This repository was archived by the owner on Jun 14, 2024. It is now read-only.
Open
Conversation
Runnable code (results not great! - requires debugging) Added callback functions for custom print statements in batch_loop and grad_based_inference
Improved output formatting Fixed a bug in the batch loop executor
Removed unneeded code in vanilla coreset Fixed a print statement
Updated model class to support multi-headed models Updated experiment class to reflect changes
Tidying up of experiment runner
…entally creating new variables on access
Added custom print function to minibatch loop
# Conflicts: # mxfusion/components/variables/variable.py # testing/components/functions/operators_test.py
…ved, but also will not be inferred.
…://github.com/google/python-fire) Some tidy up A few fixes for permuted mnist due to regressions
# Conflicts: # mxfusion/components/functions/operators/operator_impl.py # mxfusion/inference/grad_based_inference.py # mxfusion/inference/inference_alg.py # mxfusion/models/factor_graph.py
Codecov Report
@@ Coverage Diff @@
## develop #159 +/- ##
===========================================
- Coverage 85.06% 84.59% -0.47%
===========================================
Files 78 78
Lines 3897 3947 +50
Branches 660 672 +12
===========================================
+ Hits 3315 3339 +24
- Misses 383 404 +21
- Partials 199 204 +5
Continue to review full report at Codecov.
|
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description of changes:
This is an example that attempts to replication the Variational Continual Learning method of Cuong Nguyen, Yingzhen Li, Thang Bui, and Richard Turner. This required some new functionality (ignored variables) which has been incorporated into the core. Currently the the code is running (tested for split MNIST) but the results don't yet match the results from the paper.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.