TypeError: get_predictions() got an unexpected keyword argument 'input_path'
Hi, I tried to run seqweaver on .fa input with the following Selene yml:
ops: [analyze] model: { path: /lustre/home/acct-bmelgn/bmelgn-3/deepsea/models/seqweaver/seqweaver.py, class: Seqweaver, class_args: { n_classes: 217 } } analyze_sequences: !obj:selene_sdk.predict.AnalyzeSequences { trained_model_path: /lustre/home/acct-bmelgn/bmelgn-3/deepsea/models/seqweaver/human_seqweaver.pth, sequence_length: 1000, features: !obj:selene_sdk.utils.load_features_list { input_path: /lustre/home/acct-bmelgn/bmelgn-3/deepsea/models/seqweaver/data.hg19.colnames }, batch_size: 128, use_cuda: False, write_mem_limit: 5000
} prediction: { output_format: hdf5 } random_seed: 123 ...
and when i ran run_config("configs/seqs_fasta.yml"), I got:
Traceback (most recent call last): File "fasta_cli.py", line 44, in
run_config("configs/seqs_fasta.yml") File "fasta_cli.py", line 42, in run_config parse_configs_and_run(configs) File "/lustre/home/acct-bmelgn/bmelgn-3/miniconda3/envs/deepsea/lib/python3.6/site-packages/selene_sdk/utils/config_utils.py", line 341, in parse_configs_and_run execute(operations, configs, current_run_output_dir) File "/lustre/home/acct-bmelgn/bmelgn-3/miniconda3/envs/deepsea/lib/python3.6/site-packages/selene_sdk/utils/config_utils.py", line 247, in execute analyze_seqs.get_predictions(**predict_info) TypeError: get_predictions() got an unexpected keyword argument 'input_path'
I think input_path is a necessary parameter in selene, and I have no idea why it said it was unexpected. Do you have any suggestion on this issue? Thank you very much for your help.