Skip to content

Bellzum/streamlit-main

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

162 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

When AI Sees Litter

A Streamlit app that uses a YOLO model to detect three waste types: Clear plastic bottle, Drink can, Styrofoam piece. The app supports Upload image and Camera. Currently, it shows city-specific disposal guidance for Shibuya and SDG tiles for context.

Features

  • Two input modes: Upload image and Camera
  • Loads weights from a public URL or a local file
  • Adjustable thresholds: base confidence, IoU, per-class minimums, minimum box area, inference image size, optional TTA
  • Disposal guidance cards for Shibuya with official links and images
  • SDG tiles: 11, 12, 13
  • Live video was removed

Requirements

Use Python 3.10 or newer. Example requirements.txt:

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages