You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Ah, correct: tf.nn.max_pool does not support dynamic size. ksize is an attr, therefore must be a constant. This would be reasonable to fix, but would require a MaxPoolV2 op kernel similar to TopKV2. I'll leave it open as contributions welcome.
I have the following code for a convolutional layer. This layer is part a larger computational graph.
When trying to run, I get the error:
is tf.nn.max_pool unable to handle dynamic ksize?
The text was updated successfully, but these errors were encountered: