Chris Seymour

Oh sorry, @noncodo I just realised you are after multi-gpu inference, not training! That will be a little more complicated as the fast5 reader, decoder and fasta writer sit in...

Be good to know more about why `bonito download --models` is failing but sure, the URLs are all [here](https://github.com/nanoporetech/bonito/blob/master/bonito/cli/download.py#L80). ```bash $ wget -q https://nanoporetech.box.com/shared/static/uetgwsnb8yfqvuyoka8p09mxilgskqc7.zip # [email protected] $ unzip uetgwsnb8yfqvuyoka8p09mxilgskqc7.zip Archive:...

@colindaven are you working under a virtualenv? Can you check which installation your `bonito` command is associated with by running `which bonito`. If you ran `python setup.py develop` under `/mnt/ngsnfs/tools/bonito/`...

@marcpaga no, the 66K R9.4.1 reads are mainly provided as a baseline for anybody interested in method development.

Hey @addyblanch The converter expects a top level key `Reads` can your file in Python with - ```python >>> import h5py >>> f = h5py.File('HQ_mapped.hdf5', 'r') >>> list(f.keys()) ['Reads'] ```

Was `HQ_mapped.hdf5` output by `prepare_mapped_reads.py` because you should have ended up with hdf5 file like [this](https://github.com/nanoporetech/taiyaki/blob/master/docs/FILE_FORMATS.md)?

Which version of Taiyaki are you using @addyblanch?

@dberma15 `sample_id` isn't treated as optional in bonito. Are you seeing issues with this?

Hey @devonorourke You can absolutely skip training your own model and start out with the provided `dna_r9.4.1` model. I'd start with only a fraction of reads for training as you...

Here is perfect. You shouldn't have to tweak any settings to get good performance with Bonito. That's extremely slow _(~30X slower than a V100)_ what GPU do you have?