深度学习pytorch——基于CIFAR-10数据集的Lenet5、Resnet的实战（持续更新）

主函数main：

import torch
from torch.utils.data import DataLoader
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets,transforms
# from Lenet5 import Lenet5
from Resnet import ResNet18

def main():
    batchsz = 128  # how to make sure?
    # load train data
    cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])
    ]), download=True)
    cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)

    cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])
    ]), download=True)
    cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)

    x, label = iter(cifar_train).__next__()    # ?
    print('x:',x.shape,'label:',label.shape)

    device = torch.device('cuda')
    # model = Lenet5().to(device)
    model = ResNet18().to(device)
    criteon = nn.CrossEntropyLoss().to(device)
    optimizer = optim.Adam(model.parameters(), lr=1e-3)
    print(model)
    for epoch in range(1000):

        model.train()
        for batch_idx, (x, label) in enumerate(cifar_train):
            x, label = x.to(device), label.to(device)
            logits = model(x)
            loss = criteon(logits, label)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        # test
        model.eval()
        with torch.no_grad():   # test has no user for caculating grad.
            total_correct = 0
            total_num = 0
            for x, label in cifar_test:
                x, label = x.to(device), label.to(device)
                logits = model(x)
                pred = logits.argmax(dim=1)
                correct = torch.eq(pred, label).float().sum().item()
                total_correct += correct
                total_num += x.size(0)

            acc = total_correct/total_num
            print(epoch, acc)

if __name__ == '__main__':
    main()

Lenet5类：

import torch
from torch import nn
from torch.nn import functional as F

class Lenet5(nn.Module):

    def __init__(self):
        super(Lenet5, self).__init__()
        self.conv_unit = nn.Sequential(
            nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=0),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=0),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
        )
        # flatten
        self.fc_unit = nn.Sequential(
            nn.Linear(32*5*5, 32),
            nn.ReLU(),
            # nn.Linear(120, 84),
            # nn.ReLU(),
            nn.Linear(32, 10)
        )

        tmp = torch.randn(2, 3, 32, 32)
        out = self.conv_unit(tmp)
        print('con out:', out.shape)
        # con out: torch.Size([2, 32, 5, 5])

    def forward(self, x):   # indent make no mistake
        batchsz = x.size(0)
        x = self.conv_unit(x)
        x = x.view(batchsz, 32 * 5 * 5)
        logits = self.fc_unit(x)

        return logits
def main():
    net = Lenet5()

    tmp = torch.randn(2, 3, 32, 32) # ?
    out = net(tmp)
    print('lenet out:', out.shape)

if __name__ == '__main__':
    main()

Resnet类：

import torch
from torch import nn
from torch.nn import functional as F

class ResBlk(nn.Module):
    def __init__(self, ch_in, ch_out, stride=1):
        super(ResBlk, self).__init__()

        self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(ch_out)
        self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
        self.bn2 = nn.BatchNorm2d(ch_out)

        self.extra = nn.Sequential()
        if ch_out != ch_in:
            self.extra = nn.Sequential(
                nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
                nn.BatchNorm2d(ch_out)
            )

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        # short cut.
        out = self.extra(x) + out   # aim:x is the same of out.
        out = F.relu(out)
        return out  # the result of the final prediction

class ResNet18(nn.Module):
    def __init__(self):
        super(ResNet18, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=3, padding=0),
            nn.BatchNorm2d(64)
        )
        self.blk1 = ResBlk(64, 128, stride=2)
        self.blk2 = ResBlk(128, 256, stride=2)
        self.blk3 = ResBlk(256, 512, stride=2)
        self.blk4 = ResBlk(512, 512, stride=2)
        self.outlayer = nn.Linear(512*1*1, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))

        x = self.blk1(x)
        x = self.blk2(x)
        x = self.blk3(x)
        x = self.blk4(x)

        x = F.adaptive_avg_pool2d(x, [1, 1])
        x = x.view(x.size(0), -1)
        x = self.outlayer(x)

        return x

def main():
    blk = ResBlk(64, 128, stride=4)
    tmp = torch.randn(2, 64, 32, 32)
    out = blk(tmp)
    print('block:', out.shape)

    x = torch.randn(2, 3, 32, 32)
    model = ResNet18()
    out = model(x)
    print('resnet:', out.shape)

if __name__ == '__main__':
    main()

想的时候都是困难，做的时候才是答案。