import torch
from torch import nn
import d2l
net=nn.Sequential(nn.Conv2d(1,96,11,padding=1,stride=4),nn.ReLU(),nn.MaxPool2d(kernel_size=3,stride=2),nn.Conv2d(96,256,5,padding=2),nn.ReLU(),nn.MaxPool2d(kernel_size=3,stride=2),nn.Conv2d(256,384,3,padding=1),nn.ReLU(),nn.Conv2d(384, 384, 3, padding=1),nn.ReLU(),nn.Conv2d(384, 256, 3, padding=1),nn.ReLU(),nn.MaxPool2d(3,stride=2),nn.Flatten(),nn.Linear(6400,4096),nn.ReLU(),nn.Dropout(p=0.5),nn.Linear(4096,4096),nn.ReLU(),nn.Dropout(p=0.5),nn.Linear(4096,10)
)
X=torch.rand((1,1,224,224))
for layer in net:X=layer(X)print(layer.__class__.__name__,X.shape)
二.训练AlexNet
import torch
from torch import nn
from d2l import torch as d2lnet=nn.Sequential(nn.Conv2d(1,96,11,padding=1,stride=4),nn.ReLU(),nn.MaxPool2d(kernel_size=3,stride=2),nn.Conv2d(96,256,5,padding=2),nn.ReLU(),nn.MaxPool2d(kernel_size=3,stride=2),nn.Conv2d(256,384,3,padding=1),nn.ReLU(),nn.Conv2d(384, 384, 3, padding=1),nn.ReLU(),nn.Conv2d(384, 256, 3, padding=1),nn.ReLU(),nn.MaxPool2d(3,stride=2),nn.Flatten(),nn.Linear(6400,4096),nn.ReLU(),nn.Dropout(p=0.5),nn.Linear(4096,4096),nn.ReLU(),nn.Dropout(p=0.5),nn.Linear(4096,10)
)
batch_size = 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size=batch_size,resize=224)
def evaluate_accuracy_gpu(net, data_iter, device=None): #data_iter测试数据量"""使用GPU计算模型在数据集上的精度"""if isinstance(net, nn.Module):net.eval() # 设置为评估模式if not device:device = next(iter(net.parameters())).device# 正确预测的数量，总预测的数量metric = d2l.Accumulator(2)with torch.no_grad():for X, y in data_iter:if isinstance(X, list):# BERT微调所需的（之后将介绍）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]#测试正确率
#@save
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):"""用GPU训练模型(在第六章定义)"""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)optimizer = torch.optim.SGD(net.parameters(), lr=lr)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):# 训练损失之和，训练准确率之和，样本数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()#更新参数with torch.no_grad():metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])timer.stop()#训练损失率和正确率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)}')
lr, num_epochs = 0.01, 10
train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
