PaddleOCR实例化的时候，指定模型路径不生效

[mu-nigth]

ocr = PaddleOCR(text_detection_model_dir=r"D:\paddleOCR\PP-LCNet_x1_0_doc_ori_infer",

            text_recognition_model_dir=r"D:\\paddleOCR\PP-LCNet_x1_0_doc_ori_infer",
            enable_mkldnn=False,
            use_textline_orientation=False, lang="ch")

用上述代码指定模型路径的时候，仍然是去C盘的.paddle路径下加载模型

[liuhongen1234567]

你好，不太清楚您想要指定的是那个模型，为什么 text_detection_model_dir 和 text_recognition_model_dir 指定的都是 PP-LCNet_x1_0_doc_ori_infer， 一般会指定inference.yaml 的上一级目录。

[liuhongen1234567]

您好，我这边定位了一下 doc_orientation_classify_model_dir 目前确实不会生效，不过您的问题，可以直接通过更改paddleocr模型保存的目录来解决，示例代码如下：

import os
os.environ["PADDLE_PDX_CACHE_HOME"] = "/paddle/issue_test/model_dir"
from paddleocr import PaddleOCR

ocr = PaddleOCR(# 通过 use_textline_orientation 参数指定不使用文本行方向分类模型
)

result = ocr.predict("./general_ocr_002.png")
for res in result:
    res.print()
    res.save_to_img("output")
    res.save_to_json("output")

您可以在D盘任意常见一个英文名称的文件夹用来保存下载的模型，然后os.environ["PADDLE_PDX_CACHE_HOME"] = "/paddle/issue_test/model_dir" 改成您的D盘路径就可以了。

[mu-nigth]

这个是我的运行代码，按照您说的加了环境变量，还是不行

[mu-nigth]

from paddleocr import PaddleOCR

import os
os.environ["PADDLE_PDX_CACHE_HOME"] = r"D:\paddleOCR\PP-LCNet_x1_0_doc_ori_infer"
ocr = PaddleOCR(
use_textline_orientation=False, lang="ch")

报错
��Ϣ: ���ṩ��ģʽ�޷��ҵ��ļ���
D:\Python\Lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:715: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
warnings.warn(warning_message)
Creating model: ('PP-LCNet_x1_0_doc_ori', None)
Using official model (PP-LCNet_x1_0_doc_ori), the model files will be automatically downloaded and saved in C:\Users\夜幕.paddlex\official_models.
Traceback (most recent call last):
File "D:\item\xianyu-main\xianyu.py", line 6, in
ocr = PaddleOCR(
use_textline_orientation=False, lang="ch")
File "D:\Python\Lib\site-packages\paddleocr_pipelines\ocr.py", line 161, in init
super().init(**base_params)
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\paddleocr_pipelines\base.py", line 66, in init
self.paddlex_pipeline = self._create_paddlex_pipeline()
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
File "D:\Python\Lib\site-packages\paddleocr_pipelines\base.py", line 100, in _create_paddlex_pipeline
return create_pipeline(config=self.merged_paddlex_config, **kwargs)
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_init.py", line 166, in create_pipeline
pipeline = BasePipeline.get(pipeline_name)(
config=config,
...<5 lines>...
**kwargs,
)
File "D:\Python\Lib\site-packages\paddlex\utils\deps.py", line 195, in _wrapper
return old_init_func(self, *args, **kwargs)
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 103, in init
self._pipeline = self._create_internal_pipeline(config, self.device)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 158, in _create_internal_pipeline
return self.pipeline_cls(
~~~~~~~~~~~~~~~~~~^
config,
^^^^^^^
...<3 lines>...
hpi_config=self.hpi_config,
^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines\ocr\pipeline.py", line 73, in init
self.doc_preprocessor_pipeline = self.create_pipeline(
~~~~~~~~~~~~~~~~~~~~^
doc_preprocessor_config
^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines\base.py", line 140, in create_pipeline
pipeline = create_pipeline(
config=config,
...<5 lines>...
hpi_config=hpi_config,
)
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_init.py", line 166, in create_pipeline
pipeline = BasePipeline.get(pipeline_name)(
config=config,
...<5 lines>...
**kwargs,
)
File "D:\Python\Lib\site-packages\paddlex\utils\deps.py", line 195, in _wrapper
return old_init_func(self, *args, **kwargs)
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 103, in init
self._pipeline = self._create_internal_pipeline(config, self.device)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 158, in _create_internal_pipeline
return self.pipeline_cls(
~~~~~~~~~~~~~~~~~~^
config,
^^^^^^^
...<3 lines>...
hpi_config=self.hpi_config,
^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines\doc_preprocessor\pipeline.py", line 67, in init
self.doc_ori_classify_model = self.create_model(doc_ori_classify_config)
~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\paddlex\inference\pipelines\base.py", line 107, in create_model
model = create_predictor(
model_name=config["model_name"],
...<6 lines>...
**kwargs,
)
File "D:\Python\Lib\site-packages\paddlex\inference\models_init.py", line 77, in create_predictor
return BasePredictor.get(model_name)(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
model_dir=model_dir,
^^^^^^^^^^^^^^^^^^^^
...<6 lines>...
**kwargs,
^^^^^^^^^
)
^
File "D:\Python\Lib\site-packages\paddlex\inference\models\image_classification\predictor.py", line 49, in init
self.preprocessors, self.infer, self.postprocessors = self._build()
~~~~~~~~~~~^^
File "D:\Python\Lib\site-packages\paddlex\inference\models\image_classification\predictor.py", line 82, in _build
infer = self.create_static_infer()
File "D:\Python\Lib\site-packages\paddlex\inference\models\base\predictor\base_predictor.py", line 240, in create_static_infer
return PaddleInfer(self.model_dir, self.MODEL_FILE_PREFIX, self._pp_option)
File "D:\Python\Lib\site-packages\paddlex\inference\models\common\static_infer.py", line 274, in init
self.predictor = self.create()
~~~~~~~~~~~~^^
File "D:\Python\Lib\site-packages\paddlex\inference\models\common\static_infer.py", line 342, in create
config = paddle.inference.Config(str(model_file), str(params_file))
RuntimeError: (NotFound) Cannot open file C:\Users\夜幕.paddlex\official_models\PP-LCNet_x1_0_doc_ori\inference.json, please confirm whether the file is normal.
[Hint: Expected paddle::inference::IsFileExists(prog_file) == true, but received paddle::inference::IsFileExists(prog_file):0 != true:1.] (at ..\paddle\fluid\inference\api\analysis_config.cc:117)

[liuhongen1234567]

您好，
import os
os.environ["PADDLE_PDX_CACHE_HOME"] = r"D:\paddleOCR\PP-LCNet_x1_0_doc_ori_infer" 要写在 from paddleocr import PaddleOCR 前面。

如果还不生效地话window需要单独设置系统变量 PADDLE_PDX_CACHE_HOME

[mu-nigth]

已解决，万分感谢