426 add bnn #515
Open
426 add bnn #515
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
Update branch with master
- Modified Dockerfile - Did not install properly - Added git
Open
------
- Added numpy specifically to the environment setup
- "Quick-fixed" the _extract_values_from_raster function due to an error in testing (column name). There is a different path handling for Windows and Linux based OS, ("\" vs. "/"), which caused using the file path instead of the file name. `basename` resolves this issue.
- Removed one test that's already covered with `beartype`, however, which only raised up in Windows, not in Linux.
Enhancements:
-------------
- Added BNN early stopping minimum delta
- Added a test for this parameter
msmiyels
added
modification
- Added support for setting prior_std - Modified prior_std for more robust uncertainty computing
- Added probability comparison for BNN tests
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Outdated suggestions cannot be applied.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.
BNN
Object oriented implementation of the bayesian neural network for binary classification.
Designed for additional cases:
Each way needed changes in order to get even the environment running. Also added
tensorflow-probability.Works basically as other ML methods from
sklearnusing themodel.fit()approach.Done before PR:
LICENSING
Added
THRID-PARTY-LICENCSESsince some of the core capabilities rely on MIT licensing.@nmaarnio is it possible to put the
bayesian_neural_network.pyunderMITlicense? It's not mandatory but may simplify the re-use of this particular code in other applications/repos.OTHERS
_extract_values_from_rasterfunction since Windows and Linux handle file paths differently. The former code usedrsplit("/", 1)explicitly, which resulted in wrong column names on Windows.