PaddleOCR/latest/version3.x/module_usage/text_detection

[giscus[bot]]

PaddleOCR/latest/version3.x/module_usage/text_detection

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/module_usage/text_detection.html?utm_source=chatgpt.com

[KKBIRD23]

PP-OCRv5的server模型该怎么使用？
我的脚本能正常使用自动下载的模型，但是下载server模型包在本地就无法正常使用。以下是脚本代码：

test_paddleocr_with_newly_exported_json_models.py

import paddleocr
import paddle # <--- 直接导入 paddle
import os
import traceback

print(f"PaddleOCR version: {paddleocr.version}")
print(f"PaddlePaddle version: {paddle.version}") # <--- 使用导入的 paddle

指向新导出的、包含 .json 格式模型的目录

new_exported_det_model_dir = r"C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\det_server_v5"
new_exported_rec_model_dir = r"C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\rec_server_v5"

print(f"\nNewly Exported Detection model directory: {new_exported_det_model_dir}")
if os.path.exists(new_exported_det_model_dir): print(f"Contents: {os.listdir(new_exported_det_model_dir)}")
else: print(f"ERROR: Detection model directory not found"); exit()

print(f"\nNewly Exported Recognition model directory: {new_exported_rec_model_dir}")
if os.path.exists(new_exported_rec_model_dir): print(f"Contents: {os.listdir(new_exported_rec_model_dir)}")
else: print(f"ERROR: Recognition model directory not found"); exit()

ocr_params_server = {
"lang": 'ch',
"use_textline_orientation": False,
"text_detection_model_dir": new_exported_det_model_dir,
"text_recognition_model_dir": new_exported_rec_model_dir,
}

paddle_ocr_engine = None
try:
print(f"\nInitializing PaddleOCR with newly exported JSON models. Params: {ocr_params_server}")
paddle_ocr_engine = paddleocr.PaddleOCR(**ocr_params_server)
print("PaddleOCR engine initialized successfully with newly exported JSON models.")
except Exception as e:
print(f"Error initializing PaddleOCR engine: {e}")
traceback.print_exc() # 打印完整的堆栈跟踪

if paddle_ocr_engine:
real_image_path = r"C:\Users\KKBIRD\Desktop\photo\yolo_model\PIC\3.jpg"
if os.path.exists(real_image_path):
try:
print(f"Running ocr() on image: {real_image_path} ...")
result = paddle_ocr_engine.ocr(real_image_path, cls=ocr_params_server.get("use_textline_orientation", False))
if result and result[0]:
print(f"\nOCR Results:")
for line_info in result[0]:
print(f" Box: {line_info[0]}, Text: '{line_info[1][0]}', Score: {line_info[1][1]:.4f}")
else:
print("No text detected or result is empty.")
except Exception as e:
print(f"Error during OCR: {e}")
traceback.print_exc()
else:
print(f"Error: Image file not found: {real_image_path}.")
else:
print("PaddleOCR engine could not be initialized.")

以下是执行报错：
PS C:\Users\KKBIRD\Desktop\photo\yolo_model\model\BarCode_Detect> & C:/ProgramData/miniconda3/python.exe c:/Users/KKBIRD/Desktop/photo/yolo_model/model/PaddleOCR/test.py
信息: 用提供的模式无法找到文件。
C:\ProgramData\miniconda3\Lib\site-packages\paddle\utils\cpp_extension\extension_utils.py:711: 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)
PaddleOCR version: 3.0.0
PaddlePaddle version: 3.0.0
Newly Exported Detection model directory: C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\det_server_v5
Contents: ['inference.json', 'inference.pdiparams', 'inference.yml']
Newly Exported Recognition model directory: C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\rec_server_v5
Contents: ['inference.json', 'inference.pdiparams', 'inference.yml']
Initializing PaddleOCR with newly exported JSON models. Params: {'lang': 'ch', 'use_textline_orientation': False, 'text_detection_model_dir': 'C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\det_server_v5', 'text_recognition_model_dir': 'C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\rec_server_v5'}
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\KKBIRD.paddlex\official_models.
Creating model: ('UVDoc', None)
Using official model (UVDoc), the model files will be automatically downloaded and saved in C:\Users\KKBIRD.paddlex\official_models.
Creating model: ('PP-OCRv5_mobile_det', 'C:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\exported_pdmodels\det_server_v5')
Error initializing PaddleOCR engine: Model name mismatch，please input the correct model dir.
Traceback (most recent call last):
File "c:\Users\KKBIRD\Desktop\photo\yolo_model\model\PaddleOCR\test.py", line 32, in
paddle_ocr_engine = paddleocr.PaddleOCR(**ocr_params_server)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddleocr_pipelines\ocr.py", line 144, in init
super().init(**base_params)
File "C:\ProgramData\miniconda3\Lib\site-packages\paddleocr_pipelines\base.py", line 73, in init
self.paddlex_pipeline = self._create_paddlex_pipeline()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddleocr_pipelines\base.py", line 107, in _create_paddlex_pipeline
return create_pipeline(config=self.merged_paddlex_config, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\pipelines_init.py", line 165, in create_pipeline
pipeline = BasePipeline.get(pipeline_name)(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\utils\deps.py", line 195, in _wrapper
return old_init_func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 103, in init
self._pipeline = self._create_internal_pipeline(config, self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\pipelines_parallel.py", line 158, in _create_internal_pipeline
return self.pipeline_cls(
^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\pipelines\ocr\pipeline.py", line 114, in init
self.text_det_model = self.create_model(
^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\pipelines\base.py", line 99, in create_model
model = create_predictor(
^^^^^^^^^^^^^^^^^
File "C:\ProgramData\miniconda3\Lib\site-packages\paddlex\inference\models_init.py", line 75, in create_predictor
model_name == config["Global"]["model_name"]
AssertionError: Model name mismatch，please input the correct model dir.
PaddleOCR engine could not be initialized.

我甚至下载了PP-OCRv5_server_det_pretrained.pdparams和PP-OCRv5_server_rec_pretrained.pdparams使用export_model.py导出的包执行也是这个报错

不知道有解决方案或者关于server模型的文档吗？

[jweden33]

如何将.pdiparams转化为onnx模型

[jiange259873]

FlutterNodeJs Demo Ap、