Softmax 实现源代码

import numpy as np
from numpy.core._rational_tests import denominator

def softmax(x):
    
    #implementation one
    """ Compute the softmax in a numerically stable way."""
    x = x- np.max(x)
    exp_x = np.exp(x)
    softmax_x = exp_x / np.sum(exp_x)
    
    return softmax_x


def softmax_2(x):
    
    #implementation 2
    """
    Compute the softmax function for each row in matrix or vectors
    
    Arguemnts:
     
    """
    
    orig_shape = x.shape
    
    if len(x.shape) >1:
        # Matrix
        exp_minmax = lambda x: np.exp(x-np.max)
        demon  = lambda x: 1.0 / np.sum(x)
        x = np.apply_along_axis(exp_minmax, 1, x)
        denominator = np.apply_along_axis(demon,1, x)
        
        if len( denominator.shape) == 1:
            denominator = denominator.reshape((denominator.shape[0], 1) )
            
        x = x*denominator
    
    else:
        #Vector
        x_max = np.max(x)
        x = x - x_max
        numerator = np.exp(x)
        denominator = 1.0 / np.sum(numerator)
        x= numerator.dot(denominator)
    
    assert x.shape == orig_shape
    return x