Skip to content

App that leverages neural networks to classify images of the Asian giant hornet (vespa mandarinia) and 5 other hymenoptera that look similar.

Notifications You must be signed in to change notification settings

MarkPare/hornets

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

53 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Asian giant hornet detector

A simple app that leverages neural networks to classify images of the Asian giant hornet (vespa mandarinia) and 5 other hymenoptera that look similar. App is live here.

Checkout the notebook for more information on model architecture and data sourcing. Draws heavily from this pytorch tutorial.

Aside from the model, the application consists of a Flask API that receives image uploads and returns a prediction, and a React web client. The web client also serves as a user interface for manually cleaning up raw image data in an efficient way (full functionality for this depends on some local file structure handling not fully documented here).

App is deployed using Kubernetes on GKE / GCP.

Note from author

Would love to see this tool improve! If you're interested in collaborating or have additional data, please contact me.

About

App that leverages neural networks to classify images of the Asian giant hornet (vespa mandarinia) and 5 other hymenoptera that look similar.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published