search

GoekeLab / m6anet

Detection of m6A from direct RNA-Seq data
https://m6anet.readthedocs.io/
MIT License
103 stars 19 forks source link

Errors while running m6anet-train #26

Closed guowb9 closed 2 years ago

guowb9 commented 2 years ago

Hi, Thanks a lot for developing m6anet! I am trying to run m6anet-train with my own data, and I have extracted features from 2 base pairs flanking the candidate site. I modified 'num_neighboring_features = 2' in m6anet/m6anet/model/configs/model_configs/prod_pooling.toml and m6anet/m6anet/model/configs/training_configs/oversampled.toml. However I got this error

There are 2861 train sites There are 675 val sites There are 785 test sites Traceback (most recent call last): File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/bin/m6anet-train", line 33, in sys.exit(load_entry_point('m6anet==1.0.0', 'console_scripts', 'm6anet-train')()) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/scripts/train.py", line 108, in main File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/scripts/train.py", line 75, in train_and_save File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/utils/training_utils.py", line 38, in train File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/utils/training_utils.py", line 100, in train_one_epoch File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, kwargs) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/model/model.py", line 81, in forward File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/model/model.py", line 66, in get_site_probability File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/model/model.py", line 63, in get_site_representation File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/model/model.py", line 56, in get_read_representation File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, *kwargs) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/container.py", line 141, in forward input = module(input) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(input, kwargs) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/m6anet-1.0.0-py3.9.egg/m6anet/model/model_blocks/blocks.py", line 78, in forward File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/modules/sparse.py", line 158, in forward return F.embedding( File "/home/guowb/software/anaconda/ENTER/envs/machine_learning/lib/python3.9/site-packages/torch/nn/functional.py", line 2044, in embedding return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) IndexError: index out of range in self

Do I need to modify other parameters? Could you give me some suggestions about this issue? Thank you very much!