(25)梯度下降法求解曲面极小值

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

def himmelblau(x):
    return (x[0]**2 + x[1]-11)**2 + (x[0]+x[1]**2-7)**2
    
x = np.arange(-6,6,0.1)
y= np.arange(-6,6,0.1)
print(x.shape,y.shape)
X,Y = tf.meshgrid(x,y)#组合
Z = himmelblau([X,Y])

fig = plt.figure('himmelblau')
ax = fig.gca(projection='3d') # 设置 3D 坐标轴
ax.plot_surface(X, Y, Z) # 3D 曲面图
ax.view_init(15, -30)#显示视角角度
ax.set_xlabel('x')
ax.set_ylabel('y')
plt.show()

#梯度下降法求解
x=tf.constant([7.0,6.0])
for step in range(500):
    with tf.GradientTape() as tape:#自动求导监控
        tape.watch([x])#加入监控名单
        y = himmelblau(x)
    grad = tape.gradient(y,[x])[0]#求导
    x -= 0.001*grad # 更新
    if step % 20 == 19:
        print(x,y)