PaddleX/latest/data_annotations/cv_modules/semantic_segmentation

[giscus[bot]]

PaddleX/latest/data_annotations/cv_modules/semantic_segmentation

https://paddlepaddle.github.io/PaddleX/latest/data_annotations/cv_modules/semantic_segmentation.html

[Y70538889]

我用 数据标注教程下 “语义分割任务模块” 中的 “2.3.4 格式转换” 步命令时转换出错了，可以帮忙看一下是什么问题吗？下面是报错内容
(PaddlexPy312) D:\PaddleX_V3\PaddleX-release-3.0>python main.py -c paddlex/configs/modules/semantic_segmentation/PP-LiteSeg-T.yaml -o Global.mode=check_dataset -o Global.dataset_dir=./seg_dataset -o CheckDataset.convert.enable=True -o CheckDataset.convert.src_dataset_type=LabelMe
Traceback (most recent call last):
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\utils\result_saver.py", line 28, in wrap
result = func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\engine.py", line 38, in run
return self.model.check_dataset()
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\model.py", line 115, in check_dataset
return dataset_checker.check()
^^^^^^^^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\modules\base\dataset_checker\dataset_checker.py", line 72, in check
self.convert_dataset(dataset_dir)
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\modules\semantic_segmentation\dataset_checker_init.py", line 54, in convert_dataset
return convert_dataset(
^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\modules\semantic_segmentation\dataset_checker\dataset_src\convert_dataset.py", line 35, in convert_dataset
return convert_labelme_dataset(input_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\utils\deps.py", line 135, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\PaddleX_V3\PaddleX-release-3.0\paddlex\modules\semantic_segmentation\dataset_checker\dataset_src\convert_dataset.py", line 115, in convert_labelme_dataset
shutil.copy(img_path, output_img_dir)
File "D:\PaddleX_V3\miniconda3\envs\PaddlexPy312\Lib\shutil.py", line 423, in copy
copyfile(src, dst, follow_symlinks=follow_symlinks)
File "D:\PaddleX_V3\miniconda3\envs\PaddlexPy312\Lib\shutil.py", line 240, in copyfile
raise SameFileError("{!r} and {!r} are the same file".format(src, dst))
shutil.SameFileError: 'seg_dataset\annotations\..\images\4.jpg' and 'seg_dataset\images\4.jpg' are the same file

最后一行提示annotations文件夹下的4.jpg文件是不存在的，它实际是4.png文件

[linhongping98]

en labeme转这个有些bug 您那边好像是读的是json里面的文件路径 但是 但是大多时候转的时候是 复制到其他地方了，\annotations\20260104114049219.bmp is not existed, skip this image
.\annotations\20260104114039306.bmp is not existed, skip this image
.\annotations\20260104114053450.bmp is not existed, skip this image
.\annotations\20260104114040622.bmp is not existed, skip this image 这个下面是我json中的数据 "kie_linking": []
}
],
"imagePath": "20260104114041234.bmp",
"imageData": null,
"imageHeight": 2608,
"imageWidth": 2619,
"description": ""
}