How to use recent text detectors with RapidOCR? #7
Description
If I want to use one of the text detectors in this link instead of DB algorithm (default). I use paddleocr_convert but it throws an error. This is an example to convert SAST algorithm to onnex:
from paddleocr_convert import PaddleOCRModelConvert
converter = PaddleOCRModelConvert()
save_dir = 'models'
url = 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar'
converter(url, save_dir)
The error log:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
File ~\anaconda3\lib\site-packages\paddleocr_convert\main.py:49, in PaddleOCRModelConvert.__call__(self, model_path, save_dir, txt_path, is_del_raw)
48 try:
---> 49 self.change_to_dynamic(save_onnx_path)
50 except Exception as e:
File ~\anaconda3\lib\site-packages\paddleocr_convert\main.py:113, in PaddleOCRModelConvert.change_to_dynamic(self, onnx_path)
112 onnx_model = onnx.load_model(onnx_path)
--> 113 dim_shapes = onnx_model.graph.input[0].type.tensor_type.shape.ListFields()[0][1]
115 dynamic_name = 'DynamicDimension'
IndexError: list index out of range
The above exception was the direct cause of the following exception:
ConvertError Traceback (most recent call last)
Cell In[24], line 7
5 # online
6 url = 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar'
----> 7 converter(url, save_dir)
File ~\anaconda3\lib\site-packages\paddleocr_convert\main.py:51, in PaddleOCRModelConvert.__call__(self, model_path, save_dir, txt_path, is_del_raw)
49 self.change_to_dynamic(save_onnx_path)
50 except Exception as e:
---> 51 raise ConvertError(
52 'change the model to dynamic meets error.') from e
54 if is_rec:
55 txt_path = self.get_file_path(txt_path, '.')
ConvertError: change the model to dynamic meets error.
Could you please tell me how I can use different text detection algorithms instead of the specified ones in this page here.