在没有足够多数据时使用
如下图所示,3-折交叉验证,分别选取第1、2、3块数据作为验证集,其余作为训练集。
2维输入的感知机,VC维=3;它能够分类任何三个点,但不是4个(XOR)
导包
import math
import numpy as np
import torch
from torch import nn
from d2l import torch as d2l
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]
def evaluate_loss(net, data_iter, loss): #@save
"""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]
函数的逻辑如下:
def train(train_features, test_features, train_labels, test_labels,
num_epochs=400):
#损失函数为均方误差损失函数
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)) #线性模型
batch_size = min(10, train_labels.shape[0]) #小批量数据的大小
#加载训练集和测试集的数据
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)
#优化函数
trainer = torch.optim.SGD(net.parameters(), lr=0.01)
#可视化的动画
animator = d2l.Animator(xlabel='epoch', ylabel='loss', yscale='log',
xlim=[1, num_epochs], ylim=[1e-3, 1e2],
legend=['train', 'test'])
#开始每轮训练
for epoch in range(num_epochs):
d2l.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())
loss = nn.MSELoss(reduction='none')
PyTorch中的均方误差(Mean Squared Error,MSE)损失函数的定义。其中,reduction参数设置为’none’表示不进行降维操作。
reduction参数控制损失函数的降维方式,有以下选项:
# 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:])
# 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:])
# 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)