search

drivendataorg / zamba

A Python package for identifying 42 kinds of animals, training custom models, and estimating distance from camera trap videos
https://zamba.drivendata.org/docs/stable/
MIT License
116 stars 27 forks source link

fixed issue 171 #304

Closed papapizzachess closed 6 months ago

papapizzachess commented 11 months ago

Please review the changes.

netlify[bot] commented 11 months ago

Deploy Preview for silly-keller-664934 ready!

Name Link
Latest commit 34db50ff2ff6194ed930e0184dcbff7c3cbb4076
Latest deploy log https://app.netlify.com/sites/silly-keller-664934/deploys/655f7d307159b200087bc251
Deploy Preview https://deploy-preview-304--silly-keller-664934.netlify.app
Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

ejm714 commented 6 months ago

Closing as this doesn't fix the issue. Each video should only be assigned to one set (train / val / holdout). The issue is that when we have multi-species videos that contain rare species, we can end up with a train / val / holdout set that doesn't contain any examples of a given species.