使用Fashion-mnist数据集，一个隐藏层：

 

                          

 

 

多层感知机从零实现

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)

input_nums, hidden_nums, output_nums = 784, 256, 10

W1 = nn.Parameter(torch.randn(input_nums, hidden_nums) * 0.01)
b1 = nn.Parameter(torch.zeros(hidden_nums))
W2 = nn.Parameter(torch.randn(hidden_nums, output_nums) * 0.01)
b2 = nn.Parameter(torch.zeros(output_nums))

params = [W1, b1, W2, b2]

def net(X):
    X = X.reshape((-1, input_nums))
    H = torch.matmul(X, W1) + b1
    H = torch.relu(H)
    return torch.matmul(H, W2) + b2

loss = nn.CrossEntropyLoss(reduction="none")

num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)

 

多层感知机简洁实现

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

net = nn.Sequential(nn.Flatten(), nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 10))

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

batch_size, lr, num_epochs = 256, 0.1, 10
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=lr)

train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)