Darknet-YOLO Compiled For Live Cam Stream Object Recognition

[rockedge]

I have had difficulty in compiling Darknet-YOLO with Opencv support in both Puppy Linux Bionic32-v8 and Bionic64-v8. I used this version of darknet -> https://github.com/AlexeyAB/darknet

But Compiling Darknet-YOLO using BionicDog32 and BionicDog64 worked well and built Darknet with Opencv and boosted CPU performance flags enabled.

experimenting by copying the darknet binaries and YOLO weight files from BionicDog64 to a Puppy Linux Bionic64-v8 and with the devx and libopencv-dev installed, works well. Below is a screeshot of a live stream using a Microsoft webcam.

I am wondering if I should actually try to make a PET and / or an SFS ? Does anyone think something like this is worth a PET for Puppy Linux Bionic both 32 and 64 bit?

[rockedge]

I have not found a good way to package this as a PET yet so here are the binaries and what one will need to start experimenting. These are compiled in BionicDog and work well with Bionic Puppys

Compiled with Opencv in BionicDog64
http://rockedge.org/kernels/data/PET/Bi ... x64.tar.gz

Compiled with Opencv in BionicDog32
http://rockedge.org/kernels/data/PET/Bi ... -32.tar.gz

yolov3-openimages.cfg (247 MB COCO Yolo v3) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3 ... es.weights
yolov3-spp.cfg (240 MB COCO Yolo v3) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-spp.weights
yolov3.cfg (236 MB COCO Yolo v3) - requires 4 GB GPU-RAM:https://pjreddie.com/media/files/yolov3.weights
yolov3-tiny.cfg (34 MB COCO Yolo v3 tiny) - requires 1 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-tiny.weights
yolov2.cfg (194 MB COCO Yolo v2) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov2.weights
yolo-voc.cfg (194 MB VOC Yolo v2) - requires 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo-voc.weights
yolov2-tiny.cfg (43 MB COCO Yolo v2) - requires 1 GB GPU-RAM: https://pjreddie.com/media/files/yolov2-tiny.weights
yolov2-tiny-voc.cfg (60 MB VOC Yolo v2) - requires 1 GB GPU-RAM: http://pjreddie.com/media/files/yolov2-tiny-voc.weights
yolo9000.cfg (186 MB Yolo9000-model) - requires 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo9000.weights

[rockedge]

Here is Yolo_mark a Linux GUI for marking bounded boxes of objects in images for training Yolo v3 and v2

compiled in BionicDog64 and works in Bionic64-v8, this tool can be used to train your own custom objects to recognize. All binary packages are under PET in http://rockedge.org/kernels

http://rockedge.org/kernels/data/PET/Bi ... ark.tar.gz

https://github.com/AlexeyAB/Yolo_mark