- A fully retrained version of Detectron2 on the FDDB Dataset with additional modifications and added compatibility with more recent versions of Python.
- Retained the object detection aspect of Detectron2 and adapted it to just facial detection.
- Contains multiple versions of the same model, trained with some variability in our hyperparameters specified below.
See our repository to see more information regarding model and evaluation statistics, read our report, or learn about detectron2.
See installation instructions for our model.
See installation instructions for detectron2.
See Getting Started with Detectron2, and our Colab Notebook to learn about basic usage.
Learn more about Detectron2 documentation. And see projects/ for some projects that are built on top of detectron2.
@misc{gonzalez2024areyoutrieulypayingattentionorjustjoshingnoahmnotbuthilarioisNET,
author = {Hilario Gonzalez, Josh Bardwick, Noah Hathout, Trieu Tran},
title = {AreYouTrieulyPayingAttentionOrJustJoshingNoahmNotButHilarioIsNET},
howpublished = {\url{https://github.com/nhathout/AreYoutTrieulyPayingAttentionOrJustJoshingNoahmNotButHilarioIsNET}},
year = {2024}
}
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}
@misc{face-detection-40nq0_dataset,
title = { Face detection Dataset },
type = { Open Source Dataset },
author = { FDDB },
howpublished = { \url{ https://universe.roboflow.com/fddb/face-detection-40nq0 } },
url = { https://universe.roboflow.com/fddb/face-detection-40nq0 },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { feb },
note = { visited on 2024-05-02 },
}