Patrick Bohn

I have tried reducing the values to 24 and 200,000 respectively, but alas that still gave the same error. I then decreased batchsize further down to 1 and split_read_length to...

Hi @vellamike , Thank you for clearing that up for me, my mistake. I have now tried this: 1) Install cuda-11-0 package via apt 2) Install local cuda-toolkit 11.0 3)...

Okay, the second error was indeed due to these lines, I removed them and the nvrtc error is not appearing anymore. However, now I am seeing the previous error again:...

Hi, sorry for the late reply, it took a lot of time to install pytorch via conda (seems like their servers to Germany are very slow). In brief, creating a...

Hi @vellamike , I did change the basecall.py settings to reduce the batchsize and split_read_length (with setting batchsize down to 1), however the error persists. (Notably, but possibly unrelated) as...

@vellamike Thanks for the link. I wonder whether it has something to do with my fast5 files, which contain a much larger number of reads (~400,000). Will try with a...

Ah, thank you for the quick response. I extracted the tuple by reading in the tombo.index dictionary pickle, then got the values using my reference_name key, and there took the...

Hi, I can confirm that updating to a newer version of SingularityCE (as far as I'm aware the newest vagrantbox version was 3.9 at the time of trying) fixed my...

Thank you for pointing me to the right place, I'm currently trying to implement it myself in this fork: https://github.com/hasindu2008/f5c/compare/master...patbohn:f5c_filter_signal:master

Thank you for your input, I see your points and implemented it as a separate loop now. Also I think I fixed the rare issue with not filtering when having...