在TensorFlow中，不能直接使用if语句或==运算符进行条件判断，因为它们在图构建时即被评估。要实现运行时的条件控制流，应该使用tf.cond操作。该操作根据一个布尔条件 tensor 选择执行两个分支之一。若希望在条件判断后执行特定函数，一种方法是先计算函数返回值，然后通过if判断来决定是否使用。
tf中用if是不行的，用==也是不行的
因为是先建图，建图的时候也只是用tensor来进行判断
You're correct that the if statement doesn't work here, because the condition is evaluated at graph construction time, whereas presumably you want the condition to depend on the value fed to the placeholder at runtime. (In fact, it will always take the first branch, because condition > 0evaluates to a Tensor, which is "truthy" in Python.)
To support conditional control flow, TensorFlow provides the tf.cond() operator, which evaluates one of two branches, depending on a boolean condition. To show you how to use it, I'll rewrite your program so that condition is a scalar tf.int32 value for simplicity:
x = tf.
最低0.47元/天 解锁文章
扫一扫
1622
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
