CWYuan08

Hi @jamesc99, did you manage to resolve this problem? I have the same issue... Thank you!

@yanchunzhang @iiSeymour hi I am having the exact same issue here, it got reduced from above 10 to around 5. My median read length is ~550, N50=730. I also tried...

@yanchunzhang @iiSeymour hi I am having the exact same issue here, it got reduced from above 10 to around 5. My median read length is ~550, N50=730. I also tried...

Hi @mbhall88 and @menickname, I am experiencing the exact same problem, do you have any update on this issue? any progress/experience will be greatly appreciated. Thank you very much!

Thank you @mbhall88 for sharing your update, sorry to hear you had to stop there.

Hi @aistBMRG, I am wondering how to update the headers of the bonito fastq with runID=information, could you please share your method? Thank you very much!

Hi I have changed export 'PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:100’ and export 'CUDA_LAUNCH_BLOCKING=1’, but I am still getting "RuntimeError: CUDA error: out of memory", do I need to change anything in the serialization.py file?...

The GPU we are trying to run it on is an Nvidia A4000 with 16GB of VRAM.

This post: https://github.com/nanoporetech/bonito/issues/247 solved my problem