mirror of
https://github.com/modelscope/modelscope.git
synced 2025-12-23 03:29:27 +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
68 lines
2.8 KiB
Python
68 lines
2.8 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import unittest
|
|
|
|
import numpy as np
|
|
|
|
from modelscope.hub.snapshot_download import snapshot_download
|
|
from modelscope.models import Model
|
|
from modelscope.models.nlp import FeatureExtractionModel
|
|
from modelscope.outputs import OutputKeys
|
|
from modelscope.pipelines import pipeline
|
|
from modelscope.pipelines.nlp import FeatureExtractionPipeline
|
|
from modelscope.preprocessors import NLPPreprocessor
|
|
from modelscope.utils.constant import Tasks
|
|
from modelscope.utils.demo_utils import DemoCompatibilityCheck
|
|
from modelscope.utils.test_utils import test_level
|
|
|
|
|
|
class FeatureExtractionTaskModelTest(unittest.TestCase,
|
|
DemoCompatibilityCheck):
|
|
|
|
def setUp(self) -> None:
|
|
self.task = Tasks.feature_extraction
|
|
self.model_id = 'damo/pert_feature-extraction_base-test'
|
|
|
|
sentence1 = '测试embedding'
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_with_direct_file_download(self):
|
|
cache_path = snapshot_download(self.model_id)
|
|
tokenizer = NLPPreprocessor(cache_path, padding=False)
|
|
model = FeatureExtractionModel.from_pretrained(self.model_id)
|
|
pipeline1 = FeatureExtractionPipeline(model, preprocessor=tokenizer)
|
|
pipeline2 = pipeline(
|
|
Tasks.feature_extraction, model=model, preprocessor=tokenizer)
|
|
result = pipeline1(input=self.sentence1)
|
|
|
|
print(f'sentence1: {self.sentence1}\n'
|
|
f'pipeline1:{np.shape(result[OutputKeys.TEXT_EMBEDDING])}')
|
|
result = pipeline2(input=self.sentence1)
|
|
print(f'sentence1: {self.sentence1}\n'
|
|
f'pipeline1: {np.shape(result[OutputKeys.TEXT_EMBEDDING])}')
|
|
|
|
@unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
|
|
def test_run_with_model_from_modelhub(self):
|
|
model = Model.from_pretrained(self.model_id)
|
|
tokenizer = NLPPreprocessor(model.model_dir, padding=False)
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.feature_extraction, model=model, preprocessor=tokenizer)
|
|
result = pipeline_ins(input=self.sentence1)
|
|
print(np.shape(result[OutputKeys.TEXT_EMBEDDING]))
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_run_with_model_name(self):
|
|
pipeline_ins = pipeline(
|
|
task=Tasks.feature_extraction, model=self.model_id)
|
|
result = pipeline_ins(input=self.sentence1)
|
|
print(np.shape(result[OutputKeys.TEXT_EMBEDDING]))
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_run_with_default_model(self):
|
|
pipeline_ins = pipeline(task=Tasks.feature_extraction)
|
|
result = pipeline_ins(input=self.sentence1)
|
|
print(np.shape(result[OutputKeys.TEXT_EMBEDDING]))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|