README.md

---
title: Pytorch Lighting
emoji: 🏢
colorFrom: purple
colorTo: indigo
sdk: gradio
sdk_version: 3.39.0
app_file: app.py
pinned: false
license: mit
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference


Pytorch Lighting
🚀 Features:

🎨 GradCAM Visualization: User can adjust the visualization opacity and select model layers to be used.
🚫 Misclassified Images: View where the model went wrong.
📷 Image Upload & Examples:  User can test prediction on new images which can be uploaded.
🥇 Top Predictions: View model's top class predictions (up to 10).


🔍 How to Use:
📥 Choose an Image: Upload your own or pick from the examples.
🎛️ Tweak Settings: Adjust sliders for GradCAM, top predictions, and misclassified images.
🟢 Submit: Click to get results.

❓ Feedback/Contribution: Got suggestions or wish to help? Reach out!
Usecase: This interface uses a ResNet18 model trained on CIFAR10. GradCAM visualizations highlight the model's focus.

⚠️ Note: Best with CIFAR10-related images.