Hello, I know that many people like my DarkNet on OpenCL. Recently I also made an improved version of the original DarkNet on CUDA, and I called it DarkNet-vNext, and it has all improvements that probably you were looking for. All Yolo models are supported from the 1st to 4th version, it supports OpenCV 4 and, for example, benchmark possibility. The good news it is high-speed. As you probably may know, CUDA performing faster than OpenCL, but OpenCL is more system-ready. For example, recently, I helped someone run an Intel CPU with Intel HD 620 GPU to run OpenCL DarkNet as Convolutional Neural Network, and it worked flawlessly. On the training capability, the CUDA version is the best and the fastest I know. Now on DarkNet-vNext, you may train Yolo4 models, which was impossible before on the original version. And below, you may see changes in statistics.