Move samples to Matrix #34
Merged
Conversation
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
The current implementation does not work with CUDA because it returns views, which will perform scalar indexing when passing a batch to a NN. Moving a sampled batch to a Matrix not only avoids that but also speeds up the matrix multiplications during NN forward and backward passes.
|
I will make a release to include this change. This should make CUDA usable again in RL.jl. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The current implementation does not work with CUDA because it returns views, which will perform scalar indexing when passing a batch to a NN. Moving a sampled batch to a Matrix not only avoids that but also speeds up the matrix multiplications during NN forward and backward passes.