Fix bug in model parameter reset and add results#9
Open
LukasHedegaard wants to merge 10 commits intosamotiian:masterfrom
Open
Fix bug in model parameter reset and add results#9LukasHedegaard wants to merge 10 commits intosamotiian:masterfrom
LukasHedegaard wants to merge 10 commits intosamotiian:masterfrom
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi, thank You for making the code publicly available.
There is a subtle bug in the implementation when multiple experiments are run. Tensorflow and Keras do not reset model parameters automatically, so by training the model in a loop with varying data, the model is accumulating knowledge from all splits, and not only one as intended.
In this pull request, I have fixed this issue by externalising the experiment loop to an external script and adding the appropriate arguments. A print of the results running the script was added as well.
Also, a Conda environment.yml was added to make reproducibility easier.