mirror of
https://github.com/Vision-CAIR/MiniGPT-4.git
synced 2025-04-05 18:40:46 +00:00
05220fe3c1
- Add audio datasets - Add audio processors - Add audio support in bindgpt - Add audio training config --------- Co-authored-by: bingyikang <bingyikang@bytedance.com> Co-authored-by: zhaoyang <913556700@qq.com>
48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
"""
|
|
Copyright (c) 2022, salesforce.com, inc.
|
|
All rights reserved.
|
|
SPDX-License-Identifier: BSD-3-Clause
|
|
For full license text, see the LICENSE_Lavis file in the repo root or https://opensource.org/licenses/BSD-3-Clause
|
|
"""
|
|
|
|
from minigpt4.processors.base_processor import BaseProcessor
|
|
from minigpt4.processors.blip_processors import (
|
|
Blip2ImageTrainProcessor,
|
|
Blip2ImageEvalProcessor,
|
|
BlipCaptionProcessor,
|
|
)
|
|
from minigpt4.processors.imagebind_vision_processor import (
|
|
ImageBindCaptionProcessor,
|
|
ImageBindVisionTrainProcessor,
|
|
ImageBindVisionEvalProcessor
|
|
)
|
|
from minigpt4.processors.imagebind_audio_processor import (
|
|
ImageBindAudioTrainProcessor,
|
|
ImageBindAudioEvalProcessor,
|
|
)
|
|
|
|
from minigpt4.common.registry import registry
|
|
|
|
__all__ = [
|
|
"BaseProcessor",
|
|
"Blip2ImageTrainProcessor",
|
|
"Blip2ImageEvalProcessor",
|
|
"BlipCaptionProcessor",
|
|
"ImageBindCaptionProcessor",
|
|
"ImageBindVisionTrainProcessor",
|
|
"ImageBindVisionEvalProcessor",
|
|
"ImageBindAudioTrainProcessor",
|
|
"ImageBindAudioEvalProcessor",
|
|
]
|
|
|
|
|
|
def load_processor(name, cfg=None):
|
|
"""
|
|
Example
|
|
|
|
>>> processor = load_processor("alpro_video_train", cfg=None)
|
|
"""
|
|
processor = registry.get_processor_class(name).from_config(cfg)
|
|
|
|
return processor
|