class ModelInput(_EncoderPairwiseModel.Config.ModelInput):
tokens1: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128
)
tokens2: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128
)
class ModelInput(ModelInputBase):
tokens1: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text1"], max_seq_len=128)
tokens2: BERTTensorizerBase.Config = BERTTensorizer.Config(
columns=["text2"], max_seq_len=128)
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens1", "tokens2"], indexes=[2, 2])
class BertModelInput(BaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(max_seq_len=128)
dense: Optional[FloatListTensorizer.Config] = None
labels: LabelTensorizer.Config = LabelTensorizer.Config()
# for metric reporter
num_tokens: NtokensTensorizer.Config = NtokensTensorizer.Config(
names=["tokens"], indexes=[2]
)
class Config(DocumentClassificationTask.Config):
model: NewBertModel.Config = NewBertModel.Config(
inputs=NewBertModel.Config.BertModelInput(
tokens=BERTTensorizer.Config(columns=["text1", "text2"],
max_seq_len=128)))
metric_reporter: ClassificationMetricReporter.Config = (
ClassificationMetricReporter.Config(
text_column_names=["text1", "text2"]))
def test_bert_pair_tensorizer(self):
sentences = ["Focus", "Driving School"]
expected_tokens = [101, 175, 287, 766, 462, 102, 100, 379, 102]
expected_segment_labels = [0, 0, 0, 0, 0, 0, 1, 1, 1]
row = {"text1": sentences[0], "text2": sentences[1]}
tensorizer = BERTTensorizer.from_config(
BERTTensorizer.Config(
columns=["text1", "text2"],
tokenizer=WordPieceTokenizer.Config(
wordpiece_vocab_path=
"pytext/data/test/data/wordpiece_1k.txt"),
))
tokens, segment_labels, seq_len = tensorizer.numberize(row)
self.assertEqual(tokens, expected_tokens)
self.assertEqual(segment_labels, expected_segment_labels)
self.assertEqual(seq_len, len(expected_tokens))
class BertModelInput(_EncoderBaseModel.Config.ModelInput):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(max_seq_len=128)
def test_bert_tensorizer(self):
sentence = "<SOS> Focus Driving School Mulungushi bus station along Kasuba road, wamkopeka building. Ndola, Zambia."
# expected result was obtained offline by running BertModelDataHandler
expected = [
101,
133,
278,
217,
135,
175,
287,
766,
462,
100,
379,
182,
459,
334,
459,
280,
504,
462,
425,
283,
171,
462,
567,
474,
180,
262,
217,
459,
931,
262,
913,
117,
192,
262,
407,
478,
287,
744,
263,
478,
262,
560,
119,
183,
282,
287,
843,
117,
195,
262,
407,
931,
566,
119,
102,
]
row = {"text": sentence}
tensorizer = BERTTensorizer.from_config(
BERTTensorizer.Config(
tokenizer=WordPieceTokenizer.Config(
wordpiece_vocab_path="pytext/data/test/data/wordpiece_1k.txt"
)
)
)
tokens, segment_label, seq_len = tensorizer.numberize(row)
self.assertEqual(tokens, expected)
self.assertEqual(seq_len, len(expected))
self.assertEqual(segment_label, [0] * len(expected))
tokens, pad_mask, segment_labels = tensorizer.tensorize(
[(tokens, segment_label, seq_len)]
)
self.assertEqual(pad_mask[0].tolist(), [1] * len(expected))
class InputConfig(ConfigBase):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(
max_seq_len=128)
class InputConfig(ConfigBase):
tokens: BERTTensorizer.Config = BERTTensorizer.Config(
columns=["text1", "text2"], max_seq_len=128
)
labels: NumericLabelTensorizer.Config = NumericLabelTensorizer.Config()