Chris Seymour

Hey @fernanarr does your device have an Nvidia GPU in it?

@fernanarr are you sure you have at least one `*.fast5` file in `/data/reads` - bonito is reporting 0 reads found? If your fast5 file is not directly in the folder...

@dkurt first hurdle - have you seen this? ```bash /tmp/test$ python3.8 -m venv venv3.8 /tmp/test$ source venv3.8/bin/activate (venv3.8) /tmp/test$ pip install --upgrade pip Collecting pip Downloading https://files.pythonhosted.org/packages/a4/6d/6463d49a933f547439d6b5b98b46af8742cc03ae83543e4d7688c2420f8b/pip-21.3.1-py3-none-any.whl (1.7MB) |████████████████████████████████| 1.7MB...

Yes, that has resolved it @dkurt. Basecalling results are now correct for the CRF models but I'm finding the performance much slower than expected even with the smaller models _(note:...

Thanks @dkurt let me know if there is any progress w.r.t LSTM performance.

How are you measuring CPU usage here, what are you running specifically and are you targeting a GPU or CPU?

You should not see high activity on all the cores - what about if you set `export OMP_NUM_THREADS=1` before running basecalling? Yes, the bonito models on rerio should outperform the...

@madhubioinfo which version of bonito do you have installed _(you can check with `bonito -v`)_? It looks like you might have an old version. Are you able to update to...

All versions can be installed with pip and you can upgrade with: ``` $ pip install --upgrade ont-bonito ```

Can you try upgrading pip first - ``` $ pip install --upgrade pip $ pip install --upgrade ont-bonito ```