4.3 多层感知机的简洁实现

import torch
from torch import nn
from d2l import torch as d2l

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

num_inputs = 28 * 28
num_outputs = 10
num_hiddens = 256

#注意从数据集train_iter中拿到的小批量X维度是batch_size*28*28的，需要先将其展平成batch_size*784的
net = nn.Sequential(nn.Flatten(),
                    nn.Linear(num_inputs,num_hiddens),
                    nn.ReLU(),
                    nn.Linear(num_hiddens,num_outputs)
                   )

def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight,std=0.01)
    return 

net.apply(init_weights)

loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(),lr=0.1)
num_epochs = 5
d2l.train_ch3(net,train_iter,test_iter,loss,num_epochs,trainer)

在这里，

注意：

1. 从数据集train_iter中拿到的小批量X维度是batch_size*28*28的，需要先将其展平成batch_size*784的。

2. nn.Linear()的两个参数分别是线性层（全连接层）的输入神经元的个数（即输入特征数）和输出神经元的个数（即输出特征数）.