Something went wrong with running training network

[heavennew]

Hi ziye，
I have some problem in binning with comebin. The error information is below. Can you help me to fix it?

Running getting representation.
2025-03-05 22:24:53,750 - train
2025-03-05 22:24:53,811 - Generate features for the data.
Traceback (most recent call last):
File "main.py", line 369, in
main()
File "main.py", line 289, in main
train_CLmodel(logger,args)
File "/data/.conda/envs/comebin_env/bin/COMEBin/train_CLmodel.py", line 40, in train_CLmodel
args.cov_minmaxnormalize, args.cov_standardization,args.addvars,args.vars_sqrt, args.kmer_l2_normalize, args.kmerMetric_notl2normalize)
File "/data/.conda/envs/comebin_env/bin/COMEBin/get_augfeature.py", line 155, in get_ContrastiveLearningDataset
dataset, namelist = get_kmer_coverage(data_path, n_views, kmer_model_path, device, nokmer, cov_meannormalize, cov_minmaxnormalize, cov_standardization,addvars,vars_sqrt,kmer_l2_normalize,kmerMetric_notl2normalize)
File "/data/.conda/envs/comebin_env/bin/COMEBin/get_augfeature.py", line 108, in get_kmer_coverage
covMats = covMats / covMats.max(axis=0)[None, :]
File "/data/.conda/envs/comebin_env/lib/python3.7/site-packages/numpy/core/_methods.py", line 39, in _amax
return umr_maximum(a, axis, None, out, keepdims, initial, where)
ValueError: zero-size array to reduction operation maximum which has no identity
Something went wrong with running training network. Exiting.

[mianlee]

I had the similar errors:

Running getting representation.
2025-04-19 23:02:24,721 - train
2025-04-19 23:02:24,769 - Generate features for the data.
0it [00:00, ?it/s]
Traceback (most recent call last):
File "main.py", line 369, in
main()
File "main.py", line 289, in main
train_CLmodel(logger,args)
File "/mnt/data/home/mli/Desktop/Software/COMEBin-1.0.4/COMEBin/train_CLmodel.py", line 236, in train_CLmodel
simclr.train_addpretrain(train_loader, dataset, namelist)
File "/mnt/data/home/mli/Desktop/Software/COMEBin-1.0.4/COMEBin/simclr.py", line 300, in train_addpretrain
top1, top5 = accuracy(logits, labels, topk=(1, 5))
UnboundLocalError: local variable 'logits' referenced before assignment
Something went wrong with running training network. Exiting.

[jtclaypool]

@mianlee - see #4 to see if that solves your issue

[mianlee]

@jtclaypool Thank you for your reply! I tried both but still didn't work !

[mkellom]

Getting same error as @heavennew :

Running getting representation.
2025-09-07 03:29:39,654 - train
2025-09-07 03:29:39,691 - Generate features for the data.
Traceback (most recent call last):
File "main.py", line 369, in
main()
File "main.py", line 289, in main
train_CLmodel(logger,args)
File "/homes/mkellom/.micromamba/envs/comebin_env/bin/COMEBin/train_CLmodel.py", line 40, in train_CLmodel
args.cov_minmaxnormalize, args.cov_standardization,args.addvars,args.vars_sqrt, args.kmer_l2_normalize, args.kmerMetric_notl2normalize)
File "/homes/mkellom/.micromamba/envs/comebin_env/bin/COMEBin/get_augfeature.py", line 155, in get_ContrastiveLearningDataset
dataset, namelist = get_kmer_coverage(data_path, n_views, kmer_model_path, device, nokmer, cov_meannormalize, cov_minmaxnormalize, cov_standardization,addvars,vars_sqrt,kmer_l2_normalize,kmerMetric_notl2normalize)
File "/homes/mkellom/.micromamba/envs/comebin_env/bin/COMEBin/get_augfeature.py", line 108, in get_kmer_coverage
covMats = covMats / covMats.max(axis=0)[None, :]
File "/homes/mkellom/.micromamba/envs/comebin_env/lib/python3.7/site-packages/numpy/core/_methods.py", line 39, in _amax
return umr_maximum(a, axis, None, out, keepdims, initial, where)
ValueError: zero-size array to reduction operation maximum which has no identity
Something went wrong with running training network. Exiting.