"tests/vscode:/vscode.git/clone" did not exist on "9e2734a710fcc73a9790ec4b15a3cb4fb229cf55"
Unverified Commit 14be573d authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1462 from myhloli/dev

Dev
parents 2c1f06b3 2107b25e
...@@ -8,7 +8,18 @@ from rapid_table import RapidTable ...@@ -8,7 +8,18 @@ from rapid_table import RapidTable
class RapidTableModel(object): class RapidTableModel(object):
def __init__(self, ocr_engine): def __init__(self, ocr_engine):
self.table_model = RapidTable() self.table_model = RapidTable()
if ocr_engine is None: # if ocr_engine is None:
# self.ocr_model_name = "RapidOCR"
# if torch.cuda.is_available():
# from rapidocr_paddle import RapidOCR
# self.ocr_engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True)
# else:
# from rapidocr_onnxruntime import RapidOCR
# self.ocr_engine = RapidOCR()
# else:
# self.ocr_model_name = "PaddleOCR"
# self.ocr_engine = ocr_engine
self.ocr_model_name = "RapidOCR" self.ocr_model_name = "RapidOCR"
if torch.cuda.is_available(): if torch.cuda.is_available():
from rapidocr_paddle import RapidOCR from rapidocr_paddle import RapidOCR
...@@ -16,9 +27,6 @@ class RapidTableModel(object): ...@@ -16,9 +27,6 @@ class RapidTableModel(object):
else: else:
from rapidocr_onnxruntime import RapidOCR from rapidocr_onnxruntime import RapidOCR
self.ocr_engine = RapidOCR() self.ocr_engine = RapidOCR()
else:
self.ocr_model_name = "PaddleOCR"
self.ocr_engine = ocr_engine
def predict(self, image): def predict(self, image):
......
...@@ -193,7 +193,7 @@ if __name__ == '__main__': ...@@ -193,7 +193,7 @@ if __name__ == '__main__':
max_pages = gr.Slider(1, 20, 10, step=1, label='Max convert pages') max_pages = gr.Slider(1, 20, 10, step=1, label='Max convert pages')
with gr.Row(): with gr.Row():
layout_mode = gr.Dropdown(['layoutlmv3', 'doclayout_yolo'], label='Layout model', value='doclayout_yolo') layout_mode = gr.Dropdown(['layoutlmv3', 'doclayout_yolo'], label='Layout model', value='doclayout_yolo')
language = gr.Dropdown(all_lang, label='Language', value='') language = gr.Dropdown(all_lang, label='Language', value='auto')
with gr.Row(): with gr.Row():
formula_enable = gr.Checkbox(label='Enable formula recognition', value=True) formula_enable = gr.Checkbox(label='Enable formula recognition', value=True)
is_ocr = gr.Checkbox(label='Force enable OCR', value=False) is_ocr = gr.Checkbox(label='Force enable OCR', value=False)
...@@ -221,6 +221,6 @@ if __name__ == '__main__': ...@@ -221,6 +221,6 @@ if __name__ == '__main__':
file.change(fn=to_pdf, inputs=file, outputs=pdf_show) file.change(fn=to_pdf, inputs=file, outputs=pdf_show)
change_bu.click(fn=to_markdown, inputs=[file, max_pages, is_ocr, layout_mode, formula_enable, table_enable, language], change_bu.click(fn=to_markdown, inputs=[file, max_pages, is_ocr, layout_mode, formula_enable, table_enable, language],
outputs=[md, md_text, output_file, pdf_show]) outputs=[md, md_text, output_file, pdf_show])
clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr, language]) clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr])
demo.launch(server_name='0.0.0.0') demo.launch(server_name='0.0.0.0')
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment