Training step problem

[heavennew]

Hello,

I had a problem when I did the multi-sample binning. The error information is below，

2024-05-28 00:44:40 localhost.localdomain SemiBin[102770] INFO Setting number of CPUs to 64
2024-05-28 00:44:40 localhost.localdomain SemiBin[102770] INFO Binning for short_read
2024-05-28 00:44:40 localhost.localdomain SemiBin[102770] INFO SemiBin will run in self supervised mode
2024-05-28 00:44:55 localhost.localdomain SemiBin[102770] INFO Did not detect GPU, using CPU.
2024-05-28 00:44:55 localhost.localdomain SemiBin[102770] INFO Performing multi-sample binning
2024-05-28 00:44:55 localhost.localdomain SemiBin[102770] INFO Generating training data...
2024-05-28 00:47:01 localhost.localdomain SemiBin[102770] INFO Calculating coverage for every sample.
2024-05-28 02:03:22 localhost.localdomain SemiBin[102770] INFO Processed: 1_sample.mapped.sorted.bam
2024-05-28 02:03:22 localhost.localdomain SemiBin[102770] INFO Processed: 2_sample.mapped.sorted.bam
2024-05-28 02:38:16 localhost.localdomain SemiBin[102770] INFO Training model and clustering for L1_contig_1000@L1.
2024-05-28 02:38:16 localhost.localdomain SemiBin[102770] INFO Start training from a single sample.
2024-05-28 02:38:31 localhost.localdomain SemiBin[102770] INFO Training model...
^M 0%| | 0/15 [00:00<?, ?it/s]^M 0%| | 0/15 [00:30<?, ?it/s]
Traceback (most recent call last):
File "/data/ang/.conda/envs/SemiBin2/bin/SemiBin2", line 10, in
sys.exit(main2())
^^^^^^^
File "/data/ang/.conda/envs/SemiBin2/lib/python3.12/site-packages/SemiBin/main.py", line 1610, in main2
multi_easy_binning(
File "/data/ang/.conda/envs/SemiBin2/lib/python3.12/site-packages/SemiBin/main.py", line 1349, in multi_easy_binning
training(logger, None, args.num_process,
File "/data/ang/.conda/envs/SemiBin2/lib/python3.12/site-packages/SemiBin/main.py", line 1126, in training
model = train_self(logger,
^^^^^^^^^^^^^^^^^^
File "/data/ang/.conda/envs/SemiBin2/lib/python3.12/site-packages/SemiBin/self_supervised_model.py", line 108, in train_self
dataset = feature_Dataset(train_input_1, train_input_2, train_labels)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data/ang/.conda/envs/SemiBin2/lib/python3.12/site-packages/SemiBin/semi_supervised_model.py", line 120, in init
assert len(embedding1) == len(embedding2)
AssertionError

Do you know how to fix it?

[luispedro]

Thanks for the report.

Can you tell us what was the command that you ran?

[heavennew]

the command:
SemiBin multi_easy_bin -i concatenated.fa.gz -b *sample.mapped.sorted.bam -o easy_multi_sample_output --ml-threshold 30