版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
tf.less返回了两个张量各元素比较(x<y)得到的真假值组成的张量
import tensorflow as tf
A=[[1,2,3],
[4,5,6]]
i=[[1,2,3],
[1,2,3]]
r = tf.less(i, A)
with tf.Session() as sess:
print(sess.run(r))#[[False False False]
# [ True True True]]再来看损失函数的构造:
其中,e为误差,,代码实现为
regression_diff = regression - regression_target
regression_diff = keras.backend.abs(regression_diff)
regression_loss = backend.where(
keras.backend.less(regression_diff, 1.0 / sigma_squared),
0.5 * sigma_squared * keras.backend.pow(regression_diff, 2),
regression_diff - 0.5 / sigma_squared
)