tf.cond()函数的用法

 

这个函数跟if...else...的功能很像，主要控制tensorflow中计算图的张量的流向。官网中有对函数参数的解释如下：

tf.cond(
    pred,
    true_fn=None,
    false_fn=None,
    strict=False,
    name=None,
    fn1=None,
    fn2=None
)

• pred: A scalar determining whether to return the result of true_fn or false_fn.
• true_fn: The callable to be performed if pred is true.
• false_fn: The callable to be performed if pred is false.
• strict: A boolean that enables/disables 'strict' mode; see above.
• name: Optional name prefix for the returned tensors.

看的有点糊涂，用一个例子来解释下吧 ！

import tensorflow as tf
x=tf.constant(2)
y=tf.constant(5)
flag=tf.constant(True)
op=tf.cond(flag,lambda :tf.add(x,y),lambda : tf.multiply(x,y))
with tf.Session() as sess:
    result=sess.run(op)
    print(result)

当flag为True时，执行‘加’操作，结果为7，当flag为Flase时，执行“乘”操作，结果为10