Model references
Below are the resources for Daisykit deep learning models. At the current phase of Daisykit, we are focusing on model deployment and overall architecture. Therefore, source code and tutorial for training may be not available for now.
- 1. Person detection (person_detector) and Human pose (Ultralight-Nano-SimplePose):
- Pretrained models: https://github.com/dog-qiuqiu/Ultralight-SimplePose (opens in a new tab).
- 2. Facial landmark:
- Training code: https://github.com/polarisZhao/PFLD-pytorch (opens in a new tab).
- Model conversion: https://github.com/nilseuropa/pfld_ncnn/ (opens in a new tab).
- 3. Face detection (with wearing_mask output): WearMask
- Training & model conversion code: https://github.com/waittim/mask-detector (opens in a new tab).
- 4. Background matting:
- 5. Human pose estimation: Google MoveNet
- Original models: https://tfhub.dev/google/movenet/singlepose/lightning/4 (opens in a new tab), https://tfhub.dev/google/movenet/singlepose/thunder/4 (opens in a new tab), https://tfhub.dev/google/movenet/multipose/lightning/1 (opens in a new tab).
- Converted models from: https://github.com/FeiGeChuanShu/ncnn_Android_MoveNet (opens in a new tab).
- 6. Object detection model: YOLOX
- Training & model conversion code: https://github.com/Megvii-BaseDetection/YOLOX (opens in a new tab).
- Converted by FeiGeChuanShu: https://github.com/FeiGeChuanShu/ncnn-android-yolox (opens in a new tab).