File size: 1,983 Bytes
1a7ab88 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import numpy as np
from transformers import Pipeline
def softmax(outputs):
maxes = np.max(outputs, axis=-1, keepdims=True)
shifted_exp = np.exp(outputs - maxes)
return shifted_exp / shifted_exp.sum(axis=-1, keepdims=True)
class PairClassificationPipeline(Pipeline):
def _sanitize_parameters(self, **kwargs):
preprocess_kwargs = {}
if "second_text" in kwargs:
preprocess_kwargs["second_text"] = kwargs["second_text"]
return preprocess_kwargs, {}, {}
def preprocess(self, text, second_text=None):
return self.tokenizer(text,
text_pair=second_text,
return_tensors=self.framework)
def _forward(self, model_inputs):
return self.model(**model_inputs)
def postprocess(self, model_outputs):
logits = model_outputs.logits[0].numpy()
probabilities = softmax(logits)
best_class = np.argmax(probabilities)
label = self.model.config.id2label[best_class]
score = probabilities[best_class].item()
logits = logits.tolist()
return {"label": label, "score": score, "logits": logits}
from transformers.pipelines import PIPELINE_REGISTRY
from transformers import AutoModelForSequenceClassification, TFAutoModelForSequenceClassification
if __name__ == "__main__":
PIPELINE_REGISTRY.register_pipeline(
"pair-classification",
pipeline_class=PairClassificationPipeline,
pt_model=AutoModelForSequenceClassification,
tf_model=TFAutoModelForSequenceClassification,
)
from transformers import pipeline
classifier = pipeline("pair-classification",
model="sgugger/finetuned-bert-mrpc")
from huggingface_hub import Repository
repo = Repository("test-dynamic-pipeline",
clone_from="paulhindemith/test-dynamic-pipeline")
classifier.save_pretrained("test-dynamic-pipeline")
repo.push_to_hub() |