我想这已经解释得很清楚了 Github issue softmax() 仍在操作 0.0 值并返回 non-zero link ).

只有这样才能从 softmax() 就是通过考试 . 如果将屏蔽值设置为 float64 , Softmax()

要获得float64上的机器限制,您需要 tf.float64.min -1.7976931348623157e+308 post .

下面是一个实现,供您参考 tf.boolean_mask tf.where 用于创建遮罩并将其传递给 softmax()

import tensorflow as tf

inputs = np.zeros([1,5])
inputs[0,1] = 0.5
inputs[0,2] = 0.1
inputs = tf.Variable(inputs)

#Returns only the elements that are not masked (2,)
with_boolmask = tf.boolean_mask(inputs, inputs!=0)
with_boolmask = tf.keras.layers.Softmax()(with_boolmask)

#Correct way to do it!
masked_inp = tf.where(inputs!=0, inputs, tf.float64.min) #<----
with_where = tf.keras.layers.Softmax()(masked_inp)

print('BOOLEAN MASK (NOT EXPECTED)')
print(with_boolmask)

print('')
print('MASKED INPUT - ')
print(masked_inp)
print('')
print('SOFTMAX OUTPUT')
print(with_where)

BOOLEAN MASK (NOT EXPECTED)
tf.Tensor([0.59868765 0.40131232], shape=(2,), dtype=float32)

MASKED INPUT - 
tf.Tensor(
[[-1.79769313e+308  5.00000000e-001  1.00000000e-001 -1.79769313e+308
  -1.79769313e+308]], shape=(1, 5), dtype=float64)

SOFTMAX OUTPUT
tf.Tensor([[0.         0.59868765 0.40131232 0.         0.        ]], shape=(1, 5), dtype=float32)