数据集处理相关

iter() 和next()
https://blog.csdn.net/sxingming/article/details/51479039?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522158807744819724843357761%2522%252C%2522scm%2522%253A%252220140713.130102334…%2522%257D&request_id=158807744819724843357761&biz_id=0&utm_source=distribute.pc_search_result.none-task-blog-2_allfirst_rank_v2~rank_v25-2

DataLoader
https://blog.csdn.net/seven08290/article/details/83097841?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522158808105719726867832041%2522%252C%2522scm%2522%253A%252220140713.130102334…%2522%257D&request_id=158808105719726867832041&biz_id=0&utm_source=distribute.pc_search_result.none-task-blog-2_allfirst_rank_v2~rank_v25-2

PIL读取图像

from PIL import Image
lena=Image.open('F:/lena256.jpg')
from matplotlib import pyplot as plt
plt.figure("lena")
plt.imshow(lena)
plt.show()
from torchvision.transforms import ToTensor,ToPILImage
to_tensor=ToTensor()
to_pil=ToPILImage()
input = to_tensor(lena).unsqueeze(0)
output=to_pil(output.squeeze(0))

Sequential

# Sequential的三种写法
net1 = nn.Sequential()
net1.add_module('conv', nn.Conv2d(3, 3, 3))
net1.add_module('batchnorm', nn.BatchNorm2d(3))
net1.add_module('activation_layer', nn.ReLU())

net2 = nn.Sequential(
        nn.Conv2d(3, 3, 3),
        nn.BatchNorm2d(3),
        nn.ReLU()
        )

from collections import OrderedDict
net3= nn.Sequential(OrderedDict([
          ('conv1', nn.Conv2d(3, 3, 3)),
          ('bn1', nn.BatchNorm2d(3)),
          ('relu1', nn.ReLU())
        ]))
print(net1.conv, net2[0], net3.conv1)