INFO - Epoch(val) [5][ 50/5000] eta: 0:05:18 time: 0.0643 data_time: 0.0030 memory: 10793
2024/12/22 05:29:32 - mmengine - INFO - Epoch(val) [5][ 100/5000] eta: 0:04:55 time: 0.0563 data_time: 0.0001 memory: 1445
2024/12/22 05:29:34 - mmengine - INFO - Epoch(val) [5][ 150/5000] eta: 0:04:46 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:37 - mmengine - INFO - Epoch(val) [5][ 200/5000] eta: 0:04:40 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:40 - mmengine - INFO - Epoch(val) [5][ 250/5000] eta: 0:04:35 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:43 - mmengine - INFO - Epoch(val) [5][ 300/5000] eta: 0:04:31 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:46 - mmengine - INFO - Epoch(val) [5][ 350/5000] eta: 0:04:27 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:48 - mmengine - INFO - Epoch(val) [5][ 400/5000] eta: 0:04:23 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:51 - mmengine - INFO - Epoch(val) [5][ 450/5000] eta: 0:04:20 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:54 - mmengine - INFO - Epoch(val) [5][ 500/5000] eta: 0:04:17 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:29:57 - mmengine - INFO - Epoch(val) [5][ 550/5000] eta: 0:04:14 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:00 - mmengine - INFO - Epoch(val) [5][ 600/5000] eta: 0:04:10 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:03 - mmengine - INFO - Epoch(val) [5][ 650/5000] eta: 0:04:07 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:05 - mmengine - INFO - Epoch(val) [5][ 700/5000] eta: 0:04:04 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:08 - mmengine - INFO - Epoch(val) [5][ 750/5000] eta: 0:04:01 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:11 - mmengine - INFO - Epoch(val) [5][ 800/5000] eta: 0:03:58 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:14 - mmengine - INFO - Epoch(val) [5][ 850/5000] eta: 0:03:55 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:17 - mmengine - INFO - Epoch(val) [5][ 900/5000] eta: 0:03:52 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:20 - mmengine - INFO - Epoch(val) [5][ 950/5000] eta: 0:03:50 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:22 - mmengine - INFO - Epoch(val) [5][1000/5000] eta: 0:03:47 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:25 - mmengine - INFO - Epoch(val) [5][1050/5000] eta: 0:03:44 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:28 - mmengine - INFO - Epoch(val) [5][1100/5000] eta: 0:03:41 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:31 - mmengine - INFO - Epoch(val) [5][1150/5000] eta: 0:03:38 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:34 - mmengine - INFO - Epoch(val) [5][1200/5000] eta: 0:03:35 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:36 - mmengine - INFO - Epoch(val) [5][1250/5000] eta: 0:03:32 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:39 - mmengine - INFO - Epoch(val) [5][1300/5000] eta: 0:03:29 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:42 - mmengine - INFO - Epoch(val) [5][1350/5000] eta: 0:03:26 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:30:45 - mmengine - INFO - Epoch(val) [5][1400/5000] eta: 0:03:23 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:48 - mmengine - INFO - Epoch(val) [5][1450/5000] eta: 0:03:21 time: 0.0565 data_time: 0.0002 memory: 1445
2024/12/22 05:30:51 - mmengine - INFO - Epoch(val) [5][1500/5000] eta: 0:03:18 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:53 - mmengine - INFO - Epoch(val) [5][1550/5000] eta: 0:03:15 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:56 - mmengine - INFO - Epoch(val) [5][1600/5000] eta: 0:03:12 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:30:59 - mmengine - INFO - Epoch(val) [5][1650/5000] eta: 0:03:09 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:02 - mmengine - INFO - Epoch(val) [5][1700/5000] eta: 0:03:06 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:05 - mmengine - INFO - Epoch(val) [5][1750/5000] eta: 0:03:04 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:08 - mmengine - INFO - Epoch(val) [5][1800/5000] eta: 0:03:01 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:10 - mmengine - INFO - Epoch(val) [5][1850/5000] eta: 0:02:58 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:13 - mmengine - INFO - Epoch(val) [5][1900/5000] eta: 0:02:55 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:16 - mmengine - INFO - Epoch(val) [5][1950/5000] eta: 0:02:52 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:19 - mmengine - INFO - Epoch(val) [5][2000/5000] eta: 0:02:49 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:31:22 - mmengine - INFO - Epoch(val) [5][2050/5000] eta: 0:02:46 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:31:24 - mmengine - INFO - Epoch(val) [5][2100/5000] eta: 0:02:44 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:27 - mmengine - INFO - Epoch(val) [5][2150/5000] eta: 0:02:41 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:30 - mmengine - INFO - Epoch(val) [5][2200/5000] eta: 0:02:38 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:33 - mmengine - INFO - Epoch(val) [5][2250/5000] eta: 0:02:35 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:36 - mmengine - INFO - Epoch(val) [5][2300/5000] eta: 0:02:32 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:39 - mmengine - INFO - Epoch(val) [5][2350/5000] eta: 0:02:29 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:41 - mmengine - INFO - Epoch(val) [5][2400/5000] eta: 0:02:27 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:44 - mmengine - INFO - Epoch(val) [5][2450/5000] eta: 0:02:24 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:47 - mmengine - INFO - Epoch(val) [5][2500/5000] eta: 0:02:21 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:50 - mmengine - INFO - Epoch(val) [5][2550/5000] eta: 0:02:18 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:53 - mmengine - INFO - Epoch(val) [5][2600/5000] eta: 0:02:15 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:56 - mmengine - INFO - Epoch(val) [5][2650/5000] eta: 0:02:12 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:31:58 - mmengine - INFO - Epoch(val) [5][2700/5000] eta: 0:02:10 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:01 - mmengine - INFO - Epoch(val) [5][2750/5000] eta: 0:02:07 time: 0.0565 data_time: 0.0002 memory: 1445
2024/12/22 05:32:04 - mmengine - INFO - Epoch(val) [5][2800/5000] eta: 0:02:04 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:07 - mmengine - INFO - Epoch(val) [5][2850/5000] eta: 0:02:01 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:32:10 - mmengine - INFO - Epoch(val) [5][2900/5000] eta: 0:01:58 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:12 - mmengine - INFO - Epoch(val) [5][2950/5000] eta: 0:01:55 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:15 - mmengine - INFO - Epoch(val) [5][3000/5000] eta: 0:01:53 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:18 - mmengine - INFO - Epoch(val) [5][3050/5000] eta: 0:01:50 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:32:21 - mmengine - INFO - Epoch(val) [5][3100/5000] eta: 0:01:47 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:24 - mmengine - INFO - Epoch(val) [5][3150/5000] eta: 0:01:44 time: 0.0565 data_time: 0.0002 memory: 1445
2024/12/22 05:32:27 - mmengine - INFO - Epoch(val) [5][3200/5000] eta: 0:01:41 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:29 - mmengine - INFO - Epoch(val) [5][3250/5000] eta: 0:01:38 time: 0.0565 data_time: 0.0002 memory: 1445
2024/12/22 05:32:32 - mmengine - INFO - Epoch(val) [5][3300/5000] eta: 0:01:36 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:32:35 - mmengine - INFO - Epoch(val) [5][3350/5000] eta: 0:01:33 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:38 - mmengine - INFO - Epoch(val) [5][3400/5000] eta: 0:01:30 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:41 - mmengine - INFO - Epoch(val) [5][3450/5000] eta: 0:01:27 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:44 - mmengine - INFO - Epoch(val) [5][3500/5000] eta: 0:01:24 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:46 - mmengine - INFO - Epoch(val) [5][3550/5000] eta: 0:01:21 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:49 - mmengine - INFO - Epoch(val) [5][3600/5000] eta: 0:01:19 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:52 - mmengine - INFO - Epoch(val) [5][3650/5000] eta: 0:01:16 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:55 - mmengine - INFO - Epoch(val) [5][3700/5000] eta: 0:01:13 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:32:58 - mmengine - INFO - Epoch(val) [5][3750/5000] eta: 0:01:10 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:01 - mmengine - INFO - Epoch(val) [5][3800/5000] eta: 0:01:07 time: 0.0565 data_time: 0.0002 memory: 1445
2024/12/22 05:33:03 - mmengine - INFO - Epoch(val) [5][3850/5000] eta: 0:01:04 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:06 - mmengine - INFO - Epoch(val) [5][3900/5000] eta: 0:01:02 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:09 - mmengine - INFO - Epoch(val) [5][3950/5000] eta: 0:00:59 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:12 - mmengine - INFO - Epoch(val) [5][4000/5000] eta: 0:00:56 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:33:15 - mmengine - INFO - Epoch(val) [5][4050/5000] eta: 0:00:53 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:17 - mmengine - INFO - Epoch(val) [5][4100/5000] eta: 0:00:50 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:33:20 - mmengine - INFO - Epoch(val) [5][4150/5000] eta: 0:00:48 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:33:23 - mmengine - INFO - Epoch(val) [5][4200/5000] eta: 0:00:45 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:26 - mmengine - INFO - Epoch(val) [5][4250/5000] eta: 0:00:42 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:29 - mmengine - INFO - Epoch(val) [5][4300/5000] eta: 0:00:39 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:32 - mmengine - INFO - Epoch(val) [5][4350/5000] eta: 0:00:36 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:34 - mmengine - INFO - Epoch(val) [5][4400/5000] eta: 0:00:33 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:33:37 - mmengine - INFO - Epoch(val) [5][4450/5000] eta: 0:00:31 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:40 - mmengine - INFO - Epoch(val) [5][4500/5000] eta: 0:00:28 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:43 - mmengine - INFO - Epoch(val) [5][4550/5000] eta: 0:00:25 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:46 - mmengine - INFO - Epoch(val) [5][4600/5000] eta: 0:00:22 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:49 - mmengine - INFO - Epoch(val) [5][4650/5000] eta: 0:00:19 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:51 - mmengine - INFO - Epoch(val) [5][4700/5000] eta: 0:00:16 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:54 - mmengine - INFO - Epoch(val) [5][4750/5000] eta: 0:00:14 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:33:57 - mmengine - INFO - Epoch(val) [5][4800/5000] eta: 0:00:11 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:34:00 - mmengine - INFO - Epoch(val) [5][4850/5000] eta: 0:00:08 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:34:03 - mmengine - INFO - Epoch(val) [5][4900/5000] eta: 0:00:05 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:34:05 - mmengine - INFO - Epoch(val) [5][4950/5000] eta: 0:00:02 time: 0.0564 data_time: 0.0001 memory: 1445
2024/12/22 05:34:08 - mmengine - INFO - Epoch(val) [5][5000/5000] eta: 0:00:00 time: 0.0564 data_time: 0.0002 memory: 1445
2024/12/22 05:34:08 - mmengine - INFO - Evaluating bbox... 2024/12/22 05:34:12 - mmengine - INFO - bbox_mAP_copypaste: 0.000 0.000 0.000 0.000 0.000 0.000 2024/12/22 05:34:12 - mmengine - INFO - Epoch(val) [5][5000/5000] coco/bbox_mAP: 0.0000 coco/bbox_mAP_50: 0.0000
2024/12/23 00:11:01 - mmengine - INFO - Saving checkpoint at 30 epochs 2024/12/23 00:11:07 - mmengine - INFO - Epoch(val) [30][ 50/5000] eta: 0:04:40 time: 0.0566 data_time: 0.0004 memory: 10400
. . 2024/12/23 07:48:28 - mmengine - INFO - Evaluating bbox... 2024/12/23 07:48:32 - mmengine - INFO - bbox_mAP_copypaste: 0.000 0.000 0.000 0.000 0.000 0.000 2024/12/23 07:48:32 - mmengine - INFO - Epoch(val) [40][5000/5000] coco/bbox_mAP: 0.0000 coco/bbox_mAP_50: 0.0000 coco/bbox_mAP_75: 0.0000 coco/bbox_mAP_s: 0.0000 coco/bbox_mAP_m: 0.0000 coco/bbox_mAP_l: 0.0000 data_time: 0.0002 time: 0.0566 `

[ycyg8]

I also encountered the same problem, did you solve it?

[Vireakdara]

trying to check the dataset for me it's the code part that I try to modify myself

[aoji0606]

i have the same problem

[M3Dade]

the same problem

[doilion]

the same problem

[connorye]

fix by in coco dataset category should follow the same order in the class_name in config file and category_id should start at 0

[connorye]

also add metainfo in train loader dataset and val too.Same issue mentioned.u can check it