动手学深度学习PyTorch（三）：softmax回归

import torch
import torchvision
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

## 1.获取和读取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

## 2.初始化模型参数
num_inputs = 784
num_outputs = 10

W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True) 

## 3.定义模型
def net(X):
    return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

## 4.定义损失函数
def cross_entropy(y_hat, y):
    return - torch.log(y_hat.gather(1, y.view(-1, 1)))

## 4.分类准确率计算函数
def accuracy(y_hat, y):
    return (y_hat.argmax(dim=1) == y).float().mean().item()

## 5.模型训练
num_epochs, lr = 5, 0.1

# 本函数已保存在d2lzh包中方便以后使用
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:
                d2l.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_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))

train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)

## 6.模型预测
X, y = iter(test_iter).next()

true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

d2l.show_fashion_mnist(X[0:9], titles[0:9])

简洁实现

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

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

num_inputs = 784
num_outputs = 10

class LinearNet(nn.Module):
    def __init__(self, num_inputs, num_outputs):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(num_inputs, num_outputs)
    def forward(self, x): # x shape: (batch, 1, 28, 28)
        y = self.linear(x.view(x.shape[0], -1))
        return y
    
net = LinearNet(num_inputs, num_outputs)

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)

net = nn.Sequential(
    # FlattenLayer(),
    # nn.Linear(num_inputs, num_outputs)
    OrderedDict([
        ('flatten', FlattenLayer()),
        ('linear', nn.Linear(num_inputs, num_outputs))
    ])
)

init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0) 

loss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)

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