2021-02-20

albumentations-不同框架使用(三)

 

一.pytorch调用albumentations

1.1定义数据增强函数-用于检测任务中

def get_train_transforms():
    return A.Compose(
        [
            A.RandomSizedCrop(min_max_height=(800, 800), height=1024, width=1024, p=0.5),
            A.OneOf([
                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit= 0.2, 
                                     val_shift_limit=0.2, p=0.9),
                A.RandomBrightnessContrast(brightness_limit=0.2, 
                                           contrast_limit=0.2, p=0.9),
            ],p=0.9),
            A.ToGray(p=0.01),
            A.HorizontalFlip(p=0.5),
            A.VerticalFlip(p=0.5),
            A.Resize(height=512, width=512, p=1),
            A.Cutout(num_holes=8, max_h_size=64, max_w_size=64, fill_value=0, p=0.5),
            ToTensorV2(p=1.0),
        ], 
        p=1.0, 
        bbox_params=A.BboxParams(
            format='pascal_voc',
            min_area=0, 
            min_visibility=0,
            label_fields=['labels']
        )
    )

2.2pytorch调用上面定义的数据增强函数

在dataloader中，transforms直接使用即可

train_dataset = DatasetRetriever(

   image_ids=df_folds[df_folds['fold'] != fold_number].index.values,

   marking=marking,

   transforms=get_train_transforms(),

   test=False,

)