transforms.Compose和transforms.ToTensor()

1、图像处理、转不同格式显示

import torch
import torchvision
import torchvision.transforms as transforms
import cv2
import numpy as np
from PIL import Image

img_path = "./data/timg.jpg"  

# transforms.ToTensor()
transform1 = transforms.Compose([
    transforms.ToTensor(),  # range [0, 255] -> [0.0,1.0]
]
)

##numpy.ndarray
img = cv2.imread(img_path)  # 读取图像 3x1080x1920(通道*高*宽)，数值[0, 255]
print("img = ", img)
img1 = transform1(img)  # 归一化到 3x1080x1920(通道*高*宽)，数值[0.0,1.0]
print("img1 = ", img1)

# 转化为numpy.ndarray并显示
img_1 = img1.numpy()*255
img_1 = img_1.astype('uint8')
img_1 = np.transpose(img_1, (1,2,0))
cv2.imshow('img_1', img_1)
cv2.waitKey()

##PIL
img = Image.open(img_path).convert('RGB') # 读取图像
img2 = transform1(img) # 归一化到 [0.0,1.0]
print("img2 = ",img2)

#转化为PILImage并显示
img_2 = transforms.ToPILImage()(img2).convert('RGB')
print("img_2 = ",img_2)
img_2.show()

2、transforms.Compose归一化到[-1.0, 1.0]
将上面的transform1改为如下所示：

transform2 = transforms.Compose([  
    transforms.ToTensor(),  
    transforms.Normalize(mean = (0.5, 0.5, 0.5), std = (0.5, 0.5, 0.5))  
    ]  
)  

解释：
（1）transforms.Compose就是将transforms组合在一起；

（2）transforms.Normalize使用如下公式进行归一化：

channel=（channel-mean）/std(因为transforms.ToTensor()已经把数据处理成[0,1],那么(x-0.5)/0.5就是[-1.0, 1.0])

这样一来，我们的数据中的每个值就变成了[-1,1]的数了。

转载自：https://blog.csdn.net/hao5335156/article/details/80593349?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase