torch之Resnet残差网络

酥酥 发布于 2022-04-17 90 次阅读

残差网络（ResNet）

				
					import time
import torch
from torch import nn, optim
import torch.nn.functional as F

import sys
sys.path.append("..") 
import d2lzh_pytorch as d2l
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

print(torch.__version__)
print(device)
				
			
1.11.0+cu113
cuda

残差块

				
					class Residual(nn.Module):  # 本类已保存在d2lzh_pytorch包中方便以后使用
    def __init__(self, in_channels, out_channels, use_1x1conv=False, stride=1):
        super(Residual, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1, stride=stride)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.bn2 = nn.BatchNorm2d(out_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)
        return F.relu(Y + X)
				
			
				
					blk = Residual(3, 3)
X = torch.rand((4, 3, 6, 6))
blk(X).shape
				
			
				
					blk = Residual(3, 6, use_1x1conv=True, stride=2)
blk(X).shape
				
			
torch.Size([4, 3, 6, 6])

ResNet模型

				
					net = 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(in_channels, out_channels, num_residuals, first_block=False):
    if first_block:
        assert in_channels == out_channels # 第一个模块的通道数同输入通道数一致
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(in_channels, out_channels, use_1x1conv=True, stride=2))
        else:
            blk.append(Residual(out_channels, out_channels))
    return nn.Sequential(*blk)
				
			
				
					net.add_module("resnet_block1", resnet_block(64, 64, 2, first_block=True))
net.add_module("resnet_block2", resnet_block(64, 128, 2))
net.add_module("resnet_block3", resnet_block(128, 256, 2))
net.add_module("resnet_block4", resnet_block(256, 512, 2))
				
			
				
					net.add_module("global_avg_pool", d2l.GlobalAvgPool2d()) # GlobalAvgPool2d的输出: (Batch, 512, 1, 1)
net.add_module("fc", nn.Sequential(d2l.FlattenLayer(), nn.Linear(512, 10)))
				
			
				
					X = torch.rand((1, 1, 224, 224))
for name, layer in net.named_children():
    X = layer(X)
    print(name, ' output shape:\t', X.shape)
				
			
				
					batch_size = 256
# 如出现“out of memory”的报错信息，可减小batch_size或resize
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)

lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)
				
			
training on  cuda
epoch 1, loss 0.0015, train acc 0.853, test acc 0.885, time 31.0 sec
epoch 2, loss 0.0010, train acc 0.910, test acc 0.899, time 31.8 sec
epoch 3, loss 0.0008, train acc 0.926, test acc 0.911, time 31.6 sec
epoch 4, loss 0.0007, train acc 0.936, test acc 0.916, time 31.8 sec
epoch 5, loss 0.0006, train acc 0.944, test acc 0.926, time 31.5 sec