TypeError: Expected fp16 but received torch.float32

[Saranya-nanobiophotonics-lab]

Hello, I tried using Bonito for basecalling. Following command was used "bonito basecaller [email protected] test/fast5 > test/data.bam"

OUTPUT

reading fast5 outputting unaligned bam loading model [email protected] calling: 0 reads [00:00, ? reads/s]Exception in thread Thread-7:
Traceback (most recent call last): File "/usr/lib/python3.9/threading.py", line 954, in _bootstrap_inner self.run() File "/home/saranya/.local/lib/python3.9/site-packages/bonito/multiprocessing.py", line 110, in run for item in self.iterator: File "/home/saranya/.local/lib/python3.9/site-packages/bonito/crf/basecall.py", line 69, in (read, compute_scores(model, batch, reverse=reverse)) for read, batch in batches File "/home/saranya/.local/lib/python3.9/site-packages/bonito/crf/basecall.py", line 37, in compute_scores sequence, qstring, moves = beam_search( File "/home/saranya/.local/lib/python3.9/site-packages/koi/decode.py", line 13, in beam_search raise TypeError('Expected fp16 but received %s' % scores.dtype) TypeError: Expected fp16 but received torch.float32

I am getting the following error "TypeError: Expected fp16 but received torch.float32".

Could you please help me

Saranya

[N0toriou5]

I had the same issue by running Bonito on a NVIDIA GTX 1050 Ti 4 GB. Upgrading to a RTX 3080 10 GB just solved the issue.

[Saranya-nanobiophotonics-lab]

Ok @N0toriou5 . I am currently using NVIDIA GTX 1050 Ti 4 GB.

[Saranya-nanobiophotonics-lab]

@iiSeymour could you please comment whether we can run BONITO using NVIDIA GTX 1050 Ti 4 GB.

[iiSeymour]

@Saranya-nanobiophotonics-lab GTX 1050 is a pascal card and bonito depends on volta or above.

[Saranya-nanobiophotonics-lab]

@iiSeymour Thanks for your response. Now we are using NVIDIA GeForce RTX 2070. I was able to run the base calling successfully, but unable to train model. Please find the error message in the image attached.