d2l&Softmax&pytorch

Softmax回归

Softmax回归是个分类问题，他将预测值映射在[0，1]之间，从而可以预测概率。相较于线性回归，它只是增加了一个激活函数以及输出层的个数。并且关于Weight参数的个数可以看出来增加了三倍。

简单实现步骤

1. 构建Fashion-MNIST数据集
   Fashion-MNIST数据集是图像数据，是一个Class=10的分类任务
2. 构建模型并初始化参数
   这里由于数据的是图像数据，我们需要读取图片数据(RGB)转为一维的tensor数据(不使用卷积操作)，所以相比于线性回归，Softmax回归只不过是最后用了Softmax函数映射成了概率。
3. 定义损失函数
   由于这里是分类问题，常用交叉熵损失
4. 定义优化器
   这里使用SGD，一般Adam在图像分类问题收敛不好。
5. Train

输入数据

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

搭建网络

# 初始化参数
def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

net = nn.Sequential(nn.Fltten(), nn.Linear(28*28, 10))
net.apply(init_weights)

继承nn.Modult类版本：

class Net(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(Net, self).__init__()
        self.flat = nn.Flatten()
        self.linear = nn.Linear(input_dim, output_dim)

    def forward(self, x):
        return self.linear(self.flat(x))

损失函数

# 损失函数
loss = nn.CrossEntropyLoss()

优化器

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

train

这里直接导入d2l库的训练模块train_ch3

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

可能有bug->RuntimeError: DataLoader worker (pid(s) 9528, 8320) exited unexpectedly
是因为电脑进程数不够导致的。
修改源码:

d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer,  num_workers=0)

解决BUG!
完整代码：

import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt

# 初始化参数
def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)


batch_size = 32
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, num_workers=0)
# net = nn.Sequential(nn.Flatten(), nn.Linear(28*28, 10))


class Net(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(Net, self).__init__()
        self.flat = nn.Flatten()
        self.linear = nn.Linear(input_dim, output_dim)

    def forward(self, x):
        return self.linear(self.flat(x))


net = Net(28*28, 10)

net.apply(init_weights)
# 损失函数
loss = nn.CrossEntropyLoss()
# 优化器
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
plt.show()

epoch大约6、7模型训练就比较好了。epoch大于10可能会过拟合。

附：train_ch3具体文档实现:

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
    for X, y in data_iter:
        metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[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())


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]


class Animator:  #@save
    """在动画中绘制数据。"""
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
                 ylim=None, xscale='linear', yscale='linear',
                 fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
                 figsize=(3.5, 2.5)):
        # 增量地绘制多条线
        if legend is None:
            legend = []
        d2l.use_svg_display()
        self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
        if nrows * ncols == 1:
            self.axes = [self.axes, ]
        # 使用lambda函数捕获参数
        self.config_axes = lambda: d2l.set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts

    def add(self, x, y):
        # 向图表中添加多个数据点
        if not hasattr(y, "__len__"):
            y = [y]
        n = len(y)
        if not hasattr(x, "__len__"):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]
        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)
        self.axes[0].cla()
        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y, fmt)
        self.config_axes()
        display.display(self.fig)
        display.clear_output(wait=True)


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.backward()
            updater.step()
            metric.add(float(l) * len(y), accuracy(y_hat, y),
                       y.size().numel())
        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准确率
    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,))
    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