动手学深度学习02：softmax回归的从零实现与简洁实现

动手学深度学习02：softmax回归的从零实现与简洁实现

参考：李沐 《动手学深度学习》 http://zh.d2l.ai/

从零实现

import torch
from IPython import display
from d2l import torch as d2l
import torch
import torchvision
from torch.utils import data
from torchvision import transforms

def get_dataloader_workers():  #@save
    """使用2个进程来读取数据"""
    return 2

def load_data_fashion_mnist(batch_size, resize=None):  #@save
    """下载Fashion-MNIST数据集，然后将其加载到内存中"""
    trans = [transforms.ToTensor()]
    if resize:
        trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(
        root="./data", train=True, transform=trans, download=True)
    mnist_test = torchvision.datasets.FashionMNIST(
        root="./data", train=False, transform=trans, download=True)
    return (data.DataLoader(mnist_train, batch_size, shuffle=True,
                            num_workers=get_dataloader_workers()),
            data.DataLoader(mnist_test, batch_size, shuffle=False,
                            num_workers=get_dataloader_workers()))

# 定义一个load_data_fashion_mnist函数，用于获取和读取Fashion-MNIST数据集
# 这个函数返回训练集和验证集的数据迭代器。 
# 此外，这个函数还接受一个可选参数resize，用来将图像大小调整为另一种形状。
# d2l已经封装好了这个函数，可以直接d2l.load_data_fashion_mnist()调用

batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)

# 原始数据集都是28*28图像，这里需要拉平及784的向量
# 参数初始化
num_inputs = 784
num_outputs = 10

W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)

# 定义softmax
def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdim=True) # 对每一行求和
    return X_exp / partition  # 这里应用了广播机制
# 验证softmax的效果
X = torch.normal(0, 1, (2, 5))
X_prob = softmax(X)
print(X_prob)
print(X_prob.sum(1))

# 定义模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b) # x 此时为 batchsize * 784


# 定义损失函数
def cross_entropy(y_hat, y):
    return - torch.log(y_hat[range(len(y_hat)), y])

# 分类精度
def accuracy(y_hat, y):  #@save
    """计算预测正确的数量"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1) # 每一行中最大元素的索引
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())

def evaluate_accuracy(net, data_iter):  #@save
    """计算在指定数据集上模型的精度"""
    if isinstance(net, torch.nn.Module):
        net.eval()  # 将模型设置为评估模式
    metric = Accumulator(2)  # 正确预测数、预测总数
    with torch.no_grad():
        for X, y in data_iter:
            metric.add(accuracy(net(X), y), y.numel()) # 正确数与总数
    return metric[0] / metric[1]
# 累计器
class Accumulator:  #@save
    """在n个变量上累加"""
    def __init__(self, n):
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]

# 训练

def train_epoch_ch3(net, train_iter, loss, updater):  #@save
    """训练模型一个迭代周期（定义见第3章）"""
    # 将模型设置为训练模式
    if isinstance(net, torch.nn.Module):
        net.train()
    # 训练损失总和、训练准确的总和、样本数
    metric = Accumulator(3)
    for X, y in train_iter:
        # 计算梯度并更新参数
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            # 使用PyTorch内置的优化器和损失函数
            updater.zero_grad()
            l.mean().backward()
            updater.step()
        else:
            # 使用定制的优化器和损失函数
            l.sum().backward()
            updater(X.shape[0])
        metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    # 返回训练损失和训练精度
    return metric[0] / metric[2], metric[1] / metric[2]

def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):  #@save
    """训练模型（定义见第3章）"""
    for epoch in range(num_epochs):
        train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
        test_acc = evaluate_accuracy(net, test_iter)
    train_loss, train_acc = train_metrics
    assert train_loss < 0.5, train_loss
    assert train_acc <= 1 and train_acc > 0.7, train_acc
    assert test_acc <= 1 and test_acc > 0.7, test_acc

lr = 0.1

def updater(batch_size):
    return d2l.sgd([W, b], lr, batch_size)

num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)

def predict_ch3(net, test_iter, n=6):  #@save
    """预测标签（定义见第3章）"""
    for X, y in test_iter:
        break
    # trues = d2l.get_fashion_mnist_labels(y)
    # preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
    # titles = [true +'\n' + pred for true, pred in zip(trues, preds)]
    # d2l.show_images(
    #     X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
    print(y)
    print(net(X).argmax(axis=1))

predict_ch3(net, test_iter)

简洁实现

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

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

# PyTorch不会隐式地调整输入的形状。因此，
# 我们在线性层前定义了展平层（flatten），来调整网络输入的形状
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))

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

net.apply(init_weights)
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)