我可以将 tf.map_fn(...) 应用于多个输入/输出吗? [英] Can I apply tf.map_fn(...) to multiple inputs/outputs?
问题描述
a = tf.constant([[1,2,3],[4,5,6]])
b = tf.constant([True, False], dtype=tf.bool)
a.eval()
array([[1, 2, 3],
[4, 5, 6]], dtype=int32)
b.eval()
array([ True, False], dtype=bool)
我想使用 tf.map_fn
将函数应用于上述输入、a
和 b
.它将同时输入 [1,2,3]
和 True
并输出相似的值.
I want to apply a functions to the inputs above, a
, and b
using tf.map_fn
. It will input both [1,2,3]
, and True
and output similar values.
假设 out 函数只是身份:lambda(x,y): x,y
所以,给定输入 [1,2,3], True
,它将输出那些相同的张量.
Let's say out function is simply the identity: lambda(x,y): x,y
so, given an input of [1,2,3], True
, it will output those identical tensors.
我知道如何将 tf.map_fn(...)
与一个变量一起使用,但不知道如何与两个变量一起使用.在这种情况下,我有混合数据类型(int32 和 bool),所以我不能简单地连接张量并在调用后拆分它们.
I know how to use tf.map_fn(...)
with one variable, but not with two. And in this case I have mixed data types (int32 and bool) so I can't simply concatenate the tensors and split them after the call.
我可以将 tf.map_fn(...)
用于不同数据类型的多个输入/输出吗?
Can I use tf.map_fn(...)
with multiple inputs/outputs of different data types?
推荐答案
想通了.您必须在 dtype
中为每个不同的张量定义每个张量的数据类型,然后您可以将张量作为元组传递,您的 map 函数接收一个输入元组,并且 map_fn
返回一个元组.
Figured it out. You have to define the data types for each tensor in dtype
for each of the different tensors, then you can pass the tensors as a tuple, your map function receives a tuple of inputs, and map_fn
returns back back a tuple.
有效示例:
a = tf.constant([[1,2,3],[4,5,6]])
b = tf.constant([True, False], dtype=tf.bool)
c = tf.map_fn(lambda x: (x[0], x[1]), (a,b), dtype=(tf.int32, tf.bool))
c[0].eval()
array([[1, 2, 3],
[4, 5, 6]], dtype=int32)
c[1].eval()
array([ True, False], dtype=bool)
这篇关于我可以将 tf.map_fn(...) 应用于多个输入/输出吗?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!