A newer version of the Gradio SDK is available:
6.8.0
metadata
title: CIFAR10 CustomResnet GradCAM
emoji: ⚡
colorFrom: gray
colorTo: green
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
CIFAR10 ResNet18 Gradio Interface
Training details:
- This model is trained on CIFAR10 with following classes: ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
Features:
- GradCAM Visualization: User can adjust the visualization opacity and select model layers to be used.
- Misclassified Images: User can view in which images prediction went wrong.
- Image Upload & Examples: User can test prediction on new images which can be uploaded.
- Top Predictions: User can 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.
Usecase: This interface uses a ResNet18 model trained on CIFAR10. GradCAM visualizations highlight the model's focus.