Metadata-Version: 2.1
Name: fastface
Version: 0.1.4
Summary: A face detection framework for edge devices using pytorch lightning
Home-page: https://github.com/borhanMorphy/light-face-detection
Author: Ömer BORHAN
Author-email: borhano.f.42@gmail.com
License: MIT
Project-URL: Documentation, https://fastface.readthedocs.io/en/latest/
Keywords: pytorch_lightning,face detection,edge AI,LFFD
Classifier: Environment :: Console
Classifier: Natural Language :: English
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pytorch-lightning (==1.8.*)
Requires-Dist: torch (>=1.8.1)
Requires-Dist: torchvision (>=0.9.0)
Requires-Dist: torchmetrics (==1.*)
Requires-Dist: imageio (~=2.9.0)
Requires-Dist: scipy (==1.10.1)
Requires-Dist: googledrivedownloader (==0.4)
Requires-Dist: requests (~=2.25.0)
Requires-Dist: PyYAML (~=5.4.1)
Requires-Dist: checksumdir (==1.2.*)
Provides-Extra: all
Requires-Dist: isort ; extra == 'all'
Requires-Dist: black ; extra == 'all'
Requires-Dist: flake8 ; extra == 'all'
Requires-Dist: tox ; extra == 'all'
Requires-Dist: tox-conda ; extra == 'all'
Requires-Dist: pytest ; extra == 'all'
Requires-Dist: pytest-pylint ; extra == 'all'
Requires-Dist: pytest-cov ; extra == 'all'
Requires-Dist: sphinxemoji ; extra == 'all'
Requires-Dist: sphinx-rtd-theme ; extra == 'all'
Requires-Dist: recommonmark ; extra == 'all'
Requires-Dist: sphinx-markdown-tables ; extra == 'all'
Requires-Dist: sphinxcontrib-napoleon ; extra == 'all'
Provides-Extra: dev
Requires-Dist: isort ; extra == 'dev'
Requires-Dist: black ; extra == 'dev'
Requires-Dist: flake8 ; extra == 'dev'
Requires-Dist: tox ; extra == 'dev'
Requires-Dist: tox-conda ; extra == 'dev'
Requires-Dist: pytest ; extra == 'dev'
Requires-Dist: pytest-pylint ; extra == 'dev'
Requires-Dist: pytest-cov ; extra == 'dev'
Requires-Dist: sphinxemoji ; extra == 'dev'
Requires-Dist: sphinx-rtd-theme ; extra == 'dev'
Requires-Dist: recommonmark ; extra == 'dev'
Requires-Dist: sphinx-markdown-tables ; extra == 'dev'
Requires-Dist: sphinxcontrib-napoleon ; extra == 'dev'
Provides-Extra: docs
Requires-Dist: sphinxemoji ; extra == 'docs'
Requires-Dist: sphinx-rtd-theme ; extra == 'docs'
Requires-Dist: recommonmark ; extra == 'docs'
Requires-Dist: sphinx-markdown-tables ; extra == 'docs'
Requires-Dist: sphinxcontrib-napoleon ; extra == 'docs'
Provides-Extra: test
Requires-Dist: pytest ; extra == 'test'
Requires-Dist: pytest-pylint ; extra == 'test'
Requires-Dist: pytest-cov ; extra == 'test'

# FastFace: Lightweight Face Detection Framework

![PyPI](https://img.shields.io/pypi/v/fastface)
[![Documentation Status](https://readthedocs.org/projects/fastface/badge/?version=latest)](https://fastface.readthedocs.io/en/latest/?badge=latest)
[![Downloads](https://pepy.tech/badge/fastface)](https://pepy.tech/project/fastface)
![PyPI - Python Version](https://img.shields.io/pypi/pyversions/fastface)
![PyPI - License](https://img.shields.io/pypi/l/fastface)

**Easy-to-use face detection framework, developed using [pytorch-lightning](https://www.pytorchlightning.ai/).**<br>
**Checkout [documentation](https://fastface.readthedocs.io/en/latest/) for more.**

## Key Features

- :fire: **Use pretrained models for inference with just few lines of code**
- :chart_with_upwards_trend: **Evaluate models on different datasets**
- :hammer_and_wrench: **Train and prototype new models, using pre-defined architectures**
- :rocket: **Export trained models with ease, to use in production**

## Contents

- [Installation](#installation)
- [Pretrained Models](#pretrained-models)
- [Demo](#demo)
- [Benchmarks](#benchmarks)
- [Tutorials](#tutorials)
- [References](#references)
- [Citations](#citations)

## Installation

From PyPI

```
pip install fastface -U
```

From source

```
git clone https://github.com/borhanMorphy/fastface.git
cd fastface
pip install .
```

## Pretrained Models

Pretrained models can be accessable via `fastface.FaceDetector.from_pretrained(<name>)`

|       Name        | Architecture | Configuration | Parameters | Model Size |                                             Link                                              |
| :---------------: | :----------: | :-----------: | :--------: | :--------: | :-------------------------------------------------------------------------------------------: |
| **lffd_original** |     lffd     |   original    |    2.3M    |    9mb     | [weights](https://drive.google.com/file/d/1qFRuGhzoMWrW9WNlWw9jHXPY51MBssQD/view?usp=sharing) |
|   **lffd_slim**   |     lffd     |     slim      |    1.5M    |    6mb     | [weights](https://drive.google.com/file/d/1UOHllYp5NY4mV7lHmq0c9xsryRIufpAQ/view?usp=sharing) |

## Demo

Using package

```python
import fastface as ff
import imageio
from pytorch_lightning.utilities.model_summary import ModelSummary

# load image as RGB
img = imageio.imread("<your_image_file_path>")[:,:,:3]

# build model with pretrained weights
model = ff.FaceDetector.from_pretrained("lffd_original")
# model: pl.LightningModule

# get model summary
ModelSummary(model, max_depth=1)

# set model to eval mode
model.eval()

# [optional] move model to gpu
model.to("cuda")

# model inference
preds, = model.predict(img, det_threshold=.8, iou_threshold=.4)
# preds: {
#    'boxes': [[xmin, ymin, xmax, ymax], ...],
#    'scores':[<float>, ...]
# }

```

Using [demo.py](/demo.py) script

```
python demo.py --model lffd_original --device cuda --input <your_image_file_path>
```

sample output;
![alt text](resources/friends.jpg)

## Benchmarks

**Following results are obtained with this repository**

#### WIDER FACE

validation set results

|       Name        |   Easy    |  Medium   |   Hard    |
| :---------------: | :-------: | :-------: | :-------: |
| **lffd_original** | **0.893** | **0.866** | **0.758** |
|   **lffd_slim**   | **0.866** | **0.854** | **0.742** |

## Tutorials

- [Widerface Benchmark](./tutorials/widerface_benchmark/README.md)
- [BentoML Deployment](./tutorials/bentoml_deployment/README.md)

## References

- [LFFD Paper](https://arxiv.org/pdf/1904.10633.pdf)
- [Official LFFD Implementation](https://github.com/YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices)

## Citations

```bibtex
@inproceedings{LFFD,
    title={LFFD: A Light and Fast Face Detector for Edge Devices},
    author={He, Yonghao and Xu, Dezhong and Wu, Lifang and Jian, Meng and Xiang, Shiming and Pan, Chunhong},
    booktitle={arXiv:1904.10633},
    year={2019}
}
```
