keras.backend.sum用法

#沿着指定轴计算张量之和
from keras import backend as K
import numpy as np
import tensorflow as tf

a = np.arange(0 , 6).reshape(2 , 3)
print(a)

[[0 1 2]
 [3 4 5]]

sum_a_keepdims = K.sum(a , axis=-1 , keepdims=True)
sum_a_nokeepdims = K.sum(a , axis=-1 , keepdims=False)

print(sum_a_keepdims.shape)
print(sum_a_nokeepdims.shape)   

(2, 1)
(2,)

init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(sum_a_keepdims))
    print(sess.run(sum_a_nokeepdims))

[[ 3]
 [12]]
[ 3 12]