Clustering completed. #7
Open
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
…his file will be ignored by git (all files within this directory will be ignored by git with exception of ".gitkeep"). Additionally adding details to README.md to ease set up.
…er. May want to take some of these functions and turn them into a package to use in various microservices?
… not quite accurate.
…o convert to YOLO.
…d version of Ryan's selected method and datapoints are split by a diagonal line. Converted to using BoundingBox class instead of handling coordinates directly. Added labels to output.
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
…ance of center of found cluster to expected cluster center.
…ber expected clusters
charbelmarche33
changed the title
… current methods.
…clustering_mAP Added mAP as accuracy metric. Need spacing/post-processing to improve…
…in to outside ROI
Member
Author
|
@RyanDoesMath Will talk about this in the next meeting, but the results are actually much better than we were getting. We were having an issue with some of the ground-truth data not being accurate to the registered images we were using. I found you had added new data in the Google Drive under cluster_bp_and_hr_yolo.zip so we used that instead, and these are the numbers we are getting:
Still room for improvement with a more robust method of cluster naming, but all-in-all quite an improvement. |
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Outdated suggestions cannot be applied.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.
Second PR from issue 29 of extractor repo.
This is PR n.o. 2 from issue #29.
Methods Evaluated and Performance
Without any error in boxes all methods: kmeans, agglomerative, and dbscan obtained 100% accuracy.
With accounting for 5% error adding and removing boxes
Improvements:
Work moving forward for next semester/in-between other :