Add stuff from last week of competition #88
Merged
Conversation
This file contains 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
If binary_crossentropy is loss_function, then the activation should be sigmoid
Now using the correct activation fn.
If "flying blind" and using no or little validation data, it makes sense to use the model found in the final epoch instead of the "best" according to the validation score. Also, this fixes a bug wherein the model from the final epochs was always used after the train_model task completed.
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Outdated suggestions cannot be applied.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.
This PR adds a lot of odds and ends that were put together in a hurry during the last week of the competition. We added Inception V3 as a model, which seemed to improve the score, but are not including it in this PR, since the Inception code included with Keras which we were using has a problem which we don't want to fix at the moment. See #89
Connects #79