mirror of
https://github.com/modelscope/modelscope.git
synced 2025-12-23 03:29:27 +01:00
eb3209a79a
chinese word segmentation
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/9051491
* add word segmentation
* Merge branch 'master' of http://gitlab.alibaba-inc.com/Ali-MaaS/MaaS-lib
* test with model hub
* merge with master
* update some description and test levels
* adding purge logic in test
* merge with master
* update variables definition
* generic word segmentation model as token classification model
* add output check
63 lines
2.5 KiB
Python
63 lines
2.5 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import shutil
|
|
import unittest
|
|
|
|
from maas_hub.snapshot_download import snapshot_download
|
|
|
|
from modelscope.models import Model
|
|
from modelscope.models.nlp import StructBertForTokenClassification
|
|
from modelscope.pipelines import WordSegmentationPipeline, pipeline
|
|
from modelscope.preprocessors import TokenClassifcationPreprocessor
|
|
from modelscope.utils.constant import Tasks
|
|
from modelscope.utils.hub import get_model_cache_dir
|
|
from modelscope.utils.test_utils import test_level
|
|
|
|
|
|
class WordSegmentationTest(unittest.TestCase):
|
|
model_id = 'damo/nlp_structbert_word-segmentation_chinese-base'
|
|
sentence = '今天天气不错，适合出去游玩'
|
|
|
|
def setUp(self) -> None:
|
|
# switch to False if downloading everytime is not desired
|
|
purge_cache = True
|
|
if purge_cache:
|
|
shutil.rmtree(
|
|
get_model_cache_dir(self.model_id), ignore_errors=True)
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_by_direct_model_download(self):
|
|
cache_path = snapshot_download(self.model_id)
|
|
tokenizer = TokenClassifcationPreprocessor(cache_path)
|
|
model = StructBertForTokenClassification(
|
|
cache_path, tokenizer=tokenizer)
|
|
pipeline1 = WordSegmentationPipeline(model, preprocessor=tokenizer)
|
|
pipeline2 = pipeline(
|
|
Tasks.word_segmentation, 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_with_model_from_modelhub(self):
|
|
model = Model.from_pretrained(self.model_id)
|
|
tokenizer = TokenClassifcationPreprocessor(model.model_dir)
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.word_segmentation, model=model, preprocessor=tokenizer)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_run_with_model_name(self):
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.word_segmentation, model=self.model_id)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_run_with_default_model(self):
|
|
pipeline_ins = pipeline(task=Tasks.word_segmentation)
|
|
print(pipeline_ins(input=self.sentence))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|