MCPcopy Create free account
hub / github.com/MichSchli/AVeriTeC / setup

Method setup

data_loaders/DualEncoderDataLoader.py:144–149  ·  view source on GitHub ↗
(self, stage)

Source from the content-addressed store, hash-verified

142
143 # encode the sentences using the tokenizer
144 def setup(self, stage):
145 self.train = self.encode_sentences(self.train['positives'], self.train['negatives'])
146
147 self.validate = self.encode_sentences(self.validate['positives'], self.validate['negatives'])
148
149 self.test = self.encode_sentences(self.test['positives'], self.test['negatives'])
150
151 # Load the training, validation and test sets in Pytorch Dataset objects
152 def train_dataloader(self):

Callers

nothing calls this directly

Calls 1

encode_sentencesMethod · 0.95

Tested by

no test coverage detected