当前位置：网站首页>Pytorch deep learning practice (3)

Pytorch deep learning practice (3)

2022-04-23 22:02:00 【Know what you know and slowly understand what you don't know】

Random gradient descent method 

import numpy as np
import matplotlib.pyplot as plt
x_data=[1.0,2.0,3.0]
y_data=[2.0,4.0,6.0]

w=1.0
def forward(x):
    return x*w
def cost(xs,ys):
    cost=0
    for x,y in zip(xs,ys):
        y_pred=forward(x)
        cost+=(y_pred-y)**2
    return cost/len(xs)
def gradient(xs,ys):
    grad=0
    for x,y in zip(xs,ys):
        grad+=2*x*(x*w-y)
    return grad/len(xs)
print('prdeict (before training)',4,forward(4))
for epoch in range(100):
    cost_val=cost(x_data,y_data)
    grad_val=gradient(x_data,y_data)
    w-=0.01*grad_val
    print('epoch:',epoch,'w=',w,'loss=',cost_val)
print('predict (after training',4,forward(4))

#plt.plot(cost)
plt.plot(x_data,y_data)
#epoch.append(epoch)
#cost.append(cost(x_data,y_data))


#plt.plot(epoch_list,cost_list)
plt.ylabel('cost')
plt.xlabel('epoch')
plt.show()

There is a problem with the last diagram

版权声明
本文为[Know what you know and slowly understand what you don't know]所创，转载请带上原文链接，感谢
https://yzsam.com/2022/04/202204200609332775.html

边栏推荐

猜你喜欢

随机推荐