参考的这个文章
https://blog.csdn.net/ITdaka/article/details/138863017?spm=1001.2014.3001.5501
openai快捷下载：https://download.csdn.net/download/qq_43767886/89876720
然后我打算训练coco数据集，遇到了以下的问题
问题一
原因：错误提示表明你缺少 transformers 库，并且 PYTHONPATH 未正确配置，导致 Python 无法找到自定义模块 yolo_world。
安装 transformers；
yolo_world参考上面文章的链接
pip install transformers
Traceback (most recent call last):File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmengine/utils/misc.py", line 77, in import_modules_from_stringsimported_tmp = import_module(imp)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/importlib/__init__.py", line 127, in import_modulereturn _bootstrap._gcd_import(name[level:], package, level)File "<frozen importlib._bootstrap>", line 1030, in _gcd_importFile "<frozen importlib._bootstrap>", line 1007, in _find_and_loadFile "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlockedFile "<frozen importlib._bootstrap>", line 680, in _load_unlockedFile "<frozen importlib._bootstrap_external>", line 790, in exec_moduleFile "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removedFile "/home/rycc/cc/yolo-world/yolo_world/__init__.py", line 10, in <module>from .models import * # noqaFile "/home/rycc/cc/yolo-world/yolo_world/models/__init__.py", line 2, in <module>from .backbones import * # noqaFile "/home/rycc/cc/yolo-world/yolo_world/models/backbones/__init__.py", line 5, in <module>from .mm_backbone import (File "/home/rycc/cc/yolo-world/yolo_world/models/backbones/mm_backbone.py", line 10, in <module>from transformers import (AutoTokenizer, AutoModel, CLIPTextConfig)
ModuleNotFoundError: No module named 'transformers'During handling of the above exception, another exception occurred:Traceback (most recent call last):File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmengine/config/config.py", line 466, in fromfileimport_modules_from_strings(**cfg_dict['custom_imports'])File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmengine/utils/misc.py", line 84, in import_modules_from_stringsraise ImportError(f'Failed to import {imp}')
ImportError: Failed to import yolo_worldThe above exception was the direct cause of the following exception:Traceback (most recent call last):File "/home/rycc/cc/yolo-world/train.py", line 127, in <module>main()File "/home/rycc/cc/yolo-world/train.py", line 65, in maincfg = Config.fromfile(args.config)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmengine/config/config.py", line 478, in fromfileraise ImportError(err_msg) from e
ImportError: Failed to import custom modules from {'imports': ['yolo_world'], 'allow_failed_imports': False}, the current sys.path is:/home/rycc/cc/yolo-world/home/rycc/anaconda3/envs/yolo-world/lib/python39.zip/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/lib-dynload/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/tmp/tmpo38nms2p
You should set PYTHONPATH to make sys.path include the directory which contains your custom module
问题二
原因：/openai/clip-vit-base-patch32文件路径不对。
OSError: Incorrect path_or_model_id: '../openai/clip-vit-base-patch32'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
解决方法：
问题三
原因：albumentations安装的版本不对
解决方法：pip 安装 albumentations==1.3.1
Traceback (most recent call last):File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loopdata = fetcher.fetch(index)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetchdata = [self.dataset[idx] for idx in possibly_batched_index]File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp>data = [self.dataset[idx] for idx in possibly_batched_index]File "/home/rycc/cc/yolo-world/yolo_world/datasets/mm_dataset.py", line 86, in __getitem__return self.pipeline(data_info)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmengine/dataset/base_dataset.py", line 60, in __call__data = t(data)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmcv/transforms/base.py", line 12, in __call__return self.transform(results)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmdet/structures/bbox/box_type.py", line 267, in wrapperreturn func(self, results)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/mmdet/datasets/transforms/transforms.py", line 1507, in transformresults = self.aug(**results)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/albumentations/core/composition.py", line 346, in __call__self.preprocess(data)File "/home/rycc/anaconda3/envs/yolo-world/lib/python3.9/site-packages/albumentations/core/composition.py", line 373, in preprocessraise ValueError(msg)
ValueError: Key img_path is not in available keys.
我的目录文件配置
