多层感知机的简洁实现

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
import torchvision
from torchvision import transforms
import time

class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer, self).__init__()
    def forward(self, x): # x shape: (batch, *, *, ...)
        return x.view(x.shape[0], -1)

def load_data_fashion_mnist(batch_size):
    mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True,
                                                    transform=transforms.ToTensor())
    mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True,
                                                   transform=transforms.ToTensor())

    if sys.platform.startswith('win'):
        num_workers = 0  # 0表示不用额外的进程来加速读取数据
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
    start = time.time()
    for X, y in train_iter:
        continue
    print('load time: %.2f sec' % (time.time() - start))
    return train_iter, test_iter

def evaluate_accuracy(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()
            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]  #有多少行标签就是有多少个样本
        test_acc = evaluate_accuracy(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_inputs, num_outputs, num_hiddens =  784, 10, 256

net = nn.Sequential(
    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)

batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)
loss = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.5)

num_epochs = 5

train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)