_base_ = 'yolov5_s-v61_fast_8xb16-300e_crowdhuman.py'

model = dict(
    data_preprocessor=dict(
        _delete_=True,
        type='mmdet.DetDataPreprocessor',
        mean=[0., 0., 0.],
        std=[255., 255., 255.],
        bgr_to_rgb=True),
    bbox_head=dict(ignore_iof_thr=0.5))

img_scale = _base_.img_scale

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),
    # only change this
    dict(type='mmdet.LoadAnnotations', with_bbox=True)
]

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=(0.5, 1.5),
        # img_scale is (width, height)
        border=(-img_scale[0] // 2, -img_scale[1] // 2),
        border_val=(114, 114, 114)),
    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_dataloader = dict(
    collate_fn=dict(type='pseudo_collate'),
    dataset=dict(pipeline=train_pipeline))