Zhantao Yang

> @seermer thanks for the PR! I reviewed it and your new function seems to do the same as our existing function here: > > https://github.com/ultralytics/yolov5/blob/08c8c3e00a1b0fc7f03a7e76ca3cbf7a0d8542ae/utils/general.py#L654-L671 > > Would it...

@glenn-jocher Hello sir, I have just refactored the code so that the computation for counting samples will only perform once. However, the functions calculating pos_weight and class_weight are still separate...

> @seermer looks better now! Have you tried training to see how this affects the results? sorry, I don't have sufficient resources to train on any decent dataset right now,...

> Fixed it by playing around with `gpu_memory_utilisation`. Realized that lm_eval uses GPU memory that is left in addition to what vLLM instance uses. Manually calculated my vLLM instance memory...

> Hello, thank you for your feedback. Could you please provide the code you run? Because following the readme code, I can run this model on multiple GPUs. I can't...