pytorch学习笔记（十一）：pytorch实现多层感知机

下面我们使用PyTorch来实现上一节中的多层感知机。首先导入所需的包或模块。

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("..") 
import d2lzh_pytorch as d2l

1. 定义模型

隐藏层单元个数为256，并使用ReLU函数作为激活函数。

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)

3.10.2 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)


def sgd(params, lr, batch_size):
    for param in params:
        param.data -= lr * param.grad / batch_size # 注意这里更改param时用的param.data
        
def evaluate_accuraacy(data_iter, net):
    acc_sum, n = 0.0, 0
    for X, y in data_iter:
        acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
        n += y.shape[0]
    return acc_sum / n
    
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params=None, lr=None, optimizer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            y_hat = net(X)
            l = loss(y_hat, y).sum()
            
            # 梯度清零
            if optimizer is not None:
                optimizer.zero_grad()
            elif params is not None and params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()
            
            l.backward()
            if optimizer is None:
                sgd(params, lr, batch_size)
            else:
                optimizer.step()  # “softmax回归的简洁实现”一节将用到
            
            
            train_l_sum += l.item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
            n += y.shape[0]
        test_acc = evaluate_accuraacy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
              
num_epochs = 5
train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

输出：

epoch 1, loss 0.0030, train acc 0.712, test acc 0.744
epoch 2, loss 0.0019, train acc 0.823, test acc 0.821
epoch 3, loss 0.0017, train acc 0.844, test acc 0.842
epoch 4, loss 0.0015, train acc 0.856, test acc 0.842
epoch 5, loss 0.0014, train acc 0.864, test acc 0.818