| | --- |
| | 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 |
| |
|
| |
|
| | # Demo with Gradio Iterface for visualizing the GradCAM images of CIFAR10 Dataset using Custom Resnet trained on Pytorch Lightning |
| |
|
| | ## Two Demos are created using tabbedinterface |
| |
|
| | ## Demo 1 - Inference and GradCAM images |
| |
|
| |
|
| |
|
| | ### Input |
| |
|
| | 1.Whether he/she wants to see GradCAM images |
| |
|
| | 2.How many images and from which layer |
| |
|
| | 3.Customize the opacity level of the images displayed |
| |
|
| | 4.How many top classes are to be shown (max 10) |
| |
|
| | ### Output |
| |
|
| | Specified GradCAM images displayed with top predicted classes |
| |
|
| | ## Demo 2 - Misclassified Images |
| |
|
| | ### Input |
| |
|
| | How many misclassified images the user wants to visualize (max 10) |
| |
|
| |
|
| | ### Output |
| |
|
| | Specified number of misclassified images are displayed with actual and predicted classes |
| |
|
| | #### Additionally the app allow users to upload new images |
| | #### 10 example images are also provided to the user to try the app |
| |
|
| | ## Github Link |
| |
|
| | https://github.com/RashiTech/ERA-V1/tree/main/S12 |
| |
|
