Burhan

@Koldim2001 hey thanks for your write up. I'll definitely take a look at this when I have a chance, but you should update the license on your repository. Any code...

I will try to get to this sometime soon! Last week was quite busy and I didn't really have time to get back to this. Looks like you've put a...

Any reason not to use `torch.cuda.empty_cache()` at the end of an epoch? On an initial test run (on going) training has proceeded highest than before with OoM error and epoch...

I will see if I can get a benchmark setup that I can share results from in the next week or so, happy to submit a PR if it's worthwhile

@edkazcarlson hey, saw your message in the Discord server. This is an interesting PR to be sure, but I wouldn't be the best person to evaluate it. I did have...

Try using: ```py from ultralytics import YOLO if __name__ == "__main__": model = YOLO("yolov8n.pt") # recommend using pretrained weights to start results = model.train(data="config.yaml", epochs=100) # 1 epoch will not...

@NoNameCanUse9 your labels are not properly formatted, which is why you're getting errors like this: `non-normalized or out of bounds coordinates [ 1.0225]` See the [dataset docs](https://docs.ultralytics.com/datasets/detect/) for guidance on...

@SwEngine like Glenn said, we still plan on releasing these, but other tasks have taken priority. You'll see a notification from this issue when we have more updates 🚀

@Koldim2001 so I know it's been a long time, but I finally got around to looking at your revisions. I went ahead and made a bunch of updates and optimizations...

One additional idea, not sure how feasible it is, but wondering if there could be a more graceful way to terminate the example? Like adding a "Stop" or "Shutdown" example...