教程Python代碼如下：

# 1) Design model(input, output size, forward pass)

# 2) Construct loss and optimizer

# 3) Training loop 訓練循環(huán)

# - forward pass: compute prediction

# - backward pass: gradients

# - update weights

import torch

import torch.nn as nn #導入神經(jīng)網(wǎng)絡模塊

# f = w * x 此處不加偏置

# f = 2 * x

X = torch.tensor([[1],[2],[3],[4]],dtype=torch.float32)

Y = torch.tensor([[2],[4],[6],[8]],dtype=torch.float32)

X_test = torch.tensor([5],dtype=torch.float32)

n_samples, n_features = X.shape

print(n_samples, n_features)

input_size = n_features

output_size = n_features

#model = nn.Linear(input_size, output_size)

class LinearRegression(nn.Module):

def __init__(self, input_dim, output_dim):

super(LinearRegression, self).__init__()

# define layers

self.lin = nn.Linear(input_dim, output_dim)

def forward(self, x):

return self.lin(x)

model = LinearRegression(input_size, output_size)

print(f'Prediction befor training: f(5) = {model(X_test).item():.3f}')

# Training

# 學習率

learning_rate = 0.01

# 多次迭代

n_iters = 100

# loss = 均方誤差

loss = nn.MSELoss()

# 優(yōu)化器

optimizer = torch.optim.SGD(model.parameters(),lr=learning_rate) #SGD代表隨機梯度下降，參數(shù)列表是它將優(yōu)化的參數(shù)

for epoch in range(n_iters):

# prediction = forward pass

y_pred = model(X)

# loss

l = loss(Y,y_pred)

# gradients = backward pass

l.backward() # dl/dw

# update weights 更新公式：權重 = 權重 - (步長或學習速率 * dw)

optimizer.step()

# zero gradients

optimizer.zero_grad()

#打印每一步

if epoch % 10 == 0:

[w, b] = model.parameters()

print(f'epoch {epoch+1}: w = {w[0][0].item():.3f}, loss = {l:.8f}')

print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')