【动手学习pytorch笔记】16.ResNet

ResNet

残差块结构

import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l


class Residual(nn.Module):  #@save
    def __init__(self, input_channels, num_channels,use_1x1conv=False, strides=1):
        super().__init__()
        self.conv1 = nn.Conv2d(input_channels, num_channels,kernel_size=3, padding=1, stride=strides)
        self.conv2 = nn.Conv2d(num_channels, num_channels,kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(input_channels, num_channels,
                                   kernel_size=1, stride=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)

    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
        Y += X
        return F.relu(Y)

参数use_1x1conv=False：是否需要1 * 1卷积

blk = Residual(3,3)
X = torch.rand(4, 3, 6, 6)
Y = blk(X)
Y.shape

输出

torch.Size([4, 3, 6, 6])

可以看到Residual块不改变模型输入输出大小

blk = Residual(3,6, use_1x1conv=True, strides=2)
blk(X).shape

输出

torch.Size([4, 6, 3, 3])

这里通道数从3翻倍成了6

构建模型

7 * 7卷积 + MaxPooling

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

定义大的残差块，作用是判断是不是第一个

def resnet_block(input_channels, num_channels, num_residuals,
                 first_block=False):
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(input_channels, num_channels,
                                use_1x1conv=True, strides=2))
        else:
            blk.append(Residual(num_channels, num_channels))
    return blk

b相当于stage

b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

net = nn.Sequential(b1, b2, b3, b4, b5,
                    nn.AdaptiveAvgPool2d((1,1)),
                    nn.Flatten(), nn.Linear(512, 10))

每层输入输出变化情况

X = torch.rand(size=(1, 1, 224, 224))
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape:\t', X.shape)

输出

Sequential output shape:	 torch.Size([1, 64, 56, 56])
Sequential output shape:	 torch.Size([1, 64, 56, 56])
Sequential output shape:	 torch.Size([1, 128, 28, 28])
Sequential output shape:	 torch.Size([1, 256, 14, 14])
Sequential output shape:	 torch.Size([1, 512, 7, 7])
AdaptiveAvgPool2d output shape:	 torch.Size([1, 512, 1, 1])
Flatten output shape:	 torch.Size([1, 512])
Linear output shape:	 torch.Size([1, 10])

都是通道数翻倍，模型减半

训练

lr, num_epochs, batch_size = 0.05, 10, 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

loss 0.010, train acc 0.998, test acc 0.894
567.7 examples/sec on cuda:0

为什么ResNet能解决梯度消失问题