it is the best i did with the talent i had…
Hi, today I would like to show you issue I faced for a long time… I wanted to use Monte Carlo Tree Search with classic select, expand, back propagate and so on… the problem I faced was the memory leak, and I was looking for some time to good solution to reduce memory by one level and efficnet free memory. To make it correclty you have to calculate max depth and reecude Continue ReadingFree Correctly MCTS in C in the iChess.io
Hi, today I would like to share a bit one solution that makes me happy on macOS and C programming. Tracking allocated memory to look for memory leaks. It is very careful and quite detailed finds missing memory. It also can be very ellegant disabled by commented out definition of enable it. Maybe not like Valgrind on Linux but for me on macOS is super cool. Enjoy! Thanks!
Hi, my Dear Readers! ;-). Let me start Today’s story with the fact that the iChess.io starts to play Chess and Chess 960 as well ;-). Without that start statement, any design advantages do not make sense. Please remember that any good architectural design is about how things work, not how things are built. I heard that once, and it made an impression on me. It turns out a clear understanding that Continue ReadingiChess.io Architecture
This is a day, I was looking forward entire year. I remember the moment when we discuss with Professor Jacek Izydorczyk the subject of math oriented AI that can be very enjoyable and valuable, the Game of Kings. But first, we considered to reaserch AI in the medical aspects of usage, the financial, and then I told that the best in class AI is for gaming but the only game I am Continue ReadingiChess.io v2.27
Hi, it has been some time since the last entry on this blog… ;-). I almost forget how nice it is to write a blog post in the middle of the night with AirPods music :P. Truth be told, I almost dropped this iChess.io project once on the aiChess.io I could not make sufficient working self-learning of the chess. I do not want to use any books on chess, only, like they Continue ReadingThe iChess.io v1.27 is Ready to Play Publicly with Reinforcement Learning 😉
Hi, recently I helped a bit for a GitHub user rajhlinux. I am not sure if you are familiar with this Operation System. I am only a bit. But the beauty of C and C++ is that it works on different OSes and works fast! Below cute daemon image is from Wikipedia, and you can click on it to learn more. This user, a fan of FreeBSD, was using version 13.1 and Continue ReadingDarknet on OpenCL on FreeBSD 13.1
Hi, there are many challenges on Windows 11 x64 with AMD Radeon RX 6900 XT. For the last few months, from time to time, I started to try to build on Windows 10 x64 first and later I updated to Windows 11 x64. There are the following open issues I faced: 1) Time spent on detection is a bit longer than on GNU/Linux or macOS. 2) Detections seem fine when I try Continue ReadingDarknet on OpenCL on Windows 11 x64
Hello, I am a Ph.D. student in Poland at the Silesian University of Technology. And I wanted to start a general discussion on the classifier on the video stream improvement idea. I called it the “Multi-GPU & Multi-SET” or, in short, the “Multi-GPU-SET” idea. People use Multi-GPU and the “Syncing” for Convolutional Neural Networks. But nobody, in my opinion, tried multi-GPU to classify. So what is it about? Well, it is about Continue ReadingThe Multi-GPU-SET Idea
Hello, after about half-year, I at last found the solution to the biggest optimization issue I had so far in the Darknet on OpenCL solution. It was tough to solve, and I even wrote at the AMD Community Post. Today very early morning, I posted on that post solution shown below. CPU CODE THAT INVOKES THE GPU CODE AND USES BOTH GLOBAL AND LOCAL THREAD SPACES! GPU CODE THAT IS ACCELERATED WITHOUT Continue ReadingGPU OpenCL Fine-Tuning Problem Solution
Hi, This video was recorded today and shows my Ph.D. first year of study effects in detail. The first on the planet… Multi-GPU & Multi-SET image classification pattern… so, I wish you a happy watch! Thanks for watching! p ;).