README.md

metadata

title: PyTorch Lightning
emoji: 🚀
colorFrom: blue
colorTo: blue
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

Training details:

1. This model is trained on CIFAR10 with following classes: ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
2. It is trained on 24 epochs using One Cycle Policy using PyTorch Lightning

Features of spaces app:

1. User can decide on whether he/she wants to see GradCAM images and how many, and from which layer, allow opacity change as well
2. User can ask whether he/she wants to view misclassified images, and how many (maximum limit is 50)
3. User is allowed to upload new images
4. User can give number of top classes that are to be shown (maximum limit is 10)
5. 10 example images for each class is provided

Github Link for trained model: https://github.com/MPGarg/ERA1_Session12