main1.py

import matplotlib.pyplot as plt
import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt
import time
class timeTool:
    def start(self):
        self.tic = time.time()
    def end(self):
        self.toc = time.time()
        usetime = self.toc - self.tic
        print(f"completed! usetime = {usetime:.2f}s")

t = timeTool();
t.start()


net = nn.Sequential(
    # 这⾥，我们使⽤⼀个11*11的更⼤窗⼝来捕捉对象。
    # 同时，步幅为4，以减少输出的⾼度和宽度。
    # 另外，输出通道的数⽬远⼤于LeNet
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    # 减⼩卷积窗⼝，使⽤填充为2来使得输⼊与输出的⾼和宽⼀致，且增⼤输出通道数
    nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    # 使⽤三个连续的卷积层和较⼩的卷积窗⼝。
    # 除了最后的卷积层，输出通道的数量进⼀步增加。
    # 在前两个卷积层之后，汇聚层不⽤于减少输⼊的⾼度和宽度
    nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.Flatten(),
    # 这⾥，全连接层的输出数量是LeNet中的好⼏倍。使⽤dropout层来减轻过拟合
    nn.Linear(6400, 4096), nn.ReLU(),
    nn.Dropout(p=0.5),
    nn.Linear(4096, 4096), nn.ReLU(),
    nn.Dropout(p=0.5),
    # 最后是输出层。由于这⾥使⽤Fashion-MNIST，所以⽤类别数为10，⽽⾮论⽂中的1000
    nn.Linear(4096, 10))

batch_size = 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.01, 20
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
plt.show()
t.end()