Skip to content

edadaltocg/demo-ood-detection

Repository files navigation

title emoji colorFrom colorTo sdk sdk_version app_file pinned license
OOD Detection
🧐
purple
purple
gradio
3.12.0
app.py
true
mit

OOD Detection Demo 🧐

Out-of-distribution (OOD) detection is an essential safety measure for machine learning models. This app demonstrates how these methods can be useful. They try to determine wether we can trust the predictions of a ResNet-50 model trained on ImageNet-1K.

This demo is online at https://huggingface.co/spaces/edadaltocg/ood-detection

Running Gradio app locally

  1. Install dependencies:
pip install -r requirements.txt
  1. Run the app:
python app.py
  1. Open the app in your browser at http://localhost:7860.