data2vec
copied
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions
27 lines
1.1 KiB
27 lines
1.1 KiB
# Copyright 2021 Zilliz. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import numpy
|
|
import torch
|
|
from transformers import RobertaTokenizer, Data2VecTextModel
|
|
from towhee.operator.base import NNOperator
|
|
|
|
class Data2VecText(NNOperator):
|
|
def __init__(self, model_name):
|
|
self.model = Data2VecTextModel.from_pretrained(model_name)
|
|
self.tokenizer = RobertaTokenizer.from_pretrained(model_name)
|
|
|
|
def __call__(self, text: str) -> numpy.ndarray:
|
|
inputs = self.tokenizer(text, return_tensors="pt")
|
|
outputs = self.model(**inputs)
|
|
return outputs.pooler_output.detach().cpu().numpy().flatten()
|