Alexey

* What OpenCV version do you use? * Try to comment this line, does it help? https://github.com/AlexeyAB/yolo2_light/blob/85fc1b388aa00f0243220ed48dac95ac18401b22/src/additionally.h#L32 ---- I just compiled and run Darknet successfull on `Linux Debian 8.2 x64...

> I have followed that step. I comment line 32. >  > It requires **cuDNN >= 7.1.1** https://github.com/AlexeyAB/yolo2_light#yolo2_light

So you have CUDA 8.0 Now you should install `cuDNN v7.1.4 (May 16, 2018), for CUDA 8.0` https://developer.nvidia.com/rdp/cudnn-archive

@USMANHEART This repository is made: * to built-in Yolo source С-code into your application * to understand how it works This repository only for Detection Yolo, not for Training. You...

@USMANHEART * Currently you can train your model by using Float-32bit using this repo: https://github.com/AlexeyAB/darknet as usual and **must** be used one of these cfg-files: * https://github.com/AlexeyAB/yolo2_light/blob/master/bin/yolov3-tiny.cfg * https://github.com/AlexeyAB/yolo2_light/blob/master/bin/yolov3.cfg *...

> But I noticed this thing in your code. I can't use quantized in yolo v3? It's written there that quantization only for yolo v2. This is old comment, that...

@rtrahms Hi, What MSVS version do you use? Did you change anything in the source code or in the yolo_cpu.sln?

@rtrahms Yolo doesn't support OpenCV 4.x, I will do it next week.

OpenCL implementation was made for Yolov2, it still doesn't work with Yolo v3.

Yes, it may be better. You can try and compare. If it will be better you can make Pull request