adding F4 layer that runs many trees in parallel #1
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Outdated suggestions cannot be applied.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.
Here I've added a new layer
F4
that can run multiple trees in parallel.Also refactored code from
mnist_fff
notebook into a separate template code for benchmarking and made a notebook to testF4
based net vsFFF
based net.Preliminary results:
F4
net gives 95% accuracy on MNIST,FFF
net - 93% accuracy; run time is a bit quicker forFFF
net - will investigate further on larger dataset, but need to deal withmps
errors from pytorch first.