mirror of
https://github.com/modelscope/modelscope.git
synced 2025-12-25 12:39:25 +01:00
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
88 lines
3.3 KiB
Python
88 lines
3.3 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import os
|
|
import shutil
|
|
import tempfile
|
|
import unittest
|
|
|
|
from modelscope.hub.snapshot_download import snapshot_download
|
|
from modelscope.models.cv.image_denoise import NAFNetForImageDenoise
|
|
from modelscope.msdatasets import MsDataset
|
|
from modelscope.msdatasets.dataset_cls.custom_datasets.sidd_image_denoising import \
|
|
SiddImageDenoisingDataset
|
|
from modelscope.trainers import build_trainer
|
|
from modelscope.utils.config import Config
|
|
from modelscope.utils.constant import DownloadMode, ModelFile
|
|
from modelscope.utils.logger import get_logger
|
|
from modelscope.utils.test_utils import test_level
|
|
|
|
logger = get_logger()
|
|
|
|
|
|
class ImageDenoiseTrainerTest(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
print(('Testing %s.%s' % (type(self).__name__, self._testMethodName)))
|
|
self.tmp_dir = tempfile.TemporaryDirectory().name
|
|
if not os.path.exists(self.tmp_dir):
|
|
os.makedirs(self.tmp_dir)
|
|
|
|
self.model_id = 'damo/cv_nafnet_image-denoise_sidd'
|
|
self.cache_path = snapshot_download(self.model_id)
|
|
self.config = Config.from_file(
|
|
os.path.join(self.cache_path, ModelFile.CONFIGURATION))
|
|
dataset_train = MsDataset.load(
|
|
'SIDD',
|
|
namespace='huizheng',
|
|
subset_name='default',
|
|
split='test',
|
|
download_mode=DownloadMode.FORCE_REDOWNLOAD)._hf_ds
|
|
dataset_val = MsDataset.load(
|
|
'SIDD',
|
|
namespace='huizheng',
|
|
subset_name='default',
|
|
split='test',
|
|
download_mode=DownloadMode.FORCE_REDOWNLOAD)._hf_ds
|
|
self.dataset_train = SiddImageDenoisingDataset(
|
|
dataset_train, self.config.dataset, is_train=True)
|
|
self.dataset_val = SiddImageDenoisingDataset(
|
|
dataset_val, self.config.dataset, is_train=False)
|
|
|
|
def tearDown(self):
|
|
shutil.rmtree(self.tmp_dir, ignore_errors=True)
|
|
super().tearDown()
|
|
|
|
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
|
def test_trainer(self):
|
|
kwargs = dict(
|
|
model=self.model_id,
|
|
train_dataset=self.dataset_train,
|
|
eval_dataset=self.dataset_val,
|
|
work_dir=self.tmp_dir)
|
|
trainer = build_trainer(default_args=kwargs)
|
|
trainer.train()
|
|
results_files = os.listdir(self.tmp_dir)
|
|
self.assertIn(f'{trainer.timestamp}.log.json', results_files)
|
|
for i in range(1):
|
|
self.assertIn(f'epoch_{i+1}.pth', results_files)
|
|
|
|
@unittest.skipUnless(test_level() >= 1, 'skip test in current test level')
|
|
def test_trainer_with_model_and_args(self):
|
|
model = NAFNetForImageDenoise.from_pretrained(self.cache_path)
|
|
kwargs = dict(
|
|
cfg_file=os.path.join(self.cache_path, ModelFile.CONFIGURATION),
|
|
model=model,
|
|
train_dataset=self.dataset_train,
|
|
eval_dataset=self.dataset_val,
|
|
max_epochs=1,
|
|
work_dir=self.tmp_dir)
|
|
trainer = build_trainer(default_args=kwargs)
|
|
trainer.train()
|
|
results_files = os.listdir(self.tmp_dir)
|
|
self.assertIn(f'{trainer.timestamp}.log.json', results_files)
|
|
for i in range(1):
|
|
self.assertIn(f'epoch_{i+1}.pth', results_files)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|