Initial commit

configs/finetune_coco/yolo_world_v2_s_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'], allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 80
+num_training_classes = 80
+max_epochs = 80  # Maximum training epochs
+close_mosaic_epochs = 10
+save_epoch_intervals = 5
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.05
+train_batch_size_per_gpu = 16
+load_from = '../FastDet/output_models/pretrain_yolow-v8_s_clipv2_frozen_te_noprompt_t2i_bn_2e-3adamw_scale_lr_wd_32xb16-100e_obj365v1_goldg_cc3mram250k_train_lviseval-e3592307_rep_conv.pth'
+persistent_workers = False
+mixup_prob = 0.15
+copypaste_prob = 0.3
+
+# model settings
+model = dict(type='SimpleYOLOWorldDetector',
+             mm_neck=True,
+             num_train_classes=num_classes,
+             num_test_classes=num_classes,
+             reparameterized=True,
+             data_preprocessor=dict(type='YOLOv5DetDataPreprocessor'),
+             backbone=dict(_delete_=True,
+                           type='MultiModalYOLOBackbone',
+                           text_model=None,
+                           image_model={{_base_.model.backbone}},
+                           with_text_model=False),
+             neck=dict(type='YOLOWorldPAFPN',
+                       guide_channels=text_channels,
+                       embed_channels=neck_embed_channels,
+                       num_heads=neck_num_heads,
+                       block_cfg=dict(type='EfficientCSPLayerWithTwoConv')),
+             bbox_head=dict(head_module=dict(type='RepYOLOWorldHeadModule',
+                                             embed_dims=text_channels,
+                                             num_guide=num_classes,
+                                             num_classes=num_classes)),
+             train_cfg=dict(assigner=dict(num_classes=num_classes)))
+
+# dataset settings
+final_transform = [
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction'))
+]
+mosaic_affine_transform = [
+    dict(type='Mosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(type='YOLOv5CopyPaste', prob=copypaste_prob),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100.,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114),
+        min_area_ratio=_base_.min_area_ratio,
+        use_mask_refine=_base_.use_mask2refine)
+]
+train_pipeline = [
+    *_base_.pre_transform, *mosaic_affine_transform,
+    dict(type='YOLOv5MixUp',
+         prob=mixup_prob,
+         pre_transform=[*_base_.pre_transform, *mosaic_affine_transform]),
+    *_base_.last_transform[:-1], *final_transform
+]
+
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *final_transform]
+
+coco_train_dataset = dict(type='YOLOv5CocoDataset',
+                          data_root='data/coco',
+                          ann_file='annotations/instances_train2017.json',
+                          data_prefix=dict(img='train2017/'),
+                          filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                          pipeline=train_pipeline)
+
+train_dataloader = dict(persistent_workers=persistent_workers,
+                        batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=coco_train_dataset)
+
+train_dataloader = dict(persistent_workers=persistent_workers,
+                        batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=coco_train_dataset)
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param'))
+]
+coco_val_dataset = dict(type='YOLOv5CocoDataset',
+                        data_root='data/coco',
+                        ann_file='annotations/instances_val2017.json',
+                        data_prefix=dict(img='val2017/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=test_pipeline)
+
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+# training settings
+default_hooks = dict(param_scheduler=dict(scheduler_type='linear',
+                                          lr_factor=0.01,
+                                          max_epochs=max_epochs),
+                     checkpoint=dict(max_keep_ckpts=-1,
+                                     save_best=None,
+                                     interval=save_epoch_intervals))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=5,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     constructor='YOLOWv5OptimizerConstructor')
+
+# evaluation settings
+val_evaluator = dict(_delete_=True,
+                     type='mmdet.CocoMetric',
+                     proposal_nums=(100, 1, 10),
+                     ann_file='data/coco/annotations/instances_val2017.json',
+                     metric='bbox')

configs/finetune_coco/yolo_world_v2_s_rep_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'], allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 80
+num_training_classes = 80
+max_epochs = 80  # Maximum training epochs
+close_mosaic_epochs = 10
+save_epoch_intervals = 5
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.05
+train_batch_size_per_gpu = 16
+load_from = '../FastDet/output_models/yolo_world_s_clip_t2i_bn_2e-3adamw_32xb16-100e_obj365v1_goldg_train-55b943ea_rep_conv.pth'
+persistent_workers = False
+mixup_prob = 0.15
+copypaste_prob = 0.3
+
+# model settings
+model = dict(type='SimpleYOLOWorldDetector',
+             mm_neck=True,
+             num_train_classes=num_classes,
+             num_test_classes=num_classes,
+             reparameterized=True,
+             data_preprocessor=dict(type='YOLOv5DetDataPreprocessor'),
+             backbone=dict(_delete_=True,
+                           type='MultiModalYOLOBackbone',
+                           text_model=None,
+                           image_model={{_base_.model.backbone}},
+                           with_text_model=False),
+             neck=dict(type='YOLOWorldPAFPN',
+                       guide_channels=num_classes,
+                       embed_channels=neck_embed_channels,
+                       num_heads=neck_num_heads,
+                       block_cfg=dict(type='RepConvMaxSigmoidCSPLayerWithTwoConv',
+                                      guide_channels=num_classes)),
+             bbox_head=dict(head_module=dict(type='RepYOLOWorldHeadModule',
+                                             embed_dims=text_channels,
+                                             num_guide=num_classes,
+                                             num_classes=num_classes)),
+             train_cfg=dict(assigner=dict(num_classes=num_classes)))
+
+# dataset settings
+final_transform = [
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction'))
+]
+mosaic_affine_transform = [
+    dict(type='Mosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(type='YOLOv5CopyPaste', prob=copypaste_prob),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100.,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114),
+        min_area_ratio=_base_.min_area_ratio,
+        use_mask_refine=_base_.use_mask2refine)
+]
+train_pipeline = [
+    *_base_.pre_transform, *mosaic_affine_transform,
+    dict(type='YOLOv5MixUp',
+         prob=mixup_prob,
+         pre_transform=[*_base_.pre_transform, *mosaic_affine_transform]),
+    *_base_.last_transform[:-1], *final_transform
+]
+
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *final_transform]
+
+coco_train_dataset = dict(type='YOLOv5CocoDataset',
+                          data_root='data/coco',
+                          ann_file='annotations/instances_train2017.json',
+                          data_prefix=dict(img='train2017/'),
+                          filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                          pipeline=train_pipeline)
+
+train_dataloader = dict(persistent_workers=persistent_workers,
+                        batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=coco_train_dataset)
+
+train_dataloader = dict(persistent_workers=persistent_workers,
+                        batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=coco_train_dataset)
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param'))
+]
+coco_val_dataset = dict(type='YOLOv5CocoDataset',
+                        data_root='data/coco',
+                        ann_file='annotations/instances_val2017.json',
+                        data_prefix=dict(img='val2017/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=test_pipeline)
+
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+# training settings
+default_hooks = dict(param_scheduler=dict(scheduler_type='linear',
+                                          lr_factor=0.01,
+                                          max_epochs=max_epochs),
+                     checkpoint=dict(max_keep_ckpts=-1,
+                                     save_best=None,
+                                     interval=save_epoch_intervals))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=5,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     constructor='YOLOWv5OptimizerConstructor')
+
+# evaluation settings
+val_evaluator = dict(_delete_=True,
+                     type='mmdet.CocoMetric',
+                     proposal_nums=(100, 1, 10),
+                     ann_file='data/coco/annotations/instances_val2017.json',
+                     metric='bbox')

configs/finetune_coco/yolo_world_v2_s_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py

+_base_ = (
+    '../../third_party/mmyolo/configs/yolov8/'
+    'yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(
+    imports=['yolo_world'],
+    allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 80
+num_training_classes = 80
+max_epochs = 80  # Maximum training epochs
+close_mosaic_epochs = 10
+save_epoch_intervals = 5
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.05
+train_batch_size_per_gpu = 16
+load_from = 'pretrained_models/yolo_world_s_clip_t2i_bn_2e-3adamw_32xb16-100e_obj365v1_goldg_train-55b943ea.pth'
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+persistent_workers = False
+mixup_prob = 0.15
+copypaste_prob = 0.3
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+mosaic_affine_transform = [
+    dict(
+        type='MultiModalMosaic',
+        img_scale=_base_.img_scale,
+        pad_val=114.0,
+        pre_transform=_base_.pre_transform),
+    dict(type='YOLOv5CopyPaste', prob=copypaste_prob),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100.,
+        scaling_ratio_range=(1 - _base_.affine_scale,
+                             1 + _base_.affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114),
+        min_area_ratio=_base_.min_area_ratio,
+        use_mask_refine=_base_.use_mask2refine)
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    *mosaic_affine_transform,
+    dict(
+        type='YOLOv5MultiModalMixUp',
+        prob=mixup_prob,
+        pre_transform=[*_base_.pre_transform,
+                       *mosaic_affine_transform]),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+train_pipeline_stage2 = [
+    *_base_.train_pipeline_stage2[:-1],
+    *text_transform
+]
+coco_train_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5CocoDataset',
+        data_root='data/coco',
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/coco_class_texts.json',
+    pipeline=train_pipeline)
+
+train_dataloader = dict(
+    persistent_workers=persistent_workers,
+    batch_size=train_batch_size_per_gpu,
+    collate_fn=dict(type='yolow_collate'),
+    dataset=coco_train_dataset)
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5CocoDataset',
+        data_root='data/coco',
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/coco_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+# training settings
+default_hooks = dict(
+    param_scheduler=dict(
+        scheduler_type='linear',
+        lr_factor=0.01,
+        max_epochs=max_epochs),
+    checkpoint=dict(
+        max_keep_ckpts=-1,
+        save_best=None,
+        interval=save_epoch_intervals))
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0001,
+        update_buffers=True,
+        strict_load=False,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - close_mosaic_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(
+    max_epochs=max_epochs,
+    val_interval=5,
+    dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                        _base_.val_interval_stage2)])
+optim_wrapper = dict(
+    optimizer=dict(
+        _delete_=True,
+        type='AdamW',
+        lr=base_lr,
+        weight_decay=weight_decay,
+        batch_size_per_gpu=train_batch_size_per_gpu),
+    paramwise_cfg=dict(
+        custom_keys={'backbone.text_model': dict(lr_mult=0.01),
+                     'logit_scale': dict(weight_decay=0.0)}),
+    constructor='YOLOWv5OptimizerConstructor')
+
+# evaluation settings
+val_evaluator = dict(
+    _delete_=True,
+    type='mmdet.CocoMetric',
+    proposal_nums=(100, 1, 10),
+    ann_file='data/coco/annotations/instances_val2017.json',
+    metric='bbox')

configs/finetune_coco/yolo_world_v2_x_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py

+_base_ = (
+    '../../third_party/mmyolo/configs/yolov8/'
+    'yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(
+    imports=['yolo_world'],
+    allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 80
+num_training_classes = 80
+max_epochs = 80  # Maximum training epochs
+close_mosaic_epochs = 10
+save_epoch_intervals = 5
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.05
+train_batch_size_per_gpu = 16
+load_from = 'pretrained_models/yolo_world_x_clip_t2i_bn_2e-3adamw_32xb16-100e_obj365v1_goldg_cc250k_train_lviseval-8698fbfa.pth'
+text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+# text_model_name = 'openai/clip-vit-base-patch32'
+persistent_workers = False
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+mosaic_affine_transform = [
+    dict(
+        type='MultiModalMosaic',
+        img_scale=_base_.img_scale,
+        pad_val=114.0,
+        pre_transform=_base_.pre_transform),
+    dict(type='YOLOv5CopyPaste', prob=_base_.copypaste_prob),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100.,
+        scaling_ratio_range=(1 - _base_.affine_scale,
+                             1 + _base_.affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114),
+        min_area_ratio=_base_.min_area_ratio,
+        use_mask_refine=_base_.use_mask2refine)
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    *mosaic_affine_transform,
+    dict(
+        type='YOLOv5MultiModalMixUp',
+        prob=_base_.mixup_prob,
+        pre_transform=[*_base_.pre_transform,
+                       *mosaic_affine_transform]),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+train_pipeline_stage2 = [
+    *_base_.train_pipeline_stage2[:-1],
+    *text_transform
+]
+coco_train_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5CocoDataset',
+        data_root='data/coco',
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/coco_class_texts.json',
+    pipeline=train_pipeline)
+
+train_dataloader = dict(
+    persistent_workers=persistent_workers,
+    batch_size=train_batch_size_per_gpu,
+    collate_fn=dict(type='yolow_collate'),
+    dataset=coco_train_dataset)
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5CocoDataset',
+        data_root='data/coco',
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/coco_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+# training settings
+default_hooks = dict(
+    param_scheduler=dict(
+        scheduler_type='linear',
+        lr_factor=0.01,
+        max_epochs=max_epochs),
+    checkpoint=dict(
+        max_keep_ckpts=-1,
+        save_best=None,
+        interval=save_epoch_intervals))
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0001,
+        update_buffers=True,
+        strict_load=False,
+        priority=49),
+    dict(
+        type='mmdet.PipelineSwitchHook',
+        switch_epoch=max_epochs - close_mosaic_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(
+    max_epochs=max_epochs,
+    val_interval=5,
+    dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                        _base_.val_interval_stage2)])
+optim_wrapper = dict(
+    optimizer=dict(
+        _delete_=True,
+        type='AdamW',
+        lr=base_lr,
+        weight_decay=weight_decay,
+        batch_size_per_gpu=train_batch_size_per_gpu),
+    paramwise_cfg=dict(
+        custom_keys={'backbone.text_model': dict(lr_mult=0.01),
+                     'logit_scale': dict(weight_decay=0.0)}),
+    constructor='YOLOWv5OptimizerConstructor')
+# evaluation settings
+val_evaluator = dict(
+    _delete_=True,
+    type='mmdet.CocoMetric',
+    proposal_nums=(100, 1, 10),
+    ann_file='data/coco/annotations/instances_val2017.json',
+    metric='bbox')

configs/finetune_coco/yolo_world_v2_xl_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'], allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 80
+num_training_classes = 80
+max_epochs = 80  # Maximum training epochs
+close_mosaic_epochs = 10
+save_epoch_intervals = 5
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.05
+train_batch_size_per_gpu = 16
+text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+# text_model_name = 'openai/clip-vit-base-patch32'
+persistent_workers = False
+
+# scaling model from X to XL
+deepen_factor = 1.0
+widen_factor = 1.5
+
+backbone = _base_.model.backbone
+backbone.update(deepen_factor=deepen_factor, widen_factor=widen_factor)
+
+# model settings
+model = dict(type='YOLOWorldDetector',
+             mm_neck=True,
+             num_train_classes=num_training_classes,
+             num_test_classes=num_classes,
+             data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+             backbone=dict(_delete_=True,
+                           type='MultiModalYOLOBackbone',
+                           image_model=backbone,
+                           text_model=dict(type='HuggingCLIPLanguageBackbone',
+                                           model_name=text_model_name,
+                                           frozen_modules=['all'])),
+             neck=dict(type='YOLOWorldPAFPN',
+                       deepen_factor=deepen_factor,
+                       widen_factor=widen_factor,
+                       guide_channels=text_channels,
+                       embed_channels=neck_embed_channels,
+                       num_heads=neck_num_heads,
+                       block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+             bbox_head=dict(type='YOLOWorldHead',
+                            head_module=dict(
+                                type='YOLOWorldHeadModule',
+                                widen_factor=widen_factor,
+                                use_bn_head=True,
+                                embed_dims=text_channels,
+                                num_classes=num_training_classes)),
+             train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+mosaic_affine_transform = [
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(type='YOLOv5CopyPaste', prob=_base_.copypaste_prob),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100.,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        # img_scale is (width, height)
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114),
+        min_area_ratio=_base_.min_area_ratio,
+        use_mask_refine=_base_.use_mask2refine)
+]
+train_pipeline = [
+    *_base_.pre_transform, *mosaic_affine_transform,
+    dict(type='YOLOv5MultiModalMixUp',
+         prob=_base_.mixup_prob,
+         pre_transform=[*_base_.pre_transform, *mosaic_affine_transform]),
+    *_base_.last_transform[:-1], *text_transform
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+coco_train_dataset = dict(_delete_=True,
+                          type='MultiModalDataset',
+                          dataset=dict(
+                              type='YOLOv5CocoDataset',
+                              data_root='data/coco',
+                              ann_file='annotations/instances_train2017.json',
+                              data_prefix=dict(img='train2017/'),
+                              filter_cfg=dict(filter_empty_gt=False,
+                                              min_size=32)),
+                          class_text_path='data/texts/coco_class_texts.json',
+                          pipeline=train_pipeline)
+
+train_dataloader = dict(persistent_workers=persistent_workers,
+                        batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=coco_train_dataset)
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5CocoDataset',
+                 data_root='data/coco',
+                 ann_file='annotations/instances_val2017.json',
+                 data_prefix=dict(img='val2017/'),
+                 filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/coco_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+# training settings
+default_hooks = dict(param_scheduler=dict(scheduler_type='linear',
+                                          lr_factor=0.01,
+                                          max_epochs=max_epochs),
+                     checkpoint=dict(max_keep_ckpts=-1,
+                                     save_best=None,
+                                     interval=save_epoch_intervals))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=5,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')
+
+# evaluation settings
+val_evaluator = dict(_delete_=True,
+                     type='mmdet.CocoMetric',
+                     proposal_nums=(100, 1, 10),
+                     ann_file='data/coco/annotations/instances_val2017.json',
+                     metric='bbox')

configs/pretrain/yolo_world_v2_l_clip_large_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_800ft_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 768
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.0125
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-large-patch14-336'
+text_model_name = 'openai/clip-vit-large-patch14-336'
+img_scale = (800, 800)
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+
+train_pipeline_stage2 = [
+    *_base_.pre_transform,
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=True,
+        pad_val=dict(img=114.0)),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=False,
+        pad_val=dict(img=114)),
+    dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_l_clip_large_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 768
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.0125
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-large-patch14-336'
+text_model_name = 'openai/clip-vit-large-patch14-336'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_l_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_1280ft_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 20  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.025
+train_batch_size_per_gpu = 4
+load_from = "pretrained_models/yolo_world_v2_l_obj365v1_goldg_pretrain-a82b1fe3.pth"
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+img_scale = (1280, 1280)
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+
+train_pipeline_stage2 = [
+    *_base_.pre_transform,
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=True,
+        pad_val=dict(img=114.0)),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=False,
+        pad_val=dict(img=114)),
+    dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_l_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_l_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_val.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_val.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_val.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_m_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_1280ft_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_m_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+img_scale = (1280, 1280)
+
+text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+
+train_pipeline_stage2 = [
+    *_base_.pre_transform,
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=True,
+        pad_val=dict(img=114.0)),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=False,
+        pad_val=dict(img=114)),
+    dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_m_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_m_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+text_model_name = 'openai/clip-vit-large-patch14-336'
+# text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_m_vlpan_bn_noeinsum_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_m_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv',
+                             use_einsum=False)),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes,
+                                    use_einsum=False)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_s_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_1280ft_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_s_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-4
+weight_decay = 0.025
+train_batch_size_per_gpu = 4
+img_scale = (1280, 1280)
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name='openai/clip-vit-base-patch32',
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [
+    *_base_.pre_transform,
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=True,
+        pad_val=dict(img=114.0)),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=False,
+        pad_val=dict(img=114)),
+    dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_s_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_s_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name='openai/clip-vit-base-patch32',
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_x_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_1280ft_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_x_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+img_scale = (1280, 1280)
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [
+    *_base_.pre_transform,
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=True,
+        pad_val=dict(img=114.0)),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform
+]
+
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
+    dict(
+        type='LetterResize',
+        scale=img_scale,
+        allow_scale_up=False,
+        pad_val=dict(img=114)),
+    dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_x_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_x_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+# text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain/yolo_world_v2_xl_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_x_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+text_model_name = '../pretrained_models/clip-vit-base-patch32-projection'
+text_model_name = 'openai/clip-vit-base-patch32'
+
+# scaling model from X to XL
+deepen_factor = 1.0
+widen_factor = 1.5
+
+backbone = _base_.model.backbone
+backbone.update(
+    deepen_factor=deepen_factor,
+    widen_factor=widen_factor
+)
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model=backbone,
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name=text_model_name,
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldPAFPN',
+              deepen_factor=deepen_factor,
+              widen_factor=widen_factor,
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv')),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    widen_factor=widen_factor,
+                                    use_bn_head=True,
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')

configs/pretrain_v1/README.md

+## Pre-training YOLO-World-v1
+
+> The YOLO-World-v1 is an initial version, and now is nearly deprecated! We strongly suggest you use the [latest version](../pretrain/).
+
+
+
+### Zero-shot Inference on LVIS dataset
+
+| model                                                                                                                | Pre-train Data       | Size | AP<sup>mini</su> | AP<sub>r</sub> | AP<sub>c</sub> | AP<sub>f</sub> | AP<sup>val</su> | AP<sub>r</sub> | AP<sub>c</sub> | AP<sub>f</sub> |                                                                                        weights                                                                                         |
+| :------------------------------------------------------------------------------------------------------------------- | :------------------- | :----------------- | :--------------: | :------------: | :------------: | :------------: | :-------------: | :------------: | :------------: | :------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| [YOLO-World-S](./yolo_world_s_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py)   | O365+GoldG           |        640        |       24.3       |      16.6      |      22.1      |      27.7      |      17.8       |      11.0      |      14.8      |      24.0      |    [HF Checkpoints 🤗](https://huggingface.co/wondervictor/YOLO-World/resolve/main/yolo_world_s_clip_base_dual_vlpan_2e-3adamw_32xb16_100e_o365_goldg_train_pretrained-18bea4d2.pth)    |
+| [YOLO-World-M](./yolo_world_m_dual_l2norm_2e-4_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py)   | O365+GoldG           |        640        |       28.6       |      19.7      |      26.6      |      31.9      |      22.3       |      16.2      |      19.0      |      28.7      |    [HF Checkpoints 🤗](https://huggingface.co/wondervictor/YOLO-World/resolve/main/yolo_world_m_clip_base_dual_vlpan_2e-3adamw_32xb16_100e_o365_goldg_train_pretrained-2b7bd1be.pth)    |
+| [YOLO-World-L](./yolo_world_l_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py)   | O365+GoldG           |        640        |       32.5       |      22.3      |      30.6      |      36.1      |      24.8       |      17.8      |      22.4      |      32.5      |    [HF Checkpoints 🤗](https://huggingface.co/wondervictor/YOLO-World/resolve/main/yolo_world_l_clip_base_dual_vlpan_2e-3adamw_32xb16_100e_o365_goldg_train_pretrained-0e566235.pth)    |
+| [YOLO-World-L](./yolo_world_l_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py) | O365+GoldG+CC3M-Lite |        640        |       33.0       |      23.6      |      32.0      |      35.5      |      25.3       |      18.0      |      22.1      |      32.1      | [HF Checkpoints 🤗](https://huggingface.co/wondervictor/YOLO-World/blob/main/yolo_world_l_clip_base_dual_vlpan_2e-3adamw_32xb16_100e_o365_goldg_cc3mlite_train_pretrained-7a5eea3b.pth) |
+| [YOLO-World-X](./yolo_world_x_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py) | O365+GoldG+CC3M-Lite | 640 | 33.4 | 24.4 | 31.6 | 36.6 | 26.6 | 19.2 | 23.5 | 33.2 | [HF Checkpoints 🤗](https://huggingface.co/wondervictor/YOLO-World/blob/main/yolo_world_x_clip_base_dual_vlpan_2e-3adamw_32xb16_100e_o365_goldg_cc3mlite_train_pretrained-8cf6b025.pth) |
+
+
+**NOTE:**
+1. AP<sup>mini</sup>: evaluated on LVIS `minival`.
+3. AP<sup>val</sup>: evaluated on LVIS `val 1.0`.
+4. [HuggingFace Mirror](https://hf-mirror.com/) provides the mirror of HuggingFace, which is a choice for users who are unable to reach.
\ No newline at end of file

configs/pretrain_v1/yolo_world_l_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py

+_base_ = ('../../third_party/mmyolo/configs/yolov8/'
+          'yolov8_l_syncbn_fast_8xb16-500e_coco.py')
+custom_imports = dict(imports=['yolo_world'],
+                      allow_failed_imports=False)
+
+# hyper-parameters
+num_classes = 1203
+num_training_classes = 80
+max_epochs = 100  # Maximum training epochs
+close_mosaic_epochs = 2
+save_epoch_intervals = 2
+text_channels = 512
+neck_embed_channels = [128, 256, _base_.last_stage_out_channels // 2]
+neck_num_heads = [4, 8, _base_.last_stage_out_channels // 2 // 32]
+base_lr = 2e-3
+weight_decay = 0.05 / 2
+train_batch_size_per_gpu = 16
+
+# model settings
+model = dict(
+    type='YOLOWorldDetector',
+    mm_neck=True,
+    num_train_classes=num_training_classes,
+    num_test_classes=num_classes,
+    data_preprocessor=dict(type='YOLOWDetDataPreprocessor'),
+    backbone=dict(
+        _delete_=True,
+        type='MultiModalYOLOBackbone',
+        image_model={{_base_.model.backbone}},
+        text_model=dict(
+            type='HuggingCLIPLanguageBackbone',
+            model_name='openai/clip-vit-base-patch32',
+            frozen_modules=['all'])),
+    neck=dict(type='YOLOWorldDualPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv'),
+              text_enhancder=dict(type='ImagePoolingAttentionModule',
+                                  embed_channels=256,
+                                  num_heads=8)),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    embed_dims=text_channels,
+                                    num_classes=num_training_classes)),
+    train_cfg=dict(assigner=dict(num_classes=num_training_classes)))
+
+# dataset settings
+text_transform = [
+    dict(type='RandomLoadText',
+         num_neg_samples=(num_classes, num_classes),
+         max_num_samples=num_training_classes,
+         padding_to_max=True,
+         padding_value=''),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                    'flip_direction', 'texts'))
+]
+train_pipeline = [
+    *_base_.pre_transform,
+    dict(type='MultiModalMosaic',
+         img_scale=_base_.img_scale,
+         pad_val=114.0,
+         pre_transform=_base_.pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
+        max_aspect_ratio=_base_.max_aspect_ratio,
+        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *_base_.last_transform[:-1],
+    *text_transform,
+]
+train_pipeline_stage2 = [*_base_.train_pipeline_stage2[:-1], *text_transform]
+obj365v1_train_dataset = dict(
+    type='MultiModalDataset',
+    dataset=dict(
+        type='YOLOv5Objects365V1Dataset',
+        data_root='data/objects365v1/',
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32)),
+    class_text_path='data/texts/obj365v1_class_texts.json',
+    pipeline=train_pipeline)
+
+mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
+                        data_root='data/mixed_grounding/',
+                        ann_file='annotations/final_mixed_train_no_coco.json',
+                        data_prefix=dict(img='gqa/images/'),
+                        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+                        pipeline=train_pipeline)
+
+flickr_train_dataset = dict(
+    type='YOLOv5MixedGroundingDataset',
+    data_root='data/flickr/',
+    ann_file='annotations/final_flickr_separateGT_train.json',
+    data_prefix=dict(img='full_images/'),
+    filter_cfg=dict(filter_empty_gt=True, min_size=32),
+    pipeline=train_pipeline)
+
+train_dataloader = dict(batch_size=train_batch_size_per_gpu,
+                        collate_fn=dict(type='yolow_collate'),
+                        dataset=dict(_delete_=True,
+                                     type='ConcatDataset',
+                                     datasets=[
+                                         obj365v1_train_dataset,
+                                         flickr_train_dataset, mg_train_dataset
+                                     ],
+                                     ignore_keys=['classes', 'palette']))
+
+test_pipeline = [
+    *_base_.test_pipeline[:-1],
+    dict(type='LoadText'),
+    dict(type='mmdet.PackDetInputs',
+         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                    'scale_factor', 'pad_param', 'texts'))
+]
+coco_val_dataset = dict(
+    _delete_=True,
+    type='MultiModalDataset',
+    dataset=dict(type='YOLOv5LVISV1Dataset',
+                 data_root='data/coco/',
+                 test_mode=True,
+                 ann_file='lvis/lvis_v1_minival_inserted_image_name.json',
+                 data_prefix=dict(img=''),
+                 batch_shapes_cfg=None),
+    class_text_path='data/texts/lvis_v1_class_texts.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='mmdet.LVISMetric',
+                     ann_file='data/coco/lvis/lvis_v1_minival_inserted_image_name.json',
+                     metric='bbox')
+test_evaluator = val_evaluator
+
+# training settings
+default_hooks = dict(param_scheduler=dict(max_epochs=max_epochs),
+                     checkpoint=dict(interval=save_epoch_intervals,
+                                     rule='greater'))
+custom_hooks = [
+    dict(type='EMAHook',
+         ema_type='ExpMomentumEMA',
+         momentum=0.0001,
+         update_buffers=True,
+         strict_load=False,
+         priority=49),
+    dict(type='mmdet.PipelineSwitchHook',
+         switch_epoch=max_epochs - close_mosaic_epochs,
+         switch_pipeline=train_pipeline_stage2)
+]
+train_cfg = dict(max_epochs=max_epochs,
+                 val_interval=10,
+                 dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                                     _base_.val_interval_stage2)])
+optim_wrapper = dict(optimizer=dict(
+    _delete_=True,
+    type='AdamW',
+    lr=base_lr,
+    weight_decay=weight_decay,
+    batch_size_per_gpu=train_batch_size_per_gpu),
+                     paramwise_cfg=dict(bias_decay_mult=0.0,
+                                        norm_decay_mult=0.0,
+                                        custom_keys={
+                                            'backbone.text_model':
+                                            dict(lr_mult=0.01),
+                                            'logit_scale':
+                                            dict(weight_decay=0.0)
+                                        }),
+                     constructor='YOLOWv5OptimizerConstructor')