Upload 7 files

default_runtime.py

@@ -0,0 +1,43 @@
+default_scope = 'mmyolo'
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', interval=1),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='mmdet.DetVisualizationHook'))
+
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='mmdet.DetLocalVisualizer',
+    vis_backends=vis_backends,
+    name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions
+# before MMDet 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+
+backend_args = None

det_p5_tta.py

@@ -0,0 +1,58 @@
+# TODO: Need to solve the problem of multiple backend_args parameters
+# _backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+
+_backend_args = None
+
+tta_model = dict(
+    type='mmdet.DetTTAModel',
+    tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.65), max_per_img=300))
+
+img_scales = [(640, 640), (320, 320), (960, 960)]
+
+#                                LoadImageFromFile
+#                     /                 |                     \
+# (RatioResize,LetterResize) (RatioResize,LetterResize) (RatioResize,LetterResize) # noqa
+#        /      \                    /      \                    /        \
+#  RandomFlip RandomFlip      RandomFlip RandomFlip        RandomFlip RandomFlip # noqa
+#      |          |                |         |                  |         |
+#  LoadAnn    LoadAnn           LoadAnn    LoadAnn           LoadAnn    LoadAnn
+#      |          |                |         |                  |         |
+#  PackDetIn  PackDetIn         PackDetIn  PackDetIn        PackDetIn  PackDetIn # noqa
+
+_multiscale_resize_transforms = [
+    dict(
+        type='Compose',
+        transforms=[
+            dict(type='YOLOv5KeepRatioResize', scale=s),
+            dict(
+                type='LetterResize',
+                scale=s,
+                allow_scale_up=False,
+                pad_val=dict(img=114))
+        ]) for s in img_scales
+]
+
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=_backend_args),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            _multiscale_resize_transforms,
+            [
+                dict(type='mmdet.RandomFlip', prob=1.),
+                dict(type='mmdet.RandomFlip', prob=0.)
+            ], [dict(type='mmdet.LoadAnnotations', with_bbox=True)],
+            [
+                dict(
+                    type='mmdet.PackDetInputs',
+                    meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                               'scale_factor', 'pad_param', 'flip',
+                               'flip_direction'))
+            ]
+        ])
+]

yolov8_l_syncbn_fast_8xb16-500e_coco.py

@@ -0,0 +1,39 @@
+_base_ = './yolov8_m_syncbn_fast_8xb16-500e_coco.py'
+
+# ========================modified parameters======================
+deepen_factor = 1.00
+widen_factor = 1.00
+last_stage_out_channels = 512
+
+mixup_prob = 0.15
+
+# =======================Unmodified in most cases==================
+pre_transform = _base_.pre_transform
+mosaic_affine_transform = _base_.mosaic_affine_transform
+last_transform = _base_.last_transform
+
+model = dict(
+    backbone=dict(
+        last_stage_out_channels=last_stage_out_channels,
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor),
+    neck=dict(
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        in_channels=[256, 512, last_stage_out_channels],
+        out_channels=[256, 512, last_stage_out_channels]),
+    bbox_head=dict(
+        head_module=dict(
+            widen_factor=widen_factor,
+            in_channels=[256, 512, last_stage_out_channels])))
+
+train_pipeline = [
+    *pre_transform, *mosaic_affine_transform,
+    dict(
+        type='YOLOv5MixUp',
+        prob=mixup_prob,
+        pre_transform=[*pre_transform, *mosaic_affine_transform]),
+    *last_transform
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))

yolov8_m_syncbn_fast_8xb16-500e_coco.py

@@ -0,0 +1,76 @@
+_base_ = './yolov8_s_syncbn_fast_8xb16-500e_coco.py'
+
+# ========================modified parameters======================
+deepen_factor = 0.67
+widen_factor = 0.75
+last_stage_out_channels = 768
+
+affine_scale = 0.9
+mixup_prob = 0.1
+
+# =======================Unmodified in most cases==================
+img_scale = _base_.img_scale
+pre_transform = _base_.pre_transform
+last_transform = _base_.last_transform
+
+model = dict(
+    backbone=dict(
+        last_stage_out_channels=last_stage_out_channels,
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor),
+    neck=dict(
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        in_channels=[256, 512, last_stage_out_channels],
+        out_channels=[256, 512, last_stage_out_channels]),
+    bbox_head=dict(
+        head_module=dict(
+            widen_factor=widen_factor,
+            in_channels=[256, 512, last_stage_out_channels])))
+
+mosaic_affine_transform = [
+    dict(
+        type='Mosaic',
+        img_scale=img_scale,
+        pad_val=114.0,
+        pre_transform=pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        max_aspect_ratio=100,
+        scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
+        # img_scale is (width, height)
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114))
+]
+
+# enable mixup
+train_pipeline = [
+    *pre_transform, *mosaic_affine_transform,
+    dict(
+        type='YOLOv5MixUp',
+        prob=mixup_prob,
+        pre_transform=[*pre_transform, *mosaic_affine_transform]),
+    *last_transform
+]
+
+train_pipeline_stage2 = [
+    *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 - affine_scale, 1 + affine_scale),
+        max_aspect_ratio=100,
+        border_val=(114, 114, 114)), *last_transform
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+_base_.custom_hooks[1].switch_pipeline = train_pipeline_stage2

yolov8_s_syncbn_fast_8xb16-500e_coco.py

@@ -0,0 +1,334 @@
+_base_ = ['./default_runtime.py', './det_p5_tta.py']
+
+# ========================Frequently modified parameters======================
+# -----data related-----
+data_root = 'data/coco/'  # Root path of data
+# Path of train annotation file
+train_ann_file = 'annotations/instances_train2017.json'
+train_data_prefix = 'train2017/'  # Prefix of train image path
+# Path of val annotation file
+val_ann_file = 'annotations/instances_val2017.json'
+val_data_prefix = 'val2017/'  # Prefix of val image path
+
+num_classes = 80  # Number of classes for classification
+# Batch size of a single GPU during training
+train_batch_size_per_gpu = 16
+# Worker to pre-fetch data for each single GPU during training
+train_num_workers = 8
+# persistent_workers must be False if num_workers is 0
+persistent_workers = True
+
+# -----train val related-----
+# Base learning rate for optim_wrapper. Corresponding to 8xb16=64 bs
+base_lr = 0.01
+max_epochs = 500  # Maximum training epochs
+# Disable mosaic augmentation for final 10 epochs (stage 2)
+close_mosaic_epochs = 10
+
+model_test_cfg = dict(
+    # The config of multi-label for multi-class prediction.
+    multi_label=True,
+    # The number of boxes before NMS
+    nms_pre=30000,
+    score_thr=0.001,  # Threshold to filter out boxes.
+    nms=dict(type='nms', iou_threshold=0.7),  # NMS type and threshold
+    max_per_img=300)  # Max number of detections of each image
+
+# ========================Possible modified parameters========================
+# -----data related-----
+img_scale = (640, 640)  # width, height
+# Dataset type, this will be used to define the dataset
+dataset_type = 'YOLOv5CocoDataset'
+# Batch size of a single GPU during validation
+val_batch_size_per_gpu = 1
+# Worker to pre-fetch data for each single GPU during validation
+val_num_workers = 2
+
+# Config of batch shapes. Only on val.
+# We tested YOLOv8-m will get 0.02 higher than not using it.
+batch_shapes_cfg = None
+# You can turn on `batch_shapes_cfg` by uncommenting the following lines.
+# batch_shapes_cfg = dict(
+#     type='BatchShapePolicy',
+#     batch_size=val_batch_size_per_gpu,
+#     img_size=img_scale[0],
+#     # The image scale of padding should be divided by pad_size_divisor
+#     size_divisor=32,
+#     # Additional paddings for pixel scale
+#     extra_pad_ratio=0.5)
+
+# -----model related-----
+# The scaling factor that controls the depth of the network structure
+deepen_factor = 0.33
+# The scaling factor that controls the width of the network structure
+widen_factor = 0.5
+# Strides of multi-scale prior box
+strides = [8, 16, 32]
+# The output channel of the last stage
+last_stage_out_channels = 1024
+num_det_layers = 3  # The number of model output scales
+norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)  # Normalization config
+
+# -----train val related-----
+affine_scale = 0.5  # YOLOv5RandomAffine scaling ratio
+# YOLOv5RandomAffine aspect ratio of width and height thres to filter bboxes
+max_aspect_ratio = 100
+tal_topk = 10  # Number of bbox selected in each level
+tal_alpha = 0.5  # A Hyper-parameter related to alignment_metrics
+tal_beta = 6.0  # A Hyper-parameter related to alignment_metrics
+# TODO: Automatically scale loss_weight based on number of detection layers
+loss_cls_weight = 0.5
+loss_bbox_weight = 7.5
+# Since the dfloss is implemented differently in the official
+# and mmdet, we're going to divide loss_weight by 4.
+loss_dfl_weight = 1.5 / 4
+lr_factor = 0.01  # Learning rate scaling factor
+weight_decay = 0.0005
+# Save model checkpoint and validation intervals in stage 1
+save_epoch_intervals = 10
+# validation intervals in stage 2
+val_interval_stage2 = 1
+# The maximum checkpoints to keep.
+max_keep_ckpts = 2
+# Single-scale training is recommended to
+# be turned on, which can speed up training.
+env_cfg = dict(cudnn_benchmark=True)
+
+# ===============================Unmodified in most cases====================
+model = dict(
+    type='YOLODetector',
+    data_preprocessor=dict(
+        type='YOLOv5DetDataPreprocessor',
+        mean=[0., 0., 0.],
+        std=[255., 255., 255.],
+        bgr_to_rgb=True),
+    backbone=dict(
+        type='YOLOv8CSPDarknet',
+        arch='P5',
+        last_stage_out_channels=last_stage_out_channels,
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='SiLU', inplace=True)),
+    neck=dict(
+        type='YOLOv8PAFPN',
+        deepen_factor=deepen_factor,
+        widen_factor=widen_factor,
+        in_channels=[256, 512, last_stage_out_channels],
+        out_channels=[256, 512, last_stage_out_channels],
+        num_csp_blocks=3,
+        norm_cfg=norm_cfg,
+        act_cfg=dict(type='SiLU', inplace=True)),
+    bbox_head=dict(
+        type='YOLOv8Head',
+        head_module=dict(
+            type='YOLOv8HeadModule',
+            num_classes=num_classes,
+            in_channels=[256, 512, last_stage_out_channels],
+            widen_factor=widen_factor,
+            reg_max=16,
+            norm_cfg=norm_cfg,
+            act_cfg=dict(type='SiLU', inplace=True),
+            featmap_strides=strides),
+        prior_generator=dict(
+            type='mmdet.MlvlPointGenerator', offset=0.5, strides=strides),
+        bbox_coder=dict(type='DistancePointBBoxCoder'),
+        # scaled based on number of detection layers
+        loss_cls=dict(
+            type='mmdet.CrossEntropyLoss',
+            use_sigmoid=True,
+            reduction='none',
+            loss_weight=loss_cls_weight),
+        loss_bbox=dict(
+            type='IoULoss',
+            iou_mode='ciou',
+            bbox_format='xyxy',
+            reduction='sum',
+            loss_weight=loss_bbox_weight,
+            return_iou=False),
+        loss_dfl=dict(
+            type='mmdet.DistributionFocalLoss',
+            reduction='mean',
+            loss_weight=loss_dfl_weight)),
+    train_cfg=dict(
+        assigner=dict(
+            type='BatchTaskAlignedAssigner',
+            num_classes=num_classes,
+            use_ciou=True,
+            topk=tal_topk,
+            alpha=tal_alpha,
+            beta=tal_beta,
+            eps=1e-9)),
+    test_cfg=model_test_cfg)
+
+albu_train_transforms = [
+    dict(type='Blur', p=0.01),
+    dict(type='MedianBlur', p=0.01),
+    dict(type='ToGray', p=0.01),
+    dict(type='CLAHE', p=0.01)
+]
+
+pre_transform = [
+    dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
+    dict(type='LoadAnnotations', with_bbox=True)
+]
+
+last_transform = [
+    dict(
+        type='mmdet.Albu',
+        transforms=albu_train_transforms,
+        bbox_params=dict(
+            type='BboxParams',
+            format='pascal_voc',
+            label_fields=['gt_bboxes_labels', 'gt_ignore_flags']),
+        keymap={
+            'img': 'image',
+            'gt_bboxes': 'bboxes'
+        }),
+    dict(type='YOLOv5HSVRandomAug'),
+    dict(type='mmdet.RandomFlip', prob=0.5),
+    dict(
+        type='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
+                   'flip_direction'))
+]
+
+train_pipeline = [
+    *pre_transform,
+    dict(
+        type='Mosaic',
+        img_scale=img_scale,
+        pad_val=114.0,
+        pre_transform=pre_transform),
+    dict(
+        type='YOLOv5RandomAffine',
+        max_rotate_degree=0.0,
+        max_shear_degree=0.0,
+        scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
+        max_aspect_ratio=max_aspect_ratio,
+        # img_scale is (width, height)
+        border=(-img_scale[0] // 2, -img_scale[1] // 2),
+        border_val=(114, 114, 114)),
+    *last_transform
+]
+
+train_pipeline_stage2 = [
+    *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 - affine_scale, 1 + affine_scale),
+        max_aspect_ratio=max_aspect_ratio,
+        border_val=(114, 114, 114)), *last_transform
+]
+
+train_dataloader = dict(
+    batch_size=train_batch_size_per_gpu,
+    num_workers=train_num_workers,
+    persistent_workers=persistent_workers,
+    pin_memory=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    collate_fn=dict(type='yolov5_collate'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file=train_ann_file,
+        data_prefix=dict(img=train_data_prefix),
+        filter_cfg=dict(filter_empty_gt=False, min_size=32),
+        pipeline=train_pipeline))
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
+    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='mmdet.PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor', 'pad_param'))
+]
+
+val_dataloader = dict(
+    batch_size=val_batch_size_per_gpu,
+    num_workers=val_num_workers,
+    persistent_workers=persistent_workers,
+    pin_memory=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        test_mode=True,
+        data_prefix=dict(img=val_data_prefix),
+        ann_file=val_ann_file,
+        pipeline=test_pipeline,
+        batch_shapes_cfg=batch_shapes_cfg))
+
+test_dataloader = val_dataloader
+
+param_scheduler = None
+optim_wrapper = dict(
+    type='OptimWrapper',
+    clip_grad=dict(max_norm=10.0),
+    optimizer=dict(
+        type='SGD',
+        lr=base_lr,
+        momentum=0.937,
+        weight_decay=weight_decay,
+        nesterov=True,
+        batch_size_per_gpu=train_batch_size_per_gpu),
+    constructor='YOLOv5OptimizerConstructor')
+
+default_hooks = dict(
+    param_scheduler=dict(
+        type='YOLOv5ParamSchedulerHook',
+        scheduler_type='linear',
+        lr_factor=lr_factor,
+        max_epochs=max_epochs),
+    checkpoint=dict(
+        type='CheckpointHook',
+        interval=save_epoch_intervals,
+        save_best='auto',
+        max_keep_ckpts=max_keep_ckpts))
+
+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)
+]
+
+val_evaluator = dict(
+    type='mmdet.CocoMetric',
+    proposal_nums=(100, 1, 10),
+    ann_file=data_root + val_ann_file,
+    metric='bbox')
+test_evaluator = val_evaluator
+
+train_cfg = dict(
+    type='EpochBasedTrainLoop',
+    max_epochs=max_epochs,
+    val_interval=save_epoch_intervals,
+    dynamic_intervals=[((max_epochs - close_mosaic_epochs),
+                        val_interval_stage2)])
+
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')

yolov8l-world.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e56623553f30137149da28097b882b3413fa2a00cce88d19e426475b70da5dc
+size 444388398

yolov8l-world.py

@@ -0,0 +1,181 @@
+_base_ = ('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='YOLOWorldPAFPN',
+              guide_channels=text_channels,
+              embed_channels=neck_embed_channels,
+              num_heads=neck_num_heads,
+              block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv'),
+              num_csp_blocks=2),
+    bbox_head=dict(type='YOLOWorldHead',
+                   head_module=dict(type='YOLOWorldHeadModule',
+                                    embed_dims=text_channels,
+                                    use_bn_head=True,
+                                    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/captions/obj365v1_class_captions.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='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/lvis/',
+        test_mode=True,
+        ann_file='annotations/'
+                 'lvis_v1_minival_inserted_image_name.json',
+        data_prefix=dict(img=''),
+        batch_shapes_cfg=None),
+    class_text_path='data/captions/lvis_v1_class_captions.json',
+    pipeline=test_pipeline)
+val_dataloader = dict(dataset=coco_val_dataset)
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='mmdet.LVISMetric',
+    ann_file='data/lvis/annotations/'
+             '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')