mirror of
https://github.com/wassname/Castor.git
synced 2026-09-09 11:13:20 +08:00
16 lines
547 B
Python
16 lines
547 B
Python
from torchtext import data
|
|
import os
|
|
|
|
|
|
class SST1Dataset(data.TabularDataset):
|
|
dirname = 'data'
|
|
@classmethod
|
|
def splits(cls, text_field, label_field,
|
|
train='phrases.train.tsv', validation='dev.tsv', test='test.tsv'):
|
|
prefix_name = 'stsa.fine.'
|
|
path = './data'
|
|
return super(SST1Dataset, cls).splits(
|
|
path, train=prefix_name + train, validation=prefix_name + validation, test=prefix_name + test,
|
|
format='TSV', fields=[('label', label_field), ('text', text_field)]
|
|
)
|