动手学习深度学习-构建LeNet网络

#coding=utf-8
import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'

import torch
from torch import nn
from d2l import torch as d2l
class Reshape(nn.Module):
    def forward(self,x):
        return x.view(-1,1,28,28)

net=torch.nn.Sequential(
    Reshape(),
    nn.Conv2d(1,6,kernel_size=5,padding=2),
    nn.Sigmoid(),
    nn.AvgPool2d(2,stride=2),
    nn.Conv2d(6,16,kernel_size=5),
    nn.Sigmoid(),
    nn.AvgPool2d(2,stride=2),
    nn.Flatten(),
    nn.Linear(16*5*5,120),
    nn.Sigmoid(),
    nn.Linear(120,84),
    nn.Sigmoid(),
    nn.Linear(84,10),

)
#生成随机数据集，为下面展示网络结构
'''x=torch.rand(size=(1,1,28,28),dtype=torch.float32)
for layer in net:
    x=layer(x)
    print(layer.__class__.__name__,"output shape:\t",x.shape)
    '''
batch_size=256
train_iter,test_iter=d2l.load_data_fashion_mnist(batch_size=batch_size)

def eveluate_accuracty_gup(net, data_iter,device=None):
    if isinstance(net ,torch.nn.Module):
        net.eval()
        if not device:
            device=next(iter(net.parameters())).device
    #创建累加器，用来累加损失值
    metric=d2l.Accumulator(2)
    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]


lr,num_epochs=0.9,10
d2l.train_ch6(net,train_iter,test_iter,num_epochs,lr,d2l.try_gpu())

train_ch6,李沐老师是展示了详细代码，我太懒了，没有写全，直接进行的d2l库的调用，最后是在GPU上跑的模型