pytorch 图片处理

读取图片并对大小处理

简述

• Scale是做比例放缩
• CenterCrop是切割

注意，只有PIL读取的图片才能被tranforms接受emmmm（有内鬼终止交易）

from PIL import Image
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
def readImage(path='../mode.jpg', size=256):
    mode = Image.open(path)
    transform1 = transforms.Compose([
        transforms.Scale(size),
        transforms.CenterCrop((size, size)),
        transforms.ToTensor()
    ])
    mode = transform1(mode)
    return mode
def showTorchImage(image):
    mode = transforms.ToPILImage()(image)
    plt.imshow(mode)
    plt.show()
if __name__ == '__main__':
    mode = readImage(size=256)
    showTorchImage(mode)

参考

• https://blog.csdn.net/a19990412/article/details/84793917
• http://effbot.org/imagingbook/image.htm