线性回归模型从零开始的实现
# import packages and modules
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random
print(torch.__version__)
import packages and modules
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random
print(torch.version)
生成数据集
使用线性模型来生成数据集,生成一个1000个样本的数据集,下面是用来生成数据的线性关系:
# set input feature number
num_inputs = 2
# set example number
num_examples = 1000
# set true weight and bias in order to generate corresponded label
true_w = [2, -3.4]
true_b = 4.2
features = torch.randn(num_examples, num_inputs,
dtype=torch.float32)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()),
dtype=torch.float32)
使用图像来展示生成的数据
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);
读取数据集
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
random.shuffle(indices) # random read 10 samples
for i in range(0, num_examples, batch_size):
j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # the last time may be not enough for a whole batch
yield features.index_select(0, j), labels.index_select(0, j)
batch_size = 10
for X, y in data_iter(batch_size, features, labels):
print(X, '\n', y)
break
初始化模型参数
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float32)
b = torch.zeros(1, dtype=torch.float32)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
定义模型
def linreg(X, w, b):
return torch.mm(X, w) + b
定义损失函数
我们使用的是均方误差损失函数
def squared_loss(y_hat, y):
return (y_hat - y.view(y_hat.size())) ** 2 / 2
定义优化函数
在这里优化函数使用的是小批量随机梯度下降
def sgd(params, lr, batch_size):
for param in params:
param.data -= lr * param.grad / batch_size # ues .data to operate param without gradient track
训练
当数据集、模型、损失函数和优化函数定义完了之后就可来准备进行模型的训练了。
# super parameters init
lr = 0.03
num_epochs = 5
net = linreg
loss = squared_loss
# training
for epoch in range(num_epochs): # training repeats num_epochs times
# in each epoch, all the samples in dataset will be used once
# X is the feature and y is the label of a batch sample
for X, y in data_iter(batch_size, features, labels):
l = loss(net(X, w, b), y).sum()
# calculate the gradient of batch sample loss
l.backward()
# using small batch random gradient descent to iter model parameters
sgd([w, b], lr, batch_size)
# reset parameter gradient
w.grad.data.zero_()
b.grad.data.zero_()
train_l = loss(net(features, w, b), labels)
print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))