Conversation
Added an Active Learning module based on the BADGE (Batch Active
Learning by Diverse Gradient Embeddings) strategy.
The PR includes:
- Active learning plugin
- Adjustments to the CHIMP frontend and datastore logic to support
manual annotation of selected data points.
- Extended backend routes
- A scheduler that monitors labeled datapoints and triggers automatic
retraining when a threshold is reached.
**Issues:**
- Automatic retraining based on newly labeled datapoints currently fails
due to inconsistent preprocessing between the loaded image data and the
model input format.
_Error: Invalid input shape for input Tensor("data:0", shape=(64,),
dtype=float32). Expected shape (None, 96, 96, 3)_
…enter-Data-Intelligence/CHIMP into data_versioning_tests
Closed
Added git ignore rule to disable logs folder from containing files, while still being capable of existing.
Added git ignore rule to disable logs folder from containing files, while still being capable of existing.
Removed logs file as logs aren't supposed to be pushed to git.
Keeping logs folder as a safety precaution, as it was used for logging somewhere in the process. Source still needs to be determined but it is to do with the front-end.
To-do added for future reference. Not urgent, just a nice-to-have, non-breaking, vs-code profile to help with productivity.
Notebook file wasn't intended to be included.
Notebook file wasn't intended to be included.
- Added constraint file - Added requirements install for plugins in docker files - Added constaint file to pip install call - Reset requirements files (except the extra protobuf install)
Updated numpy constraint to 1.24.3.
Move init scripts to seperate folder. Create requirements and constraints for init.
Reorganise init script Fix import init script Delete logs
Bug in main.js for retrieving username Changed tensorflow version in constraints
Add debug info for image recognition Disable frontendbuttons that are not implemented yet.
… solved by Maarten)
This solves the problem that images weren't processed due to an array error.
Blazoned
force-pushed
the
data_versioning_tests
branch
from
e33ddc7 to
a8d0dc1
Compare
Collaborator
|
Alright @LegeDoos, the conflicts should have been resolved- I still like to double check if everything still works aside from the check saying it passed, but the rebase shouldn't have changed anything. |
Collaborator
Thnx, I will look into it soon :) |
LegeDoos
approved these changes
Sep 11, 2025
Collaborator
LegeDoos
left a comment
LegeDoos
left a comment
There was a problem hiding this comment.
In training/app/datastore.py there is a duplicate line on 498. This doesn't break the system and I will not block the review so we can actually close this PR. I will remove the line in the next PR with manual changes.
…enter-Data-Intelligence/CHIMP into data_versioning_tests
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.