Potential Bug in 1dConv layer#250
Open
throwaway556 wants to merge 1 commit into
Open
Conversation
Contributor
|
@throwaway556 I am a bit busy these days. I will review this PR as soon as I get time. I appreciate your efforts to find the potential bug in the codes. Thanks |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I have installed keras-rl from pip today and encountered a bug in the process.
When trying to do 1D convolution keras doesn't accept an input layer with input_shape=(1,X), it must be input_shape=(X,1). I believe this is due to the 1d conv layer needing the data shaped a certain way in order to perform convolution. The size can't be greater than the input value, so when your shape is (1,X) but you have a size of 5 it doesn't translate the convolution to the X but rather the one.
I believe I have solved this specific issue but unfortunately it breaks the ability to accept(1,X). I am posting this to bring to the developers' attention for a better solution.
I have attached my openai gym file(block world) and two files for 1dconv and non-1dconv as well as a source file of what should be changed.
Thank you for creating this package and I hope you are able to resolve the issue.