pytorch实现ResNet-18

ResNet-18

残差学习单元

网络层数越多，并不意味着效果越好。当网络深度更深的时候，每一层的误差积累，最终会导致梯度弥散。最后几层能很好的更新，但是前面几层会一直得不到更新。

ResNet设置一个机制，增加短路连接。使30层的网络最差最差也可以退换成22层。

短路连接：如果ch_in和ch_out维度不一致，就把x维度变成ch_out维度。

ResNet-18 结构

Pytorch构建ResNet-18

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2021/7/30 23:19
# @Author  : Liu Lihao
# @File    : resnet.py

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


'''
ResBlock
'''
class ResBlk(nn.Module):

    def __init__(self, ch_in, ch_out, stride=1):
        # 通过stride减少参数维度
        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)


        # [b, ch_in, h, w] => [b, ch_out, h, w]
        self.extra = nn.Sequential(
            nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
            nn.BatchNorm2d(ch_out)
        )

    def forward(self, x):
        '''
        :param x: [b, ch, h, w]
        :return:
        '''
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        # short cut
        # extra module: [b, ch_in, h, w] => [b, ch_out, h, w]
        # element-wise add:
        out = self.extra(x) + out

        return out


'''
ResNet-18
'''
class ResNet18(nn.Module):

    def __init__(self):
        super(ResNet18, self).__init__()

        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64)
        )

        # follow 4 blocks
        # [b, 64, h, w] => [b, 128, h/2, w/2]
        self.blk1 = ResBlk(64, 128, stride=2)
        # [b, 128, h/2, w/2] => [b, 256, h/4, w/4]
        self.blk2 = ResBlk(128, 256, stride=2)
        # [b, 256, h/4, w/4] => [b, 512, h/8, w/8]
        self.blk3 = ResBlk(256, 512, stride=2)
        # [b, 512, h/8, w/8] => [b, 512, h/16, w/16]
        self.blk4 = ResBlk(512, 512, stride=2)

        self.out_layer = nn.Linear(512*1*1, 10)

    def forward(self, x):

        # [b, 3, h, w] => [b, 64, h, w]
        x = F.relu(self.conv1(x))

        # [b, 64, h, w] => [b, 512, h/16, w/16]
        x = self.blk1(x)
        x = self.blk2(x)
        x = self.blk3(x)
        x = self.blk4(x)

        # [b, 512, h/16, w/16] => [b, 512, 1, 1]
        x = F.adaptive_avg_pool2d(x, [1, 1])

        # [b, 512, 1, 1] => [b, 512]
        x = x.view(x.size(0), -1)
        # [b, 512] => [b, 10]
        x = self.out_layer(x)

        return x


if __name__ == '__main__':
    res_net = ResNet18()
    tmp = torch.randn(2,3,32,32)
    print(res_net.forward(tmp).shape)

使用CIFAR10数据集测试ResNet-18

CIFAR10数据集介绍

• data – 10000x3072 的uint8s格式numpy数组。数组的每一行存储一个32x32的彩色图像，按顺序包含红色、绿色和蓝色三个通道的值，因此每行的长度为32x32x3=3072。图像按行进行存储，如数组的前32个值是图像第一行的红色通道值。
• labels – 取值为0-9的包含10000个数字的list。索引i处的数字表示数组data中第i个图像的标签。

使用CIFAR10数据集测试ResNet-18

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2021/7/30 22:09
# @Author  : Liu Lihao
# @File    : origin_restnet_main.py

import torch
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch import nn, optim
from resnet import ResNet18

def main():
    batchsz = 32

    '''引入训练集'''
    # 一次加载一张图片
    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)
    # 载入多张照片
    cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)  # shuffle随机化

    '''引入测试集'''
    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)
    # 载入多张照片
    cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)

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


    '''定义模型，loss函数，优化器'''
    device = torch.device('cuda')
    model = ResNet18().to(device)
    lossFuction = nn.CrossEntropyLoss().to(device)
    optimizer = optim.Adam(model.parameters(), lr=1e-3)  # 不需要转换到GPU
    print(model)

    '''开始训练和评估'''
    for epoch in range(1000):

        '''train'''
        model.train()  # train模式：启用Dropout， Batch Normalization的参数会学习和更新
        for batchidx, (x, label) in enumerate(cifar_train):
            # x: [b, 3, 32, 32]
            # y: [b]
            x, label = x.to(device), label.to(device)

            # logits: [b, 10]
            logits = model(x)

            # loss: tensor scalar （标量）
            loss = lossFuction(logits, label)

            # backward
            optimizer.zero_grad()  # 每次backward会对梯度累加，因此每次backward前要把梯度清零
            loss.backward()
            optimizer.step()

        print(epoch, 'loss:', loss.item())


        '''eval'''
        model.eval()  # eval模式：不启用Dropout，Batch Normalization的参数保持不变
        with torch.no_grad():  # 告诉pytorch，此段不需要构建计算图，更加安全
            # test
            total_correct = 0
            total_num = 0
            for x, label in cifar_test:
                # x: [b, 3, 32, 32]
                # y: [b]
                x, label = x.to(device), label.to(device)

                # logits: [b, 10]
                logits = model(x)
                # pred: [b]
                pred = logits.argmax(dim=1)
                # [b] vs [b] => scalar tensor
                correct = torch.eq(pred, label).float().sum().item()
                # print(correct)
                total_correct += correct
                total_num += x.size(0)

            acc = total_correct / total_num
            print(epoch, 'test acc:', acc)



if __name__ == '__main__':
    main()