Skip to content

DetectorDetective: Investigating the Effects of Adversarial Examples on Object Detectors

License

Notifications You must be signed in to change notification settings

poloclub/detector-detective

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DetectorDetective

DetectorDetective, an interactive visual tool that aims to help users better understand the behaviors of a model as adversarial images journey through an object detector.

Live Demo

https://www.youtube.com/watch?v=5C3Klh87CZI

Running Code

The DetectorDetective.ipynb consists of codes to generate all the visualizations needed. Make sure to give an appropriate path name in the file to download the visualizations. Datasets folder should have the same structure as shown here

streamlit run streamlit_visualization.py

The above command with addresses pointing to the saved image directory should be enough to open the app locally.