pytorch入门——线性回归
程序员文章站
2022-06-11 22:42:27
...
单纯的数据分析找工作可以,但是想要进阶一定要找一个方向,在之前的时候选择了推荐系统,但是在新公司对NLP更侧重,所以决定先学深度学习,这就面临选择框架,之前了解到Tensorflow,但是构建复杂,所以选择了Pytorch,先简单的做出这样的例子,有好多细节,需要慢慢理解。
构造一组输入数据X和其对应的标签y
import numpy as np
x_values = [i for i in range(11)]
x_train = np.array(x_values, dtype=np.float32)
x_train = x_train.reshape(-1, 1)
x_train.shape
(11, 1)
y_values = [2*i + 1 for i in x_values]
y_train = np.array(y_values, dtype=np.float32)
y_train = y_train.reshape(-1, 1)
y_train.shape
(11, 1)
import torch
import torch.nn as nn
线性回归模型
- 其实线性回归就是一个不加**函数的全连接层
class LinearRegressionModel(nn.Module):
def __init__(self, input_dim, output_dim):
super(LinearRegressionModel, self).__init__()
self.linear = nn.Linear(input_dim, output_dim)
def forward(self, x):#前向传播
out = self.linear(x)
return out
input_dim = 1
output_dim = 1
model = LinearRegressionModel(input_dim, output_dim)
指定好参数和损失函数
epochs = 3000
learning_rate = 0.01
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
criterion = nn.MSELoss()
for epoch in range(epochs):
epoch += 1
# 注意转行成tensor
inputs = torch.from_numpy(x_train)
labels = torch.from_numpy(y_train)
# 梯度要清零每一次迭代
optimizer.zero_grad()
# 前向传播
outputs = model(inputs)
# 计算损失
loss = criterion(outputs, labels)
# 返向传播
loss.backward()
# 更新权重参数
optimizer.step()
if epoch % 500 == 0:
print('epoch {}, loss {}'.format(epoch, loss.item()))
epoch 500, loss 0.0010986549314111471
epoch 1000, loss 4.001932211394887e-06
epoch 1500, loss 1.4628509070746532e-08
epoch 2000, loss 5.929317453690075e-11
epoch 2500, loss 1.5593505653388462e-11
epoch 3000, loss 1.5593505653388462e-11
测试模型预测结果
predicted = model(torch.from_numpy(x_train).requires_grad_()).data.numpy()
predicted
array([[ 0.99999267],
[ 2.9999938 ],
[ 4.999995 ],
[ 6.9999967 ],
[ 8.999997 ],
[10.999998 ],
[13. ],
[15.000001 ],
[17.000002 ],
[19.000004 ],
[21.000004 ]], dtype=float32)
模型的保存与读取
torch.save(model.state_dict(), 'model.pkl')
model.load_state_dict(torch.load('model.pkl'))
<All keys matched successfully>