PyTorch Tutorial 05 - Gradient Descen...

教程Python代码：numpy版

import numpy as np

# f = w * x 此处不加偏置

# f = 2 * x

X = np.array([1,2,3,4],dtype=np.float32)

Y = np.array([2,4,6,8],dtype=np.float32)

# 初始化权重

w = 0.0

# model prediction,计算模型

def forward(x):

return w * x

# loss = MSE(Mean Square Error),均方误差计算损失

def loss(y,y_predicted):

return ((y_predicted - y)**2).mean()

# gradient,手动计算损失的梯度

# MSE = 1/N * (w*x - y)**2

# dJ/dw = 1/N * 2x * (w*x - y) , 这是数值计算的计算导数

def gradient(x,y,y_predicted):

return np.dot(2*x, y_predicted-y).mean()

print(f'Prediction befor training: f(5) = {forward(5):.3f}')

# Training

learning_rate = 0.01 #学习率

n_iters = 20 #多次迭代

for epoch in range(n_iters):

# prediction = forward pass

y_pred = forward(X)

# loss

l = loss(Y,y_pred)

# gradients

dw = gradient(X, Y, y_pred)

# update weights 更新公式：权重 = 权重 - (步长或学习速率 * dw)

w -= learning_rate * dw

#打印每一步

if epoch % 1 == 0:

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

print(f'Prediction after training: f(5) = {forward(5):.3f}')