|
|
--- |
|
|
title: Face Recognition |
|
|
emoji: 🖼 |
|
|
colorFrom: purple |
|
|
colorTo: red |
|
|
sdk: gradio |
|
|
sdk_version: 5.0.1 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: mit |
|
|
short_description: Trained model to recognize faces |
|
|
startup_duration_timeout: 2h |
|
|
--- |
|
|
|
|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
|
|
|
# Face Recognition Model |
|
|
"CSSE416-final-project/face-recognition" is the Hugging Face (HF) repository for the Face Recognition Application. It runs the HF faceRecogModel |
|
|
|
|
|
|
|
|
## Files |
|
|
- app.py |
|
|
- App code to take-in an image, process it, feed it into the model, and format its outputs. |
|
|
- face_detection.py |
|
|
- Crops group photos into various individual person photos to feed into the model |
|
|
- celeb_indicies.py |
|
|
- List of all the celebrities our model can identify (used to match output index of model to celebrity name) |
|
|
- dlib-19.24.99-cp310-cp310-linux_x86_64.whl |
|
|
- Pre-compiled dlib library needed to use the face-recognition library, which identifies and extracts the faces in the images we upload. |
|
|
- DS_Store |
|
|
- Arial Bold.ttf |
|
|
- requirements.txt |
|
|
- Standard file used by the HF Space to determine which libraries it needs. |
|
|
|
|
|
## Datasource |
|
|
- Upload your image via camera, clipboard (copy and pasting), or dragging and dropping a picture file into the UI |
|
|
- For large scale testing, check out the model itself |
|
|
|
|
|
## Neccessary Package |
|
|
- Since the model all runs on Hugging Face, you don't need to install any packages. |
|
|
- However, if you do want to run the model locally, you will need to install these following packages: |
|
|
- pillow |
|
|
- gradio |
|
|
- numpy |
|
|
- diffusers |
|
|
- torchvision |
|
|
- torch |
|
|
- huggingface_hub |
|
|
- typing |
|
|
- accelerate |
|
|
- invisible_watermark |
|
|
- transformers |
|
|
- xformers |
|
|
- face-recognition |
|
|
|
|
|
## Running |
|
|
- The app runs the model out of the box by simple visiting the URL for the HF Space. |
|
|
- Alternatively, if you want to test the model locally, you can download the repo and run "app.py" |
|
|
|
|
|
|
