基于python的梯度下降法的实现代码

基于python的梯度下降法的实现

代码：

def _numerical_gradient_no_batch(f, x):
    h = 1e-4  # 0.0001
    grad = np.zeros_like(x)

    for idx in range(x.size):
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x)  # f(x+h)

        x[idx] = tmp_val - h
        fxh2 = f(x)  # f(x-h)
        grad[idx] = (fxh1 - fxh2) / (2 * h)

        x[idx] = tmp_val  # 还原值

    return grad
def numerical_gradient(f, X):
    if X.ndim == 1:
        return _numerical_gradient_no_batch(f, X)
    else:
        grad = np.zeros_like(X)

        for idx, x in enumerate(X):
            grad[idx] = _numerical_gradient_no_batch(f, x)

        return grad

def gradient_descent(f,init_x,lr=0.01,step_num=100):
    ## 梯度下降法求函数的最小值
    # f:要优化的函数
    # init_x：自变量的初始位置
    # lr:学习率
    # step_num:重复的次数
    x = init_x
    a = []
    b = []
    for i in range(step_num):
        grad = numerical_gradient(f,x)
        x = x - lr *grad
        a.append(x[0])
        b.append(x[1])
    plt.scatter(a,b,color='black')
    plt.show()
    return x

def function_2(x):
    return np.sum(x**2)

if __name__ == '__main__':
    gradient_descent(f=function_2, init_x=np.array([-3.0, 4.0]), lr=0.3, step_num=100)

运行结果：