RuntimeError: (NotFound) Cannot open file .paddleocr/2.0/det/inference.pdmodel, please confirm whether the file is normal.

[lexiaoyuan]

windows + anaconda下，PaddleOCR可以运行成功，可以识别单张图片和图像集合。但是运行python PPOCRLabel.py --lang ch，就报错：

Namespace(cls=True, cls_batch_num=30, cls_image_shape='3, 48, 192', cls_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/cls', cls_thresh=0.9, det=True, det_algorithm='DB', det_db_box_thresh=0.5, det_db_thresh=0.3, det_db_unclip_ratio=2.0, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/det', drop_score=0.5, enable_mkldnn=False, gpu_mem=8000, image_dir='', ir_optim=True, label_list=['0', '180'], lang='ch', max_text_length=25, rec=True, rec_algorithm='CRNN', rec_batch_num=30, rec_char_dict_path='./ppocr/utils/ppocr_keys_v1.txt', rec_char_type='ch', rec_image_shape='3, 32, 320', rec_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/rec/ch', use_angle_cls=True, use_gpu=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, use_zero_copy_run=False)
Traceback (most recent call last):
  File "PPOCRLabel.py", line 2005, in <module>
    sys.exit(main())
  File "PPOCRLabel.py", line 1993, in main
    app, _win = get_main_app(sys.argv)
  File "PPOCRLabel.py", line 1985, in get_main_app
    win = MainWindow(lang=args.lang,
  File "PPOCRLabel.py", line 111, in __init__
    self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
  File "..\paddleocr.py", line 269, in __init__
    super().__init__(postprocess_params)
  File "..\tools\infer\predict_system.py", line 42, in __init__
    self.text_detector = predict_det.TextDetector(args)
  File "..\tools\infer\predict_det.py", line 97, in __init__
    self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
  File "..\tools\infer\utility.py", line 135, in create_predictor
    predictor = inference.create_predictor(config)
RuntimeError: (NotFound) Cannot open file C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel, please confirm whether the file is normal.
  [Hint: Expected static_cast<bool>(fin.is_open()) == true, but received static_cast<bool>(fin.is_open()):0 != true:1.] (at D:\v2.0.0\paddle\paddle\fluid\inference\api\analysis_predictor.cc:829)

C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel这个文件是存在的。

[lexiaoyuan]

windows + anaconda下，PaddleOCR可以运行成功，可以识别单张图片和图像集合。但是运行python PPOCRLabel.py --lang ch，就报错：

Namespace(cls=True, cls_batch_num=30, cls_image_shape='3, 48, 192', cls_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/cls', cls_thresh=0.9, det=True, det_algorithm='DB', det_db_box_thresh=0.5, det_db_thresh=0.3, det_db_unclip_ratio=2.0, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/det', drop_score=0.5, enable_mkldnn=False, gpu_mem=8000, image_dir='', ir_optim=True, label_list=['0', '180'], lang='ch', max_text_length=25, rec=True, rec_algorithm='CRNN', rec_batch_num=30, rec_char_dict_path='./ppocr/utils/ppocr_keys_v1.txt', rec_char_type='ch', rec_image_shape='3, 32, 320', rec_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/rec/ch', use_angle_cls=True, use_gpu=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, use_zero_copy_run=False)
Traceback (most recent call last):
  File "PPOCRLabel.py", line 2005, in <module>
    sys.exit(main())
  File "PPOCRLabel.py", line 1993, in main
    app, _win = get_main_app(sys.argv)
  File "PPOCRLabel.py", line 1985, in get_main_app
    win = MainWindow(lang=args.lang,
  File "PPOCRLabel.py", line 111, in __init__
    self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
  File "..\paddleocr.py", line 269, in __init__
    super().__init__(postprocess_params)
  File "..\tools\infer\predict_system.py", line 42, in __init__
    self.text_detector = predict_det.TextDetector(args)
  File "..\tools\infer\predict_det.py", line 97, in __init__
    self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
  File "..\tools\infer\utility.py", line 135, in create_predictor
    predictor = inference.create_predictor(config)
RuntimeError: (NotFound) Cannot open file C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel, please confirm whether the file is normal.
  [Hint: Expected static_cast<bool>(fin.is_open()) == true, but received static_cast<bool>(fin.is_open()):0 != true:1.] (at D:\v2.0.0\paddle\paddle\fluid\inference\api\analysis_predictor.cc:829)

C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel这个文件是存在的。

已解决。C盘.paddleocr目录下的模型文件是第一次运行时下载下来的，不知道在程序里为什么会报这个错误。

在utility.py里自己指定model_dir为自己下载并解压的模型文件路径就好了。
例：

if mode == "det":
    # model_dir = args.det_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_det_infer'
elif mode == 'cls':
    # model_dir = args.cls_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_cls_infer'
else:
    # model_dir = args.rec_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_rec_infer'

其中E:/PaddleOCR/inference目录下就是参考https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/quickstart_en.md新建的inference及下载并解压的目录

[littletomatodonkey]

好的，不建议使用带中文的文件路径哈

[JunLei01]

你好，这个utility.py文件是在哪里的？我在环境中好像没找到这个

[wuliaodeashuai]

为什么还是报错啊

[lingchen-xn]

你好，这个utility.py文件是在哪里的？我在环境中好像没找到这个

同问

[ZY945]

@JunLei01 @lingchen-xn
在这里，

如果是虚拟环境，在虚拟环境文件夹里

[ZY945]

@ZY945 这个文件里修改路径----指的是模型的路径，修改时注意缩进和是否需要防止转义

[Hygge1024]

windows + anaconda下，PaddleOCR可以运行成功，可以识别单张图片和图像集合。但是运行python PPOCRLabel.py --lang ch，就报错：

Namespace(cls=True, cls_batch_num=30, cls_image_shape='3, 48, 192', cls_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/cls', cls_thresh=0.9, det=True, det_algorithm='DB', det_db_box_thresh=0.5, det_db_thresh=0.3, det_db_unclip_ratio=2.0, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/det', drop_score=0.5, enable_mkldnn=False, gpu_mem=8000, image_dir='', ir_optim=True, label_list=['0', '180'], lang='ch', max_text_length=25, rec=True, rec_algorithm='CRNN', rec_batch_num=30, rec_char_dict_path='./ppocr/utils/ppocr_keys_v1.txt', rec_char_type='ch', rec_image_shape='3, 32, 320', rec_model_dir='C:\\Users\\徐仕成/.paddleocr/2.0/rec/ch', use_angle_cls=True, use_gpu=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, use_zero_copy_run=False)
Traceback (most recent call last):
  File "PPOCRLabel.py", line 2005, in <module>
    sys.exit(main())
  File "PPOCRLabel.py", line 1993, in main
    app, _win = get_main_app(sys.argv)
  File "PPOCRLabel.py", line 1985, in get_main_app
    win = MainWindow(lang=args.lang,
  File "PPOCRLabel.py", line 111, in __init__
    self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
  File "..\paddleocr.py", line 269, in __init__
    super().__init__(postprocess_params)
  File "..\tools\infer\predict_system.py", line 42, in __init__
    self.text_detector = predict_det.TextDetector(args)
  File "..\tools\infer\predict_det.py", line 97, in __init__
    self.predictor, self.input_tensor, self.output_tensors = utility.create_predictor(
  File "..\tools\infer\utility.py", line 135, in create_predictor
    predictor = inference.create_predictor(config)
RuntimeError: (NotFound) Cannot open file C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel, please confirm whether the file is normal.
  [Hint: Expected static_cast<bool>(fin.is_open()) == true, but received static_cast<bool>(fin.is_open()):0 != true:1.] (at D:\v2.0.0\paddle\paddle\fluid\inference\api\analysis_predictor.cc:829)

C:\Users\徐仕成/.paddleocr/2.0/det/inference.pdmodel这个文件是存在的。

已解决。C盘.paddleocr目录下的模型文件是第一次运行时下载下来的，不知道在程序里为什么会报这个错误。

在utility.py里自己指定model_dir为自己下载并解压的模型文件路径就好了。 例：

if mode == "det":
    # model_dir = args.det_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_det_infer'
elif mode == 'cls':
    # model_dir = args.cls_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_cls_infer'
else:
    # model_dir = args.rec_model_dir
    model_dir = 'E:/PaddleOCR/inference/ch_ppocr_mobile_v2.0_rec_infer'

其中E:/PaddleOCR/inference目录下就是参考https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/quickstart_en.md新建的inference及下载并解压的目录

解决了。中文路径有影响，还需要在代码中更改绝对路基

[damaocode]

解决办法有用，感谢，另外用google搜索才第一条搜出来的，百度真垃圾

[sulmz]

为什么中国人开发的开源模型，会对中文路径支持不做优化呢？费解

[S1024K]

模型文件变成这样的了，和题主的不太一样了，直接从https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/models_list.md 下载，分别下载det，cls和rec这三个，然后更改路径为你下载的路径即可。

[Jain-cc]

这个问题卡了一天，就是中文路径的问题，编译后的程序改全英文路径后OK了
我一直以为是文件权限或者文件完整性问题

[Ericlong1111]

大佬们，为什么我按上述修改了下载路径，仍然报错，只能修改用户名了吗