A newer version of the Gradio SDK is available:
4.44.0
metadata
title: Cifar10C
emoji: 💻
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 3.39.0
app_file: app.py
pinned: false
license: apache-2.0
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
CIFAR10-Class Gradio Interface
Holla!, the first space app.
🚀Available Features:
- Grad-cam images: Activating this check box, will provide the grad-cam visualizations of the image at the defined layer.
- Opacity : degree of gradcam visibility.
- Target Layer : Provides the GradCam image at chosen layer number.
- Mis-classified : Activating the show_images checkbox, will visualize the mis-classified images of the trained model.
💻Usage:
- show_gradcam_images: Activate this if you wanna, view the grad-cam images.
- Opacity : Slide to Choose the degree between the range of (0,1)
- Choose Target layer: Slide Chose the layer number (either -1 or -2) for this model
- show_images : Activate this if you wanna, view mis-classified images.
- Images to display : Slide the number to view number of chosen mis-classified images.
Submit, once the conditions are provided.
👀 Sample:
- If you dont have an image to upload, play with the available example images. (Except dog & truct, need to modify them)
- Select the image you want to play and activate the inputs needed, the output will be displayed.
🏆 Results:
- Provides the top-3 class accuracies for the input image.
- Provides the GradCam Image, mis-classified images upon activating the condition.