mirror of
https://github.com/modelscope/modelscope.git
synced 2025-12-22 19:19:21 +01:00
d721fabb34
1.新增支持原始bert模型（非easynlp的 backbone prefix版本）
2.支持bert的在sequence classification/fill mask /token classification上的backbone head形式
3.统一了sequence classification几个任务的pipeline到一个类
4.fill mask 支持backbone head形式
5.token classification的几个子任务（ner，word seg， part of speech）的preprocessor 统一到了一起TokenClassificationPreprocessor
6. sequence classification的几个子任务（single classification， pair classification）的preprocessor 统一到了一起SequenceClassificationPreprocessor
7. 改动register中 cls的group_key 赋值位置，之前的group_key在多个decorators的情况下，会被覆盖，obj_cls的group_key信息不正确
8. 基于backbone head形式将 原本group_key和 module同名的情况尝试做调整，如下在modelscope/pipelines/nlp/sequence_classification_pipeline.py 中
原本
@PIPELINES.register_module(
Tasks.sentiment_classification, module_name=Pipelines.sentiment_classification)
改成
@PIPELINES.register_module(
Tasks.text_classification, module_name=Pipelines.sentiment_classification)
相应的configuration.json也有改动，这样的改动更符合任务和pipline（子任务）的关系。
8. 其他相应改动为支持上述功能
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/10041463
104 lines
4.5 KiB
Python
104 lines
4.5 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import unittest
|
|
|
|
from modelscope.hub.snapshot_download import snapshot_download
|
|
from modelscope.models import Model
|
|
from modelscope.models.nlp import (LSTMCRFForNamedEntityRecognition,
|
|
TransformerCRFForNamedEntityRecognition)
|
|
from modelscope.pipelines import pipeline
|
|
from modelscope.pipelines.nlp import NamedEntityRecognitionPipeline
|
|
from modelscope.preprocessors import TokenClassificationPreprocessor
|
|
from modelscope.utils.constant import Tasks
|
|
from modelscope.utils.demo_utils import DemoCompatibilityCheck
|
|
from modelscope.utils.test_utils import test_level
|
|
|
|
|
|
class NamedEntityRecognitionTest(unittest.TestCase, DemoCompatibilityCheck):
|
|
|
|
def setUp(self) -> None:
|
|
self.task = Tasks.named_entity_recognition
|
|
self.model_id = 'damo/nlp_raner_named-entity-recognition_chinese-base-news'
|
|
|
|
tcrf_model_id = 'damo/nlp_raner_named-entity-recognition_chinese-base-news'
|
|
lcrf_model_id = 'damo/nlp_lstm_named-entity-recognition_chinese-news'
|
|
sentence = '这与温岭市新河镇的一个神秘的传说有关。'
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_tcrf_by_direct_model_download(self):
|
|
cache_path = snapshot_download(self.tcrf_model_id)
|
|
tokenizer = TokenClassificationPreprocessor(cache_path)
|
|
model = TransformerCRFForNamedEntityRecognition(
|
|
cache_path, tokenizer=tokenizer)
|
|
pipeline1 = NamedEntityRecognitionPipeline(
|
|
model, preprocessor=tokenizer)
|
|
pipeline2 = pipeline(
|
|
Tasks.named_entity_recognition,
|
|
model=model,
|
|
preprocessor=tokenizer)
|
|
print(f'sentence: {self.sentence}\n'
|
|
f'pipeline1:{pipeline1(input=self.sentence)}')
|
|
print()
|
|
print(f'pipeline2: {pipeline2(input=self.sentence)}')
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_lcrf_by_direct_model_download(self):
|
|
cache_path = snapshot_download(self.lcrf_model_id)
|
|
tokenizer = TokenClassificationPreprocessor(cache_path)
|
|
model = LSTMCRFForNamedEntityRecognition(
|
|
cache_path, tokenizer=tokenizer)
|
|
pipeline1 = NamedEntityRecognitionPipeline(
|
|
model, preprocessor=tokenizer)
|
|
pipeline2 = pipeline(
|
|
Tasks.named_entity_recognition,
|
|
model=model,
|
|
preprocessor=tokenizer)
|
|
print(f'sentence: {self.sentence}\n'
|
|
f'pipeline1:{pipeline1(input=self.sentence)}')
|
|
print()
|
|
print(f'pipeline2: {pipeline2(input=self.sentence)}')
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_run_tcrf_with_model_from_modelhub(self):
|
|
model = Model.from_pretrained(self.tcrf_model_id)
|
|
tokenizer = TokenClassificationPreprocessor(model.model_dir)
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.named_entity_recognition,
|
|
model=model,
|
|
preprocessor=tokenizer)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_lcrf_with_model_from_modelhub(self):
|
|
model = Model.from_pretrained(self.lcrf_model_id)
|
|
tokenizer = TokenClassificationPreprocessor(model.model_dir)
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.named_entity_recognition,
|
|
model=model,
|
|
preprocessor=tokenizer)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 1, 'skip test in current test level')
|
|
def test_run_tcrf_with_model_name(self):
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.named_entity_recognition, model=self.tcrf_model_id)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_lcrf_with_model_name(self):
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.named_entity_recognition, model=self.lcrf_model_id)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_with_default_model(self):
|
|
pipeline_ins = pipeline(task=Tasks.named_entity_recognition)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skip('demo compatibility test is only enabled on a needed-basis')
|
|
def test_demo_compatibility(self):
|
|
self.compatibility_check()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|