Update README.md
Browse files
README.md
CHANGED
|
@@ -26,11 +26,13 @@ license: mit
|
|
| 26 |
- face_detection.py
|
| 27 |
- Crops group photos into various individual person photos to feed into the model
|
| 28 |
- celeb_indicies.py
|
| 29 |
-
-
|
| 30 |
- dlib-19.24.99-cp310-cp310-linux_x86_64.whl
|
|
|
|
| 31 |
- DS_Store
|
| 32 |
- Arial Bold.ttf
|
| 33 |
- requirements.txt
|
|
|
|
| 34 |
|
| 35 |
## Datasource
|
| 36 |
- Upload your image via camera, clipboard (copy and pasting), or dragging and dropping a picture file into the UI
|
|
@@ -44,12 +46,14 @@ license: mit
|
|
| 44 |
- numpy
|
| 45 |
- diffusers
|
| 46 |
- torchvision
|
|
|
|
| 47 |
- huggingface_hub
|
| 48 |
- typing
|
| 49 |
- accelerate
|
| 50 |
- invisible_watermark
|
| 51 |
- transformers
|
| 52 |
- xformers
|
|
|
|
| 53 |
|
| 54 |
## Running
|
| 55 |
- The app runs the model out of the box by simple visiting the URL for the HF Space.
|
|
|
|
| 26 |
- face_detection.py
|
| 27 |
- Crops group photos into various individual person photos to feed into the model
|
| 28 |
- celeb_indicies.py
|
| 29 |
+
- List of all the celebrities our model can identify (used to match output index of model to celebrity name)
|
| 30 |
- dlib-19.24.99-cp310-cp310-linux_x86_64.whl
|
| 31 |
+
- Pre-compiled dlib library needed to use the face-recognition library, which identifies and extracts the faces in the images we upload.
|
| 32 |
- DS_Store
|
| 33 |
- Arial Bold.ttf
|
| 34 |
- requirements.txt
|
| 35 |
+
- Standard file used by the HF Space to determine which libraries it needs.
|
| 36 |
|
| 37 |
## Datasource
|
| 38 |
- Upload your image via camera, clipboard (copy and pasting), or dragging and dropping a picture file into the UI
|
|
|
|
| 46 |
- numpy
|
| 47 |
- diffusers
|
| 48 |
- torchvision
|
| 49 |
+
- torch
|
| 50 |
- huggingface_hub
|
| 51 |
- typing
|
| 52 |
- accelerate
|
| 53 |
- invisible_watermark
|
| 54 |
- transformers
|
| 55 |
- xformers
|
| 56 |
+
- face-recognition
|
| 57 |
|
| 58 |
## Running
|
| 59 |
- The app runs the model out of the box by simple visiting the URL for the HF Space.
|