多层感知机的实现

一: 从0开始实现, 代码如下

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)#加载数据集和测试集
num_inputs, num_outputs, num_hiddens = 784,10,256
w1 = nn.Parameter(torch.randn(
    num_inputs, num_hiddens, requires_grad=True) * 0.01)#w1是inputs行hiddens列矩阵
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))##b1是1行hidden列矩阵
w2 = nn.Parameter(torch.randn(
    num_hiddens, num_outputs, requires_grad=True) * 0.01)#w2是hiddens行outputs列矩阵
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))#b2是1行outputs列矩阵
params =[w1,b1,w2,b2]
def relu(X):#激活函数, 就是对y=wx+b的y做一个转换操作
    a = torch.zeros_like(X)
    return torch.max(X, a)
def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(X@w1 + b1)  # 这里“@”代表矩阵乘法
    return (H@w2 + b2)
loss = nn.CrossEntropyLoss(reduction='none')
num_epochs, lr = 5, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)#调用了以上定义的所有函数
d2l.plt.show()

运行结果如图

 

二: 简洁实现, 代码如下

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))
#定义w1,w2与激活函数与网络模型
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, 5
loss = nn.CrossEntropyLoss(reduction='none')#定义损失函数
trainer = torch.optim.SGD(net.parameters(), lr=lr)#定义反向传播

train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)#加载数据集与测试集
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
d2l.plt.show()

运行结果如图