Hi, today I would like to share with you a truly amazing solution. It was originally presented on TED Talks about DarkNet by Joseph Redmon. Once I saw it I was wonder how to play with this solution on my MacBook Pro 13 that as you may know has not GPU I am mean it has but not very strong. But that was improved once I bought Sonnet eGFX 580 Puck… the funny thing is that they called 570 but OpenCL detecting it as 580 and it is natively supported by the latest macOS High Sierra 10.13.1, so I spent some time and with CLion from Jet-Brains I have I made many modifications, first I found that someone very smart made version of DarkNet with OpenCL, but I was wonder can I take the latest version of DarkNet from GitHub and made the same changes to have the latest code but with OpenCL support without CUDA at all, so I did that by almost whole weekend. Later I found also a way to path DarkNet with OpenCL to make it works on the latest macOS natively. And As you probably expect the goals were achieved both. Here you can see how it works on the AMD card on the below YT movie. Thanks for reading… I feel almost like C low-level developer after that last week, the results are amazing in my opinion. Also, I want to thank one of my good friend who has a camera in his car and share with me one recorded movie to this blog post. Thanks for reading, below you can find the whole solution in a nutshell as well as the whole source code in C with my patches… There is one more thing, source code is with .git folders that I cloned Today, so with the good editor, you can see all my changes… Enjoy!
VIDEO/DEMO with NO AUDIO
/usr/bin/ruby -e “$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)”
brew install opencv
brew install clblas
brew install clfft
brew install clrng
brew install cmake
brew install wget
https://github.com/pjreddie/darknet PATHED darknet.zip (349 downloads) https://github.com/sowson/darknet ;-).
https://github.com/myestro/darknet PATHED darknet-opencl.zip (383 downloads)
BUILD & TESTS CMDs
rm -r build; mkdir build; cmake -Bbuild -H.; cmake –build build; cp build/darknet .
.darknet detect cfg/yolo.cfg ../weights/yolo.weights [picture/movie]
./darknet detector test cfg/combine9k.data cfg/yolo9000.cfg ../weights/yolo9000.weights [picture/movie]
./darknet detector demo cfg/coco.data cfg/yolo.cfg ../weights/yolo.weights [picture/movie] -thresh 0.25
./darknet detector demo cfg/voc.data cfg/tiny-yolo-voc.cfg ../weights/tiny-yolo-voc.weights [picture/movie] -thresh 0.05
THERE IS ONE MORE THING 😉