深度学习实践 6：Resnet 神经网络构建

该实践与深度学习实践5比较类似，只是将Lenet 更换为了Resnet 残差神经网络，具体代码如下：

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


class Residual(nn.Module):
    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)
        self.relu = nn.ReLU(inplace=True)

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

Residual类

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))


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


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))

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

建立的Resnet神经网络。

lr, num_epochs, batch_size = 0.05, 10, 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)
device = torch.device('cuda')
train_ch6(resnet, train_iter, test_iter, num_epochs, lr, device)

输入代码进行运算

结果：

training on cuda
train loss: 0.122427
train acc: 0.951767
test acc: 0.880200