Merged
Conversation
I added some TODO notes in the code that suggesting refactorings
- Replace string reward type config with enum - add loss function to the config - make reward range dynamic - add test to check reward range for every reward type - convert state values to normal python values from Tensors - Negate full training reward
Fix a bug that causes validation loss to be computed even if it is not used.
During meta-train a random subset/prefix of MNIST is used as inner training set. In the old training set (now sgd_train_100instances_deprecated) this could cause issues at the end of the epoch, since the training dataset size was typically not a multiple of the mini-batch size and for some cases the modulo mini-batch was very small (1 or 2), in turn causing feature calculation failure (NaN). This update reduces the inner training dataset sizes to the nearest multiple of 32. As a consequence for any batch-size that is a multiple of 32, the modulo batch should never be smaller than 32. (cherry picked from commit 907eda2)
…o goktug97-sgd_dev_pr
Closed
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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.