Pytorch之数据增强3

Transforms on PIL Image

torchvision.transforms.functional

 

torchvision.transforms.functional与torchvision.transforms的区别在于torchvision.transforms.functional可以自己设定格式，torchvision.transforms一般用于torchvision.transforms.Compose中，如下：

 

transforms.Compose([
    transforms.CenterCrop(10),
    transforms.ToTensor(),
])

torchvision.transforms.functional.adjust_brightness(img, brightness_factor)
torchvision.transforms.functional.adjust_contrast(img, contrast_factor)
torchvision.transforms.functional.adjust_gamma(img, gamma, gain=1)
torchvision.transforms.functional.adjust_hue(img, hue_factor)
torchvision.transforms.functional.adjust_saturation(img, saturation_factor)
torchvision.transforms.functional.affine(img, angle, translate, scale, shear, resample=0, fillcolor=None)


torchvision.transforms.functional.hflip(img)
torchvision.transforms.functional.vflip(img)


torchvision.transforms.functional.crop(img, i, j, h, w)
torchvision.transforms.functional.five_crop(img, size)
torchvision.transforms.functional.ten_crop(img, size, vertical_flip=False)


torchvision.transforms.functional.normalize(tensor, mean, std, inplace=False)

torchvision.transforms.functional.pad(img, padding, fill=0, padding_mode='constant')

torchvision.transforms.functional.resize(img, size, interpolation=2)

torchvision.transforms.functional.resized_crop(img, i, j, h, w, size, interpolation=2)

torchvision.transforms.functional.rotate(img, angle, resample=False, expand=False, center=None)


torchvision.transforms.functional.to_grayscale(img, num_output_channels=1)

torchvision.transforms.functional.to_pil_image(pic, mode=None)

torchvision.transforms.functional.to_tensor(pic)