Overview
I created an inference app using Hugging Face Spaces and a YOLOv5 model trained on the KaoKore dataset.
The KaoKore dataset published by the Center for Open Data in the Humanities (CODH) is as follows:
Yingtao Tian, Chikahiko Suzuki, Tarin Clanuwat, Mikel Bober-Irizar, Alex Lamb, Asanobu Kitamoto, “KaoKore: A Pre-modern Japanese Art Facial Expression Dataset”, arXiv:2002.08595.
http://codh.rois.ac.jp/face/dataset/
You can try the inference app at the following URL:
https://huggingface.co/spaces/nakamura196/yolov5-face
The source code and trained model can be downloaded from the following URL. I hope it serves as a reference when developing similar applications.
https://huggingface.co/spaces/nakamura196/yolov5-face/tree/main
The application development referenced the following Space:
https://huggingface.co/spaces/pytorch/YOLOv5
Usage
You can upload an image or select one from the Examples. Detection results can be confirmed as shown below.
“Bunsho Soshi” (Japanese Classical Books Dataset (owned by NIJL) distributed by CODH)
Summary
While the detection accuracy may not be sufficient in some areas, I hope this serves as a useful reference.
The current model uses YOLOv5, but I would like to try newer models in the future.