"""
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')
