多层感知机实现(单层感知器和多层感知器)

大家好，又见面了，我是你们的朋友全栈君。

前面利用了softmax来对图像进行分类，也可以使用多层感知机的方法对图像进行分类。

多层感知机从零开始实现方法

1.导入包

import torch
import numpy as np
import sys
sys.path.append("..") # 为了导入上层目录的d2lzh_pytorch
import d2lzh_pytorch as d2l

print(torch.__version__)

2.获取和读取数据

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

3.定义模型参数

num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)

params = [W1, b1, W2, b2]
for param in params:
    param.requires_grad_(requires_grad=True)

4.定义激活函数

def relu(X):
    return torch.max(input=X, other=torch.tensor(0.0))

5.定义模型

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

6.定义损失函数

loss = torch.nn.CrossEntropyLoss()

7.训练模型

num_epochs, lr = 5, 100.0
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)

简洁实现的方法：

1.定义模型

num_inputs, num_outputs, num_hiddens = 784, 10, 256
    
net = nn.Sequential(
        d2l.FlattenLayer(),
        nn.Linear(num_inputs, num_hiddens),
        nn.ReLU(),
        nn.Linear(num_hiddens, num_outputs), 
        )
    
for params in net.parameters():
    init.normal_(params, mean=0, std=0.01)

2.读取数据并训练模型

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
loss = torch.nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(net.parameters(), lr=0.5)

num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)