Hi, Today I would like to announce that my GitHub fork at https://github.com/sowson/darknet has a new update, the fork is an advanced port of DarkNet CNN from CUDA to OpenCL and tested on macOS with eGPU from Sonnet named Breakaway RX 570 Puck and on my GreenPC it also supports Intel Iris GPU, OpenCV 3, and there are several use cases for it. Yolo3, Yolo2, Yolo1, CIFAR-10 solutions work fine, using demo from webcam also, from mp4 videos Continue ReadingDarkNet in OpenCL
Hi, Today I would like to announce that my GitHub fork at https://github.com/sowson/darknet has a new update, the fork is an advanced port of DarkNet CNN from CUDA to OpenCL and tested on macOS with eGPU from Sonnet named Breakaway RX 570 Puck and on my GreenPC. Let’s get started the training by the inspiration from the solution original author Joseph Redmon given the TED talk. Interested how it works and how to rebuild? Why I spent some Continue ReadingDarkNet Training
Hi, Today I would like to announce that my GitHub fork at https://github.com/sowson/darknet has a new update, the fork is a advanced port of DarkNet CNN from CUDA to OpenCL and tested on macOS with eGPU from Sonnet named Breakaway RX 570 Puck. You can enjoy my coding work on this subject by cloning the GIT repository. I only want to show you two pictures of detections on my GreenPC. YoloV2 [gamer@dreampc darknet]$ ./darknet detect cfg/yolov2.cfg ../../weights/yolov2.weights data/dog.jpgDevice Continue ReadingDarkNet CNN in OpenCL on macOS with Yolo3
Yes, I know that it is impossible to predict lottery results. But if the results would be predictable? Of course I know they are not, but just hypothetically for a play with Perceptron Neural Network and prediction algorithms I want to show you that in 256 ;-) lines of code you are able to play with prediction thanks to EnCog 3.4 library. I bought recently 2 Jeff Heaton’s books about neural networks and C# and his library. Continue ReadingEuroJackpot with EnCog ANN and Stats
Hi, today I will instead of any new idea, show you my latest upgraded DreamPC. I used it for some time to Image Recognition and it works quite well. Once I was involved by myself into self-study about Convutional Neural Networks and the C code I used CentOS GNU/Linux, but now I bring it back. I want to share the spec, it is not so impressive I believe. But it is enough to play all games I Continue ReadingGreen PC
Hi, First welcome in 2018 on my blog, I hope you all feel exited in the new year like me, sorry to be silent for a while, but I was absorbing my first GitHub fork wich is “sowson/darknet” and I was coding like a crazy one. Still I have several todo on this code but I really like it. And regarding to this journey, Today I would like to share with you something really awesome that I Continue ReadingFloating Pointers on OpenCL cl_mem
Hi, today I would like to share with you 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 Continue ReadingCar See by DarkNet CNN on MacBookPro 13 with Sonnet eGFX 580
Sorry, I do not know how to play, I just love Piano sound… ;-). Do you like it? I will play anyway… ;-). p ;).
The winner is: eGFX Breakaway Puck RX 570 aka Beauty Beast Pros: Natively support macOS 10.13.1, support ghost HDMI adapter, very quiet, awesome :-). Cons: Price :-(, ghost HDMI adapter could be included. p ;-).
Hi, some time ago I wrote the post about Sonnet eGPU company product. It was in my opinion too big, too heavy and overall not nice. But I found on the YouTube nice video when Sonnet representative has small box to present and he named it puck solution. It was awesome, I found on the research and development of the company that this is something Sonnet is planning to do and lunch. I was really impressed of Continue ReadingeGFX Breakaway Puck Beauty Beast
Hi, today I would like to show you how to solve the code puzzle with the time line. Where you have to in O(n) determine how many maximal events happen the same time… I hope you like it ;-). I looked on the Internet and there is no correct solution for this problem in my opinion, so far. So I decided to write on my own this solution and share with my readers… On the Internet there Continue ReadingHackerRank Customer Service Capacity
I was never try to give a motivation a speech and probably I will never do publicly. But after great people like Steve, Oprah, Joan, Bill who had given a speech to postgraduate of Stanford and Harvard I want to try to write my own three stories of my life, no big deal just three stories. I know I am not a category of persons I seen and I try to follow, famous and rich, but I Continue ReadingMotivational Speach