参考资料:沐神——动手学深度学习
import random
import matplotlib
import math
import time
import numpy as np
import torch
from d2l import torch as d2l
#-------------------- 生成输入数据 --------------------------#
def synthetic_data(w,b,num_examples):
x = torch.normal(0,1,(num_examples,len(w)))
y = torch.matmul(x,w) + b
y += torch.normal(0,0.01,y.shape)
return x,y.reshape((-1,1))
true_w = torch.tensor([2,-3.4])
true_b = 4.2
features, labels = synthetic_data(true_w,true_b,1000)
# print('features:', features[0], '\nlabel:', lables[0])
# d2l.set_figsize()
# d2l.plt.scatter(features[:,1].detach().numpy(), labels.detach().numpy(),1)
# d2l.plt.show()
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
# print("indices:",indices)
random.shuffle(indices)
for i in range(0,num_examples,batch_size):
batch_indices = torch.tensor(indices[i:min(i+batch_size,num_examples)])
yield features[batch_indices], labels[batch_indices] # 返回迭代器,每调用一次函数返回一组features 和 labels,直到超出range范围
batch_size = 10
for x,y in data_iter(batch_size,features,labels):
print(x,'\n',y)
break
# ----------------------- 构建模型 ----------------------- #
w = torch.normal(0,0.01,size = (2,1),requires_grad = True)
b = torch.zeros(1,requires_grad = True)
def linreg(x,w,b):
return torch.matmul(x,w) + b
# 损失函数
def squared_loss(y_hat,y):
return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2
# 定义优化算法(随机梯度)
def SGD(params,learning_rate,batch_size):
with torch.no_grad():
for param in params:
param -= learning_rate * param.grad / batch_size
param.grad.zero_() # 手动把梯度设置为0,因为torch计算梯度会累积上次的计算结果
# ----------- 训练过程 ------------------- #
learning_rate = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
for epoch in range(num_epochs):
for x,y in data_iter(batch_size,features,labels):
y_hat = net(x,w,b)
l = loss(y_hat,y)
l.sum().backward()
SGD([w,b],learning_rate,batch_size)
with torch.no_grad():
train_l = loss(net(features,w,b),labels)
print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')
# ----- 比较真实参数和训练得到的参数来评估模型训练的成功程度 ------ #
print(f'w的估计误差: {true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差: {true_b - b}')