PyTorch 深度学习实践（梯度下降算法）

梯度下降上课代码

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)    #计算MSE

def gradient(xs,ys):
    grad = 0
    for x,y in zip(xs,ys):
        grad += 2 * x * (x * w - y)     #相应的梯度落差式（即导数式）
    return grad / len(xs)

mse_list = []
print('Predict (befortraining)',4,forward(4))
for epoch in range(100):
    cost_val = cost(x_data,y_data)    #便于画图
    grad_val = gradient(x_data,y_data)
    w -= 0.01 * grad_val
    mse_list.append(cost_val)
    print('Epoch:',epoch,'w=',w,'loss=',cost_val)
print('Predict(after training)',4,forward(4))

w_list=np.arange(0,100,1)
plt.plot(w_list,mse_list)
plt.ylabel('cost')
plt.xlabel('times')
plt.show()

随机梯度下降

只需要求出一个样本的均值

相应代码修改如下

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

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

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