nanoporetech / bonito

A PyTorch Basecaller for Oxford Nanopore Reads
https://nanoporetech.com/
Other
389 stars 120 forks source link

training dataset #125

Open visanuwan opened 3 years ago

visanuwan commented 3 years ago

I have an issue using the pre-prepared dataset from the command provided in the README.md

$ bonito download --training
$ bonito train --amp /data/training/model-dir

I have successfully downloaded the dna_r9.4.1.hdf5 However, I got an error after running the second command. Could you please guide me? The error message is as follows:

(venv3) c1701:visanu:~/tools/bonito/bonito$ bonito train --amp test_train
[loading data]
Traceback (most recent call last):
  File "/scrfs/storage/visanu/home/tools/bonito/venv3/bin/bonito", line 11, in <module>
    load_entry_point('ont-bonito', 'console_scripts', 'bonito')()
  File "/scrfs/storage/visanu/home/tools/bonito/bonito/__init__.py", line 39, in main
    args.func(args)
  File "/scrfs/storage/visanu/home/tools/bonito/bonito/cli/train.py", line 36, in main
    train_data = load_data(limit=args.chunks, directory=args.directory)
  File "/scrfs/storage/visanu/home/tools/bonito/bonito/util.py", line 220, in load_data
    chunks = np.load(os.path.join(directory, "chunks.npy"), mmap_mode='r')
  File "/scrfs/storage/visanu/home/tools/bonito/venv3/lib/python3.7/site-packages/numpy/lib/npyio.py", line 417, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '/scrfs/storage/visanu/home/tools/bonito/bonito/data/dna_r9.4.1/chunks.npy'
iiSeymour commented 3 years ago

Hey @visanuwan

You can specify the location of the training data with --directory

$ bonito train --amp /data/training/model-dir --directory /data/training/training-data-dir