0903Softmax简洁实现

点击查看代码

import torch
import torchvision
from torch import nn
from d2l import torch as d2l
from torch.utils import data
from torchvision.transforms import transforms

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
# trans = transforms.ToTensor()
# train_set = torchvision.datasets.FashionMNIST(root="./data", train=True,
#                                                 transform=trans, download=True)
# test_set = torchvision.datasets.FashionMNIST(root="./data", train=False,
#                                                transform=trans, download=True)
#
#
# train_iter = data.DataLoader(train_set, batch_size, shuffle=True)
# test_iter = data.DataLoader(test_set, batch_size, shuffle=True)

# 初始化模型参数
# PyTorch不会隐式地调整输入的形状。因此，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);

# 交叉熵损失函数
loss = nn.CrossEntropyLoss(reduction='none')

# 优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)

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)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())


# 评估在任意模型net的精度
def evaluate_accuracy(net, data_iter):  #@save
    """计算在指定数据集上模型的精度"""
    # isinstance 判断一个对象的变量类型
    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())
    return metric[0] / metric[1]

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、训练准确度总和、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）"""
    # animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
    #                     legend=['train loss', 'train acc', 'test acc'])
    for epoch in range(num_epochs):
        train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
        test_acc = evaluate_accuracy(net, test_iter)
        # animator.add(epoch + 1, train_metrics + (test_acc,))
        print("train_acc:{},train_loss:{},".format(train_metrics[1], train_metrics[0]))
        print("test_acc:{}".format(test_acc))
    train_loss, train_acc = train_metrics

num_epochs = 2
# d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)

d2l.predict_ch3(net, test_iter)