Coolpi has been adapted to FastDeploy

[zhengbicheng]

Brief Introduction

FastDeploy is an easy-to-use and high performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. Including image classification, object detection, image segmentation, face detection, face recognition, keypoint detection, matting, OCR, NLP, TTS and other tasks to meet developers' industrial deployment needs for multi-scenario, multi-hardware and multi-platform.

We spent a lot of time on the adaptation of FastDeploy for Coolpi. The model we have adapted can be used in Detection, Face Detection, Face Recognition, Face Alignment, Segmentation, OCR and other fields. These models will greatly improve Coolpi's ability in edge computing.

Model List

In order to facilitate you to choose a reasonable model to apply to your project, we have provided the running speed of the model.

Task	Model Name	Model Version	Whether to Quantify	RKNN Speed(ms)
Classification	ResNet	ResNet50_vd	No	33
Detection	Picodet	Picodet-s	No	112
Detection	PaddleDetection Yolov8	yolov8-n	No	100
Detection	PPYOLOE	ppyoloe-s	Yes	141
Detection	RKYOLOV5	YOLOV5-S-Relu	Yes	57
Detection	RKYOLOX	yolox-s	Yes	130
Detection	RKYOLOV7	yolov7-tiny	Yes	58
Segmentation	Unet	Unet-cityscapes	No	-
Segmentation	PP-HumanSegV2Lite	portrait	Yes	43
Segmentation	PP-HumanSegV2Lite	human	Yes	43
Face Detection	SCRFD	SCRFD-2.5G-kps-640	Yes	42
Face FaceRecognition	InsightFace	ms1mv3_arcface_r18	Yes	12

Demo

• Face Detection with SCRFD
• Face Recognition with ArcFace
• Try to deploy YOLOv5 on coolpi

Contribution

Thanks to Baidu FastDeploy team for making such a good tool so that we can easily deploy AI model.

[bbsvs2000]

期待NPU支持 :

单镜头、单类别的单目标跟踪

单镜头、单类别的多目标跟踪

单镜头、多类别的多目标跟踪

[zhengbicheng]

@bbsvs2000 目标追踪？指deepsort一类的吗？

[ccjjww1222]

@zhengbicheng 我也期望有追踪，deepsort就可以了，利用CPU算，比较耗费资源，特别是多个摄像头追踪，NPU算比较好