LeNet网络的实现

LeNet网络的实现

import torch
from torch import nn
from d2l import torch as d2lx = 28
net = nn.Sequential(nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(),nn.AvgPool2d(kernel_size=2, stride=2),nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),nn.AvgPool2d(kernel_size=2, stride=2),nn.Flatten(),nn.Linear(16 * (x/4 - 2) * (x/4 - 2), 120), nn.Sigmoid(),nn.Linear(120, 84), nn.Sigmoid(),nn.Linear(84, 10))

输入图像是单通道 x*x大小

1. 卷积层。
   输入一个通道，输出六个通道，卷积核大小5*5，填充2，步幅1,因此输出图像大小不变。
2. 平均汇聚层。
   核大小2*2，步幅2，因此输出图像大小减半。（x/2)(x/2）
3. 卷积层。
   输入6通道，输出16通道，核大小5，输出图像大小减4.(x/2-4) (x/2 - 4)
4. 平均汇聚层。
   核大小2*2，步幅2，输出大小减半。(x/4-2)(x/4-2)
5. 全连接层。
   输入大小： 16 * (x/4 - 2) * (x/4 - 2)
   输出大小： 10

测试函数

def evaluate_accuracy_gpu(net , data_iter,device=None):if isinstance(net , nn.Module):net.eval()if not device:# 获取第一个参数所在的设备，把以后的数据放在同一个设备上device = next(iter(net.parameters())).devicemetric = d2l.Accumulator(2)with torch.no_grad():for X , y in data_iter:if isinstance(X , list):X = [x.to(device) for x in X]else:X = X.to(device)y = y.to(device)metric.add(d2l.accuracy(net(X),y) , y.numel())return metric[0] / metric[1]

训练和测试

def train_ch6(net , train_iter , test_iter, num_epochs , lr ,device):# 初始化权重def init_weights(m):if type(m) == nn.Linear or type(m) == nn.Conv2d:nn.init.xavier_uniform_(m.weight)net.apply(init_weights)print( ' training on ' , device)net.to(device)# 优化器  optimizer = torch.optim.SGD(net.parameters(), lr)# 损失函数loss = nn.CrossEntropyLoss()animator = d2l.Animator(xlabel='epoch',xlim=[1 , num_epochs],legend=['train loss','train acc','test acc'])timer , num_batches = d2l.Timer() , len(train_iter)for epoch in range(num_epochs):metric = d2l.Accumulator(3)net.train()for i , (X, y ) in enumerate(train_iter):timer.start()optimizer.zero_grad()X , y = X.to(device) , y.to(device)y_hat = net(X)l = loss(y_hat , y)l.backward()optimizer.step()with torch.no_grad():metric.add(l*X.shape[0] , d2l.accuracy(y_hat , y) , X.shape[0])timer.stop()train_l = metric[0] / metric[2]train_acc = metric[1] / metric[2]if (i+1) % (num_batches //5) ==0 or i ==num_batches - 1:animator.add(epoch + (i+1) /num_batches,(train_l , train_acc , None))test_acc = evaluate_accuracy_gpu(net , test_iter)animator.add(epoch+1 ,(None , None , test_acc))print(f'loss {train_l:.3f},train_acc {train_acc:.3f} ,  'f'test_acc{test_acc:.3f}')print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec'f'on {str(device)}')