No fasta file input argument in co-assembly binning using SemiBin2 train_self

[Ijingyuliu]

Error output:
SemiBin2: error: unrecognized arguments: -i AU_KOA_F_contig.fa
By running
SemiBin2 train_self -h
the output contains no -i comand, while in the tutoriols, https://semibin.readthedocs.io/en/latest/usage/, it has the -i fasta input in example for Advanced co-assembly binning workflows, I wondered which one is correct, and do I need to input the contig files for the model training in co-assembly?

Tutorials

SemiBin2 train_self \ -i contig.fa \ --data contig_output/data.csv \ --data-split contig_output/data_split.csv \ -o contig_output

Output

usage: SemiBin2 train_self [-h] --data [DATA ...] --data-split [DATA_SPLIT ...] -o OUTPUT [--batch-size BATCHSIZE] [--train-from-many | --no-train-from-many] [--epochs EPOCHES] [--tmpdir TMPDIR] [-p] [--verbose | --quiet] [--random-seed RANDOM_SEED]
                           [--engine ENGINE]

options:
  -h, --help            show this help message and exit
  --batch-size BATCHSIZE
                        Batch size used in the training process (Default: 2048).
  --train-from-many, --no-train-from-many
                        Train the model with several samples. You must provide data, data_split, cannot, and fasta files for corresponding samples in the same order. Note: You can only use `--train-from-many` mode when performing single-sample
                        binning. Training from many samples with multi-sample binning is not supported.
  --epochs EPOCHES, --epoches EPOCHES
                        Number of epochs used in the training process (Default: 15).
  --tmpdir TMPDIR       option to set temporary directory
  -p , --processes , -t , --threads 
                        Number of CPUs used (pass the value 0 to use all CPUs, default: 0)
  --verbose             Verbose output
  --quiet, -q           Quiet output
  --random-seed RANDOM_SEED
                        Random seed. Set it to a fixed value to reproduce results across runs. The default is that the seed is set by the system and .
  --engine ENGINE       device used to train the model (auto/gpu/cpu, auto means if SemiBin detects the gpu, SemiBin will use GPU)

Mandatory arguments:
  --data [DATA ...]     Path to the input data.csv file.
  --data-split [DATA_SPLIT ...]
                        Path to the input data_split.csv file.
  -o OUTPUT, --output OUTPUT
                        Output directory (will be created if non-existent)