深度学习——多层感知机实现代码

一从零实现

import torch
from torch import nn
from d2l import torch as d2

1.加载数据集

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

2.初始化模型参数 输入是向量

num_inputs = 784  # 每个图像的灰度像素28*28=784
num_outputs = 10  # 10个类别
num_hiddens = 256  # 256隐藏单元

# 输入层--隐藏层
W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
# 隐藏层--输出层
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]

3.实现relu激活函数

def relu(x):
    a = torch.zeros_like(x)  # 全0
    return torch.max(x, a)

4.实现模型

def net(x):
    x = x.reshape((-1, num_inputs))  # 二维图像转换为一个num_inputs向量
    h = relu(x @ W1 + b1)  # @ 矩阵乘法 隐藏层: 激活函数
    return (h @ W2 + b2)  # 输出 h*w2+b2

5.损失函数

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

6.训练

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

二简单实现

1.创建网络
# 网络 256隐藏单元  展平--线性层输入---激活函数-- 线性层输出
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 10))

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


net.apply(init_weight)

2.训练

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)