README.md

metadata

title: CIFAR10 classification with ResNet
emoji: 🔥
colorFrom: green
colorTo: purple
sdk: gradio
sdk_version: 3.39.0
app_file: app.py
pinned: false
license: mit

Gradio UI for CIFAR10 classification with ResNet

How to use?

1. Select if you want visualize the misclassified images & Select the count of misclassified images.
2. Select if you want to visualize the GradCAM images & Also select count of Gradcam images, Model layer and Opacity of the resulting image.
3. Click on the upload button to upload the local image to be used for prediction and select the image for prediction.
4. If you want use one of the sample images, please pick one from the list of 10 sample images.
5. Select the top n classes for which you want see the model performance.
6. Click on the Run button
7. On the right side of the interface, the top view displays the selected number of misclassified images.
8. The second view displays the GradCAM output.
9. And Final view displays the top n predicitons for the given image.

Components Used:

1. gr.Dropdown : Used for selecting the number of images for Misclassified & GradCAM output and also for the top n classes to be displayed.
2. gr.Checkbox : Used for boolean inputs like if user wants to visualize Misclassified or if they want to visualize gradCAM images.
3. gr.Slider : Used to select the opacity paramter to be used with GradCAM viaualization.
4. gr.Gallery: Used to display a numebr of images, used for displaying input images and output images.
5. gr.UploadButton: A generic file uplaod button, used for picking and uploading local image file for prediction.
6. gr.Button: Used for calling the main prediction module.
7. gr.Label: Used for displaying the top n classification results.

HuggingFace Interface