Easy-to-use face detection framework, developed using pytorch-lightning.
Checkout documentation for more.
- ๐ฅ Use pretrained models for inference with just few lines of code
- ๐ Evaluate models on different datasets
- ๐ ๏ธ Train and prototype new models, using pre-defined architectures
- ๐ Export trained models with ease, to use in production
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 can be accessable via fastface.FaceDetector.from_pretrained(<name>)
Name | Architecture | Configuration | Parameters | Model Size | Link |
---|---|---|---|---|---|
lffd_original | lffd | original | 2.3M | 9mb | weights |
lffd_slim | lffd | slim | 1.5M | 6mb | weights |
Using package
import fastface as ff
import imageio
# 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
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':[<float>, ...]
# }
Using demo.py script
python demo.py --model lffd_original --device cuda --input <your_image_file_path>
Following results are obtained with this repository
validation set results
Name | Easy | Medium | Hard |
---|---|---|---|
lffd_original | 0.893 | 0.866 | 0.758 |
lffd_slim | 0.866 | 0.854 | 0.742 |
@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}
}