dog-qiuqiu/simple-rknn2

Stars
42
Rank 653,001 (Top 13 %)
Language
C++
Created over 2 years ago
Updated over 2 years ago

dog-qiuqiu/simple-rknn2

dog-qiuqiu

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588

Yolo-Fastest

⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+

MobileNet-Yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥

Yolo-FastestV2

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

FastestDet

⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

Ultralight-SimplePose

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

Android_NCNN_yolov4-tiny

yolov4-tiny ncnn android sample

Android_MobileNetV2-YOLOV3-Nano-NCNN

MobileNetV2-YOLOV3-Nano NCNN sample

libopencv

Opencv ARM Linux precompiled library

Simple-TensorRT

Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process

dog-qiuqiu