Flower9618
Flower9618
> Can you load your training data and post the shapes? > > ```python > >>> import os > >>> import numpy as np > >>> directory = "/data/training" >...
> Can you try without `--multi-gpu`? Yes, `chunksize` is important for training and 100 samples is too short Thank you very much. When I try without '--multi-gpu', it works. Why...
Thank you very much for your reply, @iiSeymour . It is really helpful for me.
> Hi @Flower9618 > > Bonito only does a [simple peak detection](https://github.com/nanoporetech/bonito/blob/master/bonito/fast5.py#L136) in signal space to trim the start of each [read](https://github.com/nanoporetech/bonito/blob/master/bonito/fast5.py#L78). No sequence-based trimming is done currently. Thank you...
> Hello. We only store the nonzero entries for the full (nbase + nbase)^2 transition matrix. Every base has a "flip" and a "flop" state, so (nbase + nbase) states...
Hello, I meet the same problem. Do you know what this snp file means? @tahuh .Thank you very much.
@rhpvorderman Thank you so much for your information, which is helpful for me to study these two tools. I am still finding a tool which has a good performance on...
@rhpvorderman Thank you so much for sharing this information. 😊
I see. Thank you so much. I will try this command. In addition, for the ‘modkit repair’ command, both the input and output files must be in BAM format. Is...
Hello, @ArtRand , Thank you so much for your reply. I have molecules that have been modified base-calling by Dorado and saved in a BAM file (with MM,ML tag). Now,...