FastFace: Lightweight Face Detection Framework
Easy-to-use face detection framework, developed using pytorch-lightning.
Checkout documentation for more.
Key Features
-
🔥 Use pretrained models for inference with just few lines of code -
📈 Evaluate models on different datasets -
🛠️ Train and prototype new models, using pre-defined architectures -
🚀 Export trained models with ease, to use in production
Contents
Installation
From PyPI
pip install fastface -U
From source
git clone https://github.com/borhanMorphy/light-face-detection.git
cd light-face-detection
pip install .
Pretrained Models
Pretrained models can be accessable via fastface.FaceDetector.from_pretrained(
| Name | Architecture | Configuration | Parameters | Model Size | Link |
|---|---|---|---|---|---|
| lffd_original | lffd | original | 2.3M | 9mb | weights |
| lffd_slim | lffd | slim | 1.5M | 6mb | weights |
Demo
Using package
")[:,:,:3]
# build model with pretrained weights
model = ff.FaceDetector.from_pretrained("lffd_original")
# model: pl.LightningModule
# get model summary
model.summarize()
# 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':[, ...]
# }
">
import fastface as ff import imageio # load image as RGB img = imageio.imread("" )[:,:,:3] # build model with pretrained weights model = ff.FaceDetector.from_pretrained("lffd_original") # model: pl.LightningModule # get model summary model.summarize() # 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':[, ...] # }
Using demo.py script
python demo.py --model lffd_original --device cuda --input
sample output; 
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
References
Citations
@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}
}
16 Dec 7, 2022
42 Dec 30, 2022
125 Dec 22, 2022
1.3k Dec 25, 2022
52 Dec 30, 2022
![[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction](https://github.com/MCG-NJU/SADRNet/raw/main/data/output/30904b202ac883bc14e59c1225c9316c.gif)
99 Dec 30, 2022
86 Aug 3, 2022
17 Apr 26, 2022
608 Jan 2, 2023
2.2k Jan 8, 2023
2 Feb 10, 2022
519 Dec 29, 2022
77 Dec 8, 2022
52 Nov 9, 2022
1 Jan 13, 2022
342 Jan 3, 2023
41 Nov 23, 2022
40 Dec 22, 2022
5 Nov 18, 2022