下面是使用numpy的广义解，以及与tensorflow和scipy的正确性比较:

数据准备:

import numpy as np

np.random.seed(2019)

batch_size = 1
n_items = 3
n_classes = 2
logits_np = np.random.rand(batch_size,n_items,n_classes).astype(np.float32)
print('logits_np.shape', logits_np.shape)
print('logits_np:')
print(logits_np)

输出:

logits_np.shape (1, 3, 2)
logits_np:
[[[0.9034822  0.3930805 ]
  [0.62397    0.6378774 ]
  [0.88049906 0.299172  ]]]

使用tensorflow的Softmax:

import tensorflow as tf

logits_tf = tf.convert_to_tensor(logits_np, np.float32)
scores_tf = tf.nn.softmax(logits_np, axis=-1)

print('logits_tf.shape', logits_tf.shape)
print('scores_tf.shape', scores_tf.shape)

with tf.Session() as sess:
    scores_np = sess.run(scores_tf)

print('scores_np.shape', scores_np.shape)
print('scores_np:')
print(scores_np)

print('np.sum(scores_np, axis=-1).shape', np.sum(scores_np,axis=-1).shape)
print('np.sum(scores_np, axis=-1):')
print(np.sum(scores_np, axis=-1))

输出:

logits_tf.shape (1, 3, 2)
scores_tf.shape (1, 3, 2)
scores_np.shape (1, 3, 2)
scores_np:
[[[0.62490064 0.37509936]
  [0.4965232  0.5034768 ]
  [0.64137274 0.3586273 ]]]
np.sum(scores_np, axis=-1).shape (1, 3)
np.sum(scores_np, axis=-1):
[[1. 1. 1.]]

使用scipy的Softmax:

from scipy.special import softmax

scores_np = softmax(logits_np, axis=-1)

print('scores_np.shape', scores_np.shape)
print('scores_np:')
print(scores_np)

print('np.sum(scores_np, axis=-1).shape', np.sum(scores_np, axis=-1).shape)
print('np.sum(scores_np, axis=-1):')
print(np.sum(scores_np, axis=-1))

输出:

scores_np.shape (1, 3, 2)
scores_np:
[[[0.62490064 0.37509936]
  [0.4965232  0.5034768 ]
  [0.6413727  0.35862732]]]
np.sum(scores_np, axis=-1).shape (1, 3)
np.sum(scores_np, axis=-1):
[[1. 1. 1.]]

Softmax使用numpy (https://nolanbconaway.github.io/blog/2017/softmax-numpy):

def softmax(X, theta = 1.0, axis = None):
    """
    Compute the softmax of each element along an axis of X.

    Parameters
    ----------
    X: ND-Array. Probably should be floats.
    theta (optional): float parameter, used as a multiplier
        prior to exponentiation. Default = 1.0
    axis (optional): axis to compute values along. Default is the
        first non-singleton axis.

    Returns an array the same size as X. The result will sum to 1
    along the specified axis.
    """

    # make X at least 2d
    y = np.atleast_2d(X)

    # find axis
    if axis is None:
        axis = next(j[0] for j in enumerate(y.shape) if j[1] > 1)

    # multiply y against the theta parameter,
    y = y * float(theta)

    # subtract the max for numerical stability
    y = y - np.expand_dims(np.max(y, axis = axis), axis)

    # exponentiate y
    y = np.exp(y)

    # take the sum along the specified axis
    ax_sum = np.expand_dims(np.sum(y, axis = axis), axis)

    # finally: divide elementwise
    p = y / ax_sum

    # flatten if X was 1D
    if len(X.shape) == 1: p = p.flatten()

    return p


scores_np = softmax(logits_np, axis=-1)

print('scores_np.shape', scores_np.shape)
print('scores_np:')
print(scores_np)

print('np.sum(scores_np, axis=-1).shape', np.sum(scores_np, axis=-1).shape)
print('np.sum(scores_np, axis=-1):')
print(np.sum(scores_np, axis=-1))

输出:

scores_np.shape (1, 3, 2)
scores_np:
[[[0.62490064 0.37509936]
  [0.49652317 0.5034768 ]
  [0.64137274 0.3586273 ]]]
np.sum(scores_np, axis=-1).shape (1, 3)
np.sum(scores_np, axis=-1):
[[1. 1. 1.]]

所以，这实际上是对desertnaut的回答的一个评论，但由于我的声誉，我还不能评论它。正如他所指出的，只有当输入包含单个样本时，你的版本才是正确的。如果您的输入包含多个样本，则是错误的。然而，沙漠探险者的解决方案也是错误的。问题是一旦他得到一个一维的输入然后他又得到一个二维的输入。让我给你们看看这个。

import numpy as np

# your solution:
def your_softmax(x):
    """Compute softmax values for each sets of scores in x."""
    e_x = np.exp(x - np.max(x))
    return e_x / e_x.sum()

# desertnaut solution (copied from his answer): 
def desertnaut_softmax(x):
    """Compute softmax values for each sets of scores in x."""
    e_x = np.exp(x - np.max(x))
    return e_x / e_x.sum(axis=0) # only difference

# my (correct) solution:
def softmax(z):
    assert len(z.shape) == 2
    s = np.max(z, axis=1)
    s = s[:, np.newaxis] # necessary step to do broadcasting
    e_x = np.exp(z - s)
    div = np.sum(e_x, axis=1)
    div = div[:, np.newaxis] # dito
    return e_x / div

让我们以沙漠探险者为例:

x1 = np.array([[1, 2, 3, 6]]) # notice that we put the data into 2 dimensions(!)

输出如下:

your_softmax(x1)
array([[ 0.00626879,  0.01704033,  0.04632042,  0.93037047]])

desertnaut_softmax(x1)
array([[ 1.,  1.,  1.,  1.]])

softmax(x1)
array([[ 0.00626879,  0.01704033,  0.04632042,  0.93037047]])

你可以看到沙漠版本在这种情况下会失败。(如果输入是一维的，就不会像np那样。数组([1,2,3,6])。

现在让我们使用3个样本，因为这就是为什么我们使用二维输入的原因。下面的x2和沙漠例子中的x2不一样。

x2 = np.array([[1, 2, 3, 6],  # sample 1
               [2, 4, 5, 6],  # sample 2
               [1, 2, 3, 6]]) # sample 1 again(!)

该输入由一个有3个样本的批次组成。但样本一和样本三本质上是一样的。我们现在期望3行softmax激活，其中第一行应该与第三行相同，也与x1的激活相同!

your_softmax(x2)
array([[ 0.00183535,  0.00498899,  0.01356148,  0.27238963],
       [ 0.00498899,  0.03686393,  0.10020655,  0.27238963],
       [ 0.00183535,  0.00498899,  0.01356148,  0.27238963]])


desertnaut_softmax(x2)
array([[ 0.21194156,  0.10650698,  0.10650698,  0.33333333],
       [ 0.57611688,  0.78698604,  0.78698604,  0.33333333],
       [ 0.21194156,  0.10650698,  0.10650698,  0.33333333]])

softmax(x2)
array([[ 0.00626879,  0.01704033,  0.04632042,  0.93037047],
       [ 0.01203764,  0.08894682,  0.24178252,  0.65723302],
       [ 0.00626879,  0.01704033,  0.04632042,  0.93037047]])

我希望你能明白，这只是我的解的情况。

softmax(x1) == softmax(x2)[0]
array([[ True,  True,  True,  True]], dtype=bool)

softmax(x1) == softmax(x2)[2]
array([[ True,  True,  True,  True]], dtype=bool)

另外，下面是TensorFlows softmax实现的结果:

import tensorflow as tf
import numpy as np
batch = np.asarray([[1,2,3,6],[2,4,5,6],[1,2,3,6]])
x = tf.placeholder(tf.float32, shape=[None, 4])
y = tf.nn.softmax(x)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(y, feed_dict={x: batch})

结果是:

array([[ 0.00626879,  0.01704033,  0.04632042,  0.93037045],
       [ 0.01203764,  0.08894681,  0.24178252,  0.657233  ],
       [ 0.00626879,  0.01704033,  0.04632042,  0.93037045]], dtype=float32)

为了提供另一种解决方案，请考虑这样的情况:参数的值非常大，以至于exp(x)会溢出(在负的情况下)或溢出(在正的情况下)。这里你希望尽可能长时间地保持在对数空间中，只在你可以相信结果是良好的地方取幂。

import scipy.special as sc
import numpy as np

def softmax(x: np.ndarray) -> np.ndarray:
    return np.exp(x - sc.logsumexp(x))

我想说，虽然从数学上讲，这两种方法都是正确的，但就实现而言，第一个方法更好。在计算softmax时，中间值可能会变得很大。两个大数的除法在数值上是不稳定的。这些笔记(来自斯坦福大学)提到了一个归一化技巧，这基本上就是你正在做的事情。

import tensorflow as tf
import numpy as np

def softmax(x):
    return (np.exp(x).T / np.exp(x).sum(axis=-1)).T

logits = np.array([[1, 2, 3], [3, 10, 1], [1, 2, 5], [4, 6.5, 1.2], [3, 6, 1]])

sess = tf.Session()
print(softmax(logits))
print(sess.run(tf.nn.softmax(logits)))
sess.close()

从数学的角度看，两边是相等的。

这很容易证明。m = max (x)。现在你的函数softmax返回一个向量，它的第i个坐标等于

注意，这适用于任何m，因为对于所有(甚至是复数)数e^m != 0

from computational complexity point of view they are also equivalent and both run in O(n) time, where n is the size of a vector. from numerical stability point of view, the first solution is preferred, because e^x grows very fast and even for pretty small values of x it will overflow. Subtracting the maximum value allows to get rid of this overflow. To practically experience the stuff I was talking about try to feed x = np.array([1000, 5]) into both of your functions. One will return correct probability, the second will overflow with nan your solution works only for vectors (Udacity quiz wants you to calculate it for matrices as well). In order to fix it you need to use sum(axis=0)