Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/orestis-z/facial-beauty-predictor
Deep learning model to predict a beauty score for faces in images. Outperforms the state-of-the-art by up to 18% (2019).
https://github.com/orestis-z/facial-beauty-predictor
computer-vision deep-learning deep-neural-networks facial-beauty-prediction scikit-learn tensorflow
Last synced: 12 days ago
JSON representation
Deep learning model to predict a beauty score for faces in images. Outperforms the state-of-the-art by up to 18% (2019).
- Host: GitHub
- URL: https://github.com/orestis-z/facial-beauty-predictor
- Owner: orestis-z
- License: mit
- Created: 2020-10-16T20:42:40.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2020-10-16T20:52:44.000Z (over 4 years ago)
- Last Synced: 2024-12-30T02:42:35.117Z (25 days ago)
- Topics: computer-vision, deep-learning, deep-neural-networks, facial-beauty-prediction, scikit-learn, tensorflow
- Language: Python
- Homepage:
- Size: 2.15 MB
- Stars: 25
- Watchers: 1
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Facial Beauty Predictor
A deep learning model based on FaceNet and MTCNN to predict a beauty score for faces in images. The CNN outperformes the state-of-the art by up to 18% (2019).
Included are scripts for generating features from images, training regressors, as well as a async server for inference based on gunicorn / gevent.
## Based on
[tindetheus](https://github.com/cjekel/tindetheus)
[FaceNet](https://github.com/davidsandberg/facenet)
[MTCNN](https://github.com/ipazc/mtcnn)
## Requirements:
- python 3.7
- [pipenv](https://github.com/pypa/pipenv)
## Installation
`pipenv install --dev`
## Quick Start
- Download [SCUT](https://github.com/HCIILAB/SCUT-FBP5500-Database-Release) dataset
- Download [HotOrNot](https://www.researchgate.net/publication/261595808_Female_Facial_Beauty_Dataset_ECCV2010_v10) dataset
- Download the FaceNet model [20170512-110547](https://drive.google.com/file/d/0B5MzpY9kBtDVZ2RpVDYwWmxoSUk/edit) and extract it into the `data` directory
- Convert datasets with:
- `python scripts/convert_scut.py --db-dir `
- `python scripts/convert_tinder.py --db-dir `
- `python scripts/convert_hotornot.py --db-dir `
- Generate features for SCUT dataset once and store them to the disk:
- `python scripts/generate_features_async.py --db data/scut.pkl --output-dir data/scut`
- Train regressor models with
- `python scripts/train_regressor.py --db data/scut.pkl --output-dir data/scut/mtcnn-facenet --features data/scut/mtcnn-facenet/features.npy`
- Compare regressors:
- `python scripts/compare_models.py --db data/scut.pkl --output-dir data/scut/mtcnn-facenet --models-dir data/scut/mtcnn-facenet/models --features data/scut/mtcnn-facenet/features.npy`
- Generate model trained on all the dataset:
- `python scripts/train_regressor.py --db data/scut.pkl --output-dir data/scut/mtcnn-facenet --features data/scut/mtcnn-facenet/features.npy --no-split`
- Generate features for Tinder dataset once and store them to the disk:
- `python scripts/generate_features_async.py --db data/tinder.pkl --output-dir data/tinder`
- Infer results on tinder dataset:
- `python scripts/infer.py --db data/tinder.pkl --features data/tinder/mtcnn-facenet/features.npy --model data/scut/mtcnn-facenet/models/all/sklearn.linear_model.base.LinearRegression_1.pkl`
Those steps can be repeated for a mtcnn-only backbone (put `--backbone mtcnn` flag where necessary and replace `mtcnn-facenet` with `mtcnn`)
## Results
### SCUT Dataset
#### FaceNet features
| Regressor | PC |
| --------- | ----- |
| Lasso | 0.846 |
| Ridge | 0.872 |
| Linear | 0.872 |
#### FaceNet + MTCNN features:
| Regressor | PC |
| --------- | --- |
@TODO (note: was slightly better than Facenet features only)
#### MTCNN only features
| Regressor | PC |
| --------- | --- |
@TODO
### HotOrNot Dataset
#### FaceNet features
| Regressor | PC |
| --------- | ----- |
| Linear | 0.536 |
| Lasso | 0.550 |
| Ridge | 0.567 |
#### FaceNet + MTCNN features
| Regressor | PC |
| --------- | --- |
@TODO
#### MTCNN only features
| Regressor | PC |
| --------- | --- |
@TODO