多层感知机

输入和输出中间，增加了隐藏层

隐藏层先做 w * x + b的线性运算，再组合 rule、sigmod、tanh的非线性运算

多层感知机的超参有

• 学习率 learning rate
• 批大小 batch_size
• 训练周期 epoches
• 隐藏层的个数，以及每层的神经元个数

简易实现

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, num_outputs, num_hiddens = 784, 10, 256

# 定义两个矩阵
W1 = nn.Parameter(torch.randn(
    num_inputs, num_hiddens, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(
    num_hiddens, num_outputs, requires_grad=True) * 0.01)
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))

params = [W1, b1, W2, b2]

def rule(X):
    return torch.max(X, torch.zeros_like(X))

def net(X):
    X = X.reshape((-1, num_inputs))
    H = rule(X@W1 + b1)
    return (H@W2 + b2)

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

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

torch工具类实现

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)