third_party/mmyolo/configs/yolov5/ins_seg/yolov5_ins_s-v61_syncbn_fast_non_overlap_8xb16-300e_coco_instance.py

_base_ = './yolov5_ins_s-v61_syncbn_fast_8xb16-300e_coco_instance.py'  # noqa

# ========================modified parameters======================
mask_overlap = False  # Polygon2Mask

# ===============================Unmodified in most cases====================
model = dict(bbox_head=dict(mask_overlap=mask_overlap))

train_pipeline = [
    *_base_.pre_transform,
    dict(
        type='Mosaic',
        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),
        border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2),
        border_val=(114, 114, 114),
        min_area_ratio=_base_.min_area_ratio,
        max_aspect_ratio=_base_.max_aspect_ratio,
        use_mask_refine=True),
    dict(
        type='mmdet.Albu',
        transforms=_base_.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='Polygon2Mask',
        downsample_ratio=_base_.downsample_ratio,
        mask_overlap=mask_overlap),
    dict(
        type='PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
                   'flip_direction'))
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))