刘老师的《Pytorch深度学习实践》第三讲：梯度下降算法代码

我的宠物不是小马

已于 2022-09-16 18:51:02 修改

阅读量354

点赞数 1

文章标签： python 深度学习机器学习 pytorch

于 2022-09-16 17:29:03 首次发布

本文链接：https://blog.csdn.net/weixin_52539595/article/details/126894674

版权

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('Predict (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#更新
    print('Epoch:',epoch,'W=',w,'loss=',cost_val)
print('Predict(after training)',4,forward(4))

随机梯度下降

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 loss(x,y):
    y_pred=forward(x)
    return(y_pred-y)**2

def gradient(x,y):
    return 2*x*(x*w-y)

print('Predict (before training',4,forward(4))

for epoch in range(100):
    for x,y in zip(x_data,y_data):
        grad=gradient(x,y)
        w=w-0.01*grad
        print("\tgrad:",x,y,grad)
        l=loss(x,y)
    print("progress:",epoch,'w=',w,'loss=',1)
print('Predict(after training)',4,forward(4))