代码如下
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
#给多项式分配参数
true_w = np.zeros(max_degree)
true_w[0:4] = np.array([5, 1.2, -3.4, 5.6])
#选取200行1列的x值并打乱
features = np.random.normal(size=(n_train + n_test, 1))
np.random.shuffle(features)
#对x取次方操作
poly_features = np.power(features, np.arange(max_degree).reshape(1, -1))
#形成一个多项式函数
for i in range(max_degree):
poly_features[:, i] /= math.gamma(i + 1) # gamma(n)=(n-1)!
labels = np.dot(poly_features, true_w)
#多项式函数加上噪音, 最终得到的y的值
labels += np.random.normal(scale=0.1, size=labels.shape)
# NumPy ndarray转换为tensor, feature代表随机x的值, labels代表根据多项式得到的y的值, poly_feature代表取次方后x的值
true_w, features, poly_features, labels = [torch.tensor(x, dtype=
torch.float32) for x in [true_w, features, poly_features, labels]]
#定义损失函数
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]
def train(train_features, test_features, train_labels, test_labels,
num_epochs=200):
loss = nn.MSELoss(reduction='none')#定义损失函数
input_shape = train_features.shape[-1]
#选取4行1列的网络模型
net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))
batch_size = min(10, train_labels.shape[0])
#选取数据集
train_iter = d2l.load_array((train_features, train_labels.reshape(-1,1)),
batch_size)
#选取测试集
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)#反向传播
#画图
animator = d2l.Animator(xlabel='epoch', ylabel='loss', yscale='log',
xlim=[1, num_epochs], ylim=[1e-3, 1e2],
legend=['train', 'test'])
for epoch in range(num_epochs):
d2l.train_epoch_ch3(net, train_iter, loss, trainer)
#画图
if epoch == 0 or (epoch + 1) % 20 == 0:
animator.add(epoch + 1, (evaluate_loss(net, train_iter, loss),
evaluate_loss(net, test_iter, loss)))
d2l.plt.show()
# 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:])
运行结果如下