Tensorflow: how could tf.nn.max_pool work with dynamic kernel size?
ahmed-touati
All 3 comments
Not with the current op interface. You would have to write a new op that takes the kernel size as an input tensor. The kernel implementation can be refactored to use most of the current max_pool implementation.
zheng-xq
on 18 Apr 2016
Closing. Feel free to reopen if this is a feature request worth tracking.
vincentvanhoucke
on 9 Jun 2016
+1
I would like to request that feature.
apple2373
on 18 Jun 2016
👍13
Was this page helpful?
0 / 5 - 0 ratings
Related issues
indiejoseph
·
3Comments
jricheimer
·
3Comments
kepricon
·
3Comments
nicholaslocascio
·
3Comments
NHDaly
·
3Comments
Most helpful comment
+1
I would like to request that feature.