Error when training the model for single sample binning

[Louis-MG]

Hello ! I just want to check that my reasoning is good. I made my bam files using the documentation, and if sometimes I can obtain mags (or not but due to finding 0 bins), I also encounter this error:

2025-04-07 11:56:51 vls136.compbio.ulaval.ca SemiBin[226229] INFO Calculating coverage for every sample.
2025-04-07 11:56:52 vls136.compbio.ulaval.ca SemiBin[226229] INFO Processed: Paracoccus_alignments//R142A_S10_L001.mapped.sorted.bam
2025-04-07 11:56:52 vls136.compbio.ulaval.ca SemiBin[226229] INFO Start training from a single sample.
2025-04-07 11:56:55 vls136.compbio.ulaval.ca SemiBin[226229] INFO Training model...
  0%|          | 0/15 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/home/guelou01/miniconda3/envs/SemiBin/bin/SemiBin2", line 10, in <module>
    sys.exit(main2())
             ^^^^^^^
  File "/home/guelou01/miniconda3/envs/SemiBin/lib/python3.12/site-packages/SemiBin/main.py", line 1600, in main2
    single_easy_binning(
  File "/home/guelou01/miniconda3/envs/SemiBin/lib/python3.12/site-packages/SemiBin/main.py", line 1279, in single_easy_binning
    training(logger, None,
  File "/home/guelou01/miniconda3/envs/SemiBin/lib/python3.12/site-packages/SemiBin/main.py", line 1126, in training
    model = train_self(logger,
            ^^^^^^^^^^^^^^^^^^
  File "/home/guelou01/miniconda3/envs/SemiBin/lib/python3.12/site-packages/SemiBin/self_supervised_model.py", line 100, in train_self
    train_input_1 = np.concatenate(
                    ^^^^^^^^^^^^^^^
ValueError: all the input array dimensions except for the concatenation axis must match exactly, but along dimension 1, the array at index 0 has size 136 and the array at index 1 has size 0

Is it due to not having enough data (like a very alignment rate) or could it be something else ? I am using 2.1.0 from bioconda, and the reads from the sample were aligned against scaffolds assembled with the same sample only.