使用梯度下降求函数的极小值

	import numpy as np
        from mpl_toolkits.mplot3d import     Axes3D
        from matplotlib import pyplot as plt
	import torch
	
	# 目标函数
	def fun(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)
	# print(type(x))
	print('x,y range:', x.shape, y.shape)
	X, Y = np.meshgrid(x, y)
	# print(X)
	print('X,Y maps:', X.shape, Y.shape)
	Z = fun([X, Y])
	
	# 对函数进行可视化
	fig = plt.figure('fun')
	ax = fig.gca(projection='3d')
	ax.plot_surface(X, Y, Z)
	ax.view_init(60, 30)
	ax.set_xlabel('x')
	ax.set_ylabel('y')
	
	# 对x赋初值，不同的初始值可能得到的极小值不一样
	x = torch.tensor([4., 0.], requires_grad=True)
	optimizer = torch.optim.Adam([x], lr=1e-3)
	for step in range(20000):
	    pred = fun(x)
	    optimizer.zero_grad()
	    pred.backward()
	    optimizer.step()
	
	    if step % 2000 == 0:
	        print('step{} : x = {}, f(x) = {}'.format(step, x.tolist(), pred.item()))
	
	plt.show()