[WIP] Mini-batch training in VAE #10
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
* Masking is disabled as it seems to necessitate more implementation details, and we're not planning on using it * A GC layer that doesn't want to subsample can simply use a gather input equal to all node indices * Gather input is fed to the layer call; it is a 1-D tensor, so not compatible with keras shape constraints (which uses at least 2-D tensors to include batch and inner dimensions); we will be feeding it through TF native placeholders
This lets us give a `feed_dict` to session calls inside predict and fit functions.
The update notebook also shows how to use it.
|
Things left to do:
|
…d_loss is right for a non-tiled adjacency prediction
In particular, `Codec.logprobability()`, when called from `Codec.estimated_pred_loss()`, should return something that has shape (batch, samples), i.e. it should flatten and average over all the other inner dimensions.
wehlutyk
added a commit
that referenced
this pull request
Jul 10, 2018
wehlutyk
added a commit
that referenced
this pull request
Jul 10, 2018
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Outdated suggestions cannot be applied.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.
Work-in-progress pull request for #3, updated as work advances.
Feel free to comment or push other commits!