mirror of
https://github.com/modelscope/modelscope.git
synced 2026-07-10 12:33:28 +02:00
e02a260c93
Refactor the task_datasets module: 1. Add new module modelscope.msdatasets.dataset_cls.custom_datasets. 2. Add new function: modelscope.msdatasets.ms_dataset.MsDataset.to_custom_dataset(). 2. Add calling to_custom_dataset() func in MsDataset.load() to adapt new custom_datasets module. 3. Refactor the pipeline for loading custom dataset: 1) Only use MsDataset.load() function to load the custom datasets. 2) Combine MsDataset.load() with class EpochBasedTrainer. 4. Add new entry func for building datasets in EpochBasedTrainer: see modelscope.trainers.trainer.EpochBasedTrainer.build_dataset() 5. Add new func to build the custom dataset from model configuration, see: modelscope.trainers.trainer.EpochBasedTrainer.build_dataset_from_cfg() 6. Add new registry function for building custom datasets, see: modelscope.msdatasets.dataset_cls.custom_datasets.builder.build_custom_dataset() 7. Refine the class SiameseUIETrainer to adapt the new custom_datasets module. 8. Add class TorchCustomDataset as a superclass for custom datasets classes. 9. To move modules/classes/functions: 1) Move module msdatasets.audio to custom_datasets 2) Move module msdatasets.cv to custom_datasets 3) Move module bad_image_detecting to custom_datasets 4) Move module damoyolo to custom_datasets 5) Move module face_2d_keypoints to custom_datasets 6) Move module hand_2d_keypoints to custom_datasets 7) Move module human_wholebody_keypoint to custom_datasets 8) Move module image_classification to custom_datasets 9) Move module image_inpainting to custom_datasets 10) Move module image_portrait_enhancement to custom_datasets 11) Move module image_quality_assessment_degradation to custom_datasets 12) Move module image_quality_assmessment_mos to custom_datasets 13) Move class LanguageGuidedVideoSummarizationDataset to custom_datasets 14) Move class MGeoRankingDataset to custom_datasets 15) Move module movie_scene_segmentation custom_datasets 16) Move module object_detection to custom_datasets 17) Move module referring_video_object_segmentation to custom_datasets 18) Move module sidd_image_denoising to custom_datasets 19) Move module video_frame_interpolation to custom_datasets 20) Move module video_stabilization to custom_datasets 21) Move module video_super_resolution to custom_datasets 22) Move class GoproImageDeblurringDataset to custom_datasets 23) Move class EasyCVBaseDataset to custom_datasets 24) Move class ImageInstanceSegmentationCocoDataset to custom_datasets 25) Move class RedsImageDeblurringDataset to custom_datasets 26) Move class TextRankingDataset to custom_datasets 27) Move class VecoDataset to custom_datasets 28) Move class VideoSummarizationDataset to custom_datasets 10. To delete modules/functions/classes: 1) Del module task_datasets 2) Del to_task_dataset() in EpochBasedTrainer 3) Del build_dataset() in EpochBasedTrainer and renew a same name function. 11. Rename class Datasets to CustomDatasets in metainfo.py Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/11872747
67 lines
2.2 KiB
Python
67 lines
2.2 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import os
|
|
import shutil
|
|
import tempfile
|
|
import unittest
|
|
|
|
from modelscope.metainfo import Trainers
|
|
from modelscope.msdatasets import MsDataset
|
|
from modelscope.pipelines import pipeline
|
|
from modelscope.trainers import build_trainer
|
|
from modelscope.utils.constant import DownloadMode, Tasks
|
|
|
|
|
|
class TestFinetuneSiameseUIE(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
print(('Testing %s.%s' % (type(self).__name__, self._testMethodName)))
|
|
self.tmp_dir = tempfile.TemporaryDirectory().name
|
|
os.makedirs(self.tmp_dir, exist_ok=True)
|
|
|
|
def tearDown(self):
|
|
shutil.rmtree(self.tmp_dir)
|
|
super().tearDown()
|
|
|
|
@unittest.skip(
|
|
'skip since the test requires multiple GPU and takes a long time to run'
|
|
)
|
|
def test_finetune_people_daily(self):
|
|
model_id = 'damo/nlp_structbert_siamese-uie_chinese-base'
|
|
WORK_DIR = '/tmp'
|
|
train_dataset = MsDataset.load(
|
|
'people_daily_ner_1998_tiny',
|
|
namespace='damo',
|
|
split='train',
|
|
download_mode=DownloadMode.FORCE_REDOWNLOAD)
|
|
eval_dataset = MsDataset.load(
|
|
'people_daily_ner_1998_tiny',
|
|
namespace='damo',
|
|
split='validation',
|
|
download_mode=DownloadMode.FORCE_REDOWNLOAD)
|
|
max_epochs = 3
|
|
kwargs = dict(
|
|
model=model_id,
|
|
train_dataset=train_dataset,
|
|
eval_dataset=eval_dataset,
|
|
max_epochs=max_epochs,
|
|
work_dir=WORK_DIR)
|
|
trainer = build_trainer('siamese-uie-trainer', default_args=kwargs)
|
|
trainer.train()
|
|
for i in range(max_epochs):
|
|
eval_results = trainer.evaluate(f'{WORK_DIR}/epoch_{i+1}.pth')
|
|
print(f'epoch {i} evaluation result:')
|
|
print(eval_results)
|
|
pipeline_uie = pipeline(
|
|
task=Tasks.siamese_uie, model=f'{WORK_DIR}/output')
|
|
pipeline_uie(
|
|
input='1944年毕业于北大的名古屋铁道会长谷口清太郎等人在日本积极筹资',
|
|
schema={
|
|
'人物': None,
|
|
'地理位置': None,
|
|
'组织机构': None
|
|
})
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|