深度学习梯度法实现与原理

import sys,os
sys.path.append(r"D:\源码\dataset")

import numpy as np
from mnist import load_mnist

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) ##复制一个x形状的数组，然后元素都为空

    for idx, x in enumerate(X): #enumerate用来返回迭代对象，
        grad[idx] = _numerical_gradient_no_batch(f, x)
    return grad

def softmax(arr):
max_num=np.max(arr)
return np.exp(arr-max_num)/np.sum(np.exp(arr-max