#!/opt/conda/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from tape.main import run_train
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(run_train())
"""
This file is used for calling run_train() in main.py
"""
from tape import main
main.run_train()
This takes in a list of outputs from the dataset's __getitem__
method. You can use the `pad_sequences` helper function to pad
a list of numpy arrays.
"""
input_ids, input_mask, ss_label = tuple(zip(*batch))
input_ids = torch.from_numpy(pad_sequences(input_ids, 0))
input_mask = torch.from_numpy(pad_sequences(input_mask, 0))
ss_label = torch.from_numpy(pad_sequences(ss_label, -1))
output = {
'input_ids': input_ids,
'input_mask': input_mask,
'targets': ss_label
}
return output
registry.register_task_model('secondary_structure_8', 'transformer',
ProteinBertForSequenceToSequenceClassification)
if __name__ == '__main__':
""" To actually run the task, you can do one of two things. You can
simply import the appropriate run function from tape.main. The
possible functions are `run_train`, `run_train_distributed`, and
`run_eval`. Alternatively, you can add this dataset directly to
tape/datasets.py.
"""
from tape.main import run_train
run_train()