torch--模型选择-欠拟合-过拟合

合集 - torch(9)

1.torch神经网络--线性回归2024-10-052.pytorch之hub模块2024-10-053.torch--minst手写体识别2024-10-064.torch神经网络温度预测2024-10-065.torch找不到CUDA的问题2024-12-176.torch--fashion mnist drop out2024-11-07

7.torch--模型选择-欠拟合-过拟合2024-11-06

8.torch--多层感知机实现图像分类2024-11-049.torch--fashion-minst分类2024-10-31

收起

"""
模型选择，欠拟合、过拟合
"""

import math
import numpy as np
import torch
from d2l import torch as d2l
from IPython import display
import matplotlib.pyplot as plt
from torch import nn


max_degree = 20                                # 多项式的最大阶数
n_train, n_test = 100, 100                     # 训练和测试数据集大小
true_w = np.zeros(max_degree)                  # 分配大量的空间
true_w[0:4] = np.array([5, 1.2, -3.4, 5.6])

features = np.random.normal(size=(n_train + n_test, 1))
np.random.shuffle(features)
poly_features = np.power(features, np.arange(max_degree).reshape(1, -1))
for i in range(max_degree):
    poly_features[:, i] /= math.gamma(i + 1)  # gamma(n)=(n-1)!
# labels的维度:(n_train+n_test,)
labels = np.dot(poly_features, true_w)
labels += np.random.normal(scale=0.1, size=labels.shape)


# NumPy ndarray转换为tensor
true_w, features, poly_features, labels = [torch.tensor(x, dtype=torch.float32) for x in [true_w, features, poly_features, labels]]

features[:2], poly_features[:2, :], labels[:2]


class Animator:
    """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), pic_name=None):
        # 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
        self.pic_name = pic_name

    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()
        plt.draw()
        plt.pause(0.1)
        plt.savefig(self.pic_name)
        display.display(self.fig)
        display.clear_output(wait=True)

    def show(self):
        display.display(self.fig)


def evaluate_loss(net, data_iter, loss):
    """评估给定数据集上模型的损失"""
    metric = d2l.Accumulator(2)  # 损失的总和,样本数量
    for X, y in data_iter:
        out = net(X)
        y = y.reshape(out.shape)
        l = loss(out, y)
        metric.add(l.sum(), l.numel())
    return metric[0] / metric[1]


def train_epoch_ch3(net, train_iter, loss, updater):
    """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 = d2l.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])


def train(train_features, test_features, train_labels, test_labels,
          num_epochs=400, state='正常'):
    loss = nn.MSELoss(reduction='none')
    input_shape = train_features.shape[-1]
    # 不设置偏置，因为我们已经在多项式中实现了它
    net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))
    batch_size = min(10, train_labels.shape[0])
    train_iter = d2l.load_array((train_features, train_labels.reshape(-1, 1)),
                                batch_size)
    test_iter = d2l.load_array((test_features, test_labels.reshape(-1, 1)),
                               batch_size, is_train=False)
    trainer = torch.optim.SGD(net.parameters(), lr=0.01)
    animator = Animator(xlabel='epoch', ylabel='loss', yscale='log',
                        xlim=[1, num_epochs], ylim=[1e-3, 1e2],
                        legend=['train', 'test'], pic_name=f'model_select_{state}')
    for epoch in range(num_epochs):
        train_epoch_ch3(net, train_iter, loss, trainer)
        if epoch == 0 or (epoch + 1) % 20 == 0:
            animator.add(epoch + 1, (evaluate_loss(net, train_iter, loss),
                                     evaluate_loss(net, test_iter, loss)))
    print('weight:', net[0].weight.data.numpy())


# 三阶多项式函数拟合(正常)
# 从多项式特征中选择前4个维度，即1,x,x^2/2!,x^3/3!
train(poly_features[:n_train, :4], poly_features[n_train:, :4],
      labels[:n_train], labels[n_train:], state='正常拟合')

# 线性函数拟合(欠拟合)
# 从多项式特征中选择前2个维度，即1和x
train(poly_features[:n_train, :2], poly_features[n_train:, :2],
      labels[:n_train], labels[n_train:], state='欠拟合')

# 高阶多项式函数拟合(过拟合)
# 从多项式特征中选取所有维度
train(poly_features[:n_train, :], poly_features[n_train:, :],
      labels[:n_train], labels[n_train:], num_epochs=1500, state='过拟合')