| | --- |
| | title: Action Detection In Images |
| | emoji: 😻 |
| | colorFrom: blue |
| | colorTo: pink |
| | sdk: gradio |
| | sdk_version: 4.31.5 |
| | app_file: app.py |
| | pinned: false |
| | license: mit |
| | --- |
| | |
| | Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
| |
|
| | # General Action Classifier |
| |
|
| | This is a Gradio interface that allows users to upload an image and specify candidate labels to check if a certain action is present in the image. The app uses a CLIP-ViT model to classify the image based on the provided labels. |
| |
|
| | ## How to Use |
| |
|
| | 1. Upload an image. |
| | 2. Enter candidate labels separated by commas. |
| | 3. The app will classify the image and display the results. |
| |
|
| | ## Example |
| |
|
| | For instance, to check if a person is holding a beverage, you can enter labels like: "human with beverage, human, beverage". |
| |
|
