Update files

app.py

@@ -84,7 +84,24 @@ def visualize(image_path, boxes, txts, scores,
  return image_save
 
 
-def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5):
+def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5,
+ text_det=None, text_rec=None):
+ det_model_path = str(Path('models') / 'text_det' / text_det)
+ rec_model_path = str(Path('models') / 'text_rec' / text_rec)
+ if 'v2' in rec_model_path:
+ rec_image_shape = [3, 32, 320]
+ else:
+ rec_image_shape = [3, 48, 320]
+
+ print('Init Class')
+ s = time.time()
+ rapid_ocr = RapidOCR(det_model_path=det_model_path,
+ rec_model_path=rec_model_path,
+ rec_img_shape=rec_image_shape)
+ print(det_model_path, rec_model_path, rec_image_shape)
+ elapse = time.time() - s
+ print(elapse)
+
  img = cv2.imread(img_path)
  ocr_result, _ = rapid_ocr(img, box_thresh=box_thresh,
  unclip_ratio=unclip_ratio,
@@ -99,8 +116,7 @@ def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5):
  return img_save_path, output_text
 
 
-rapid_ocr = RapidOCR()
-examples = [['images/1.jpg']]
+examples = [['images/1.jpg'], ['images/ch_en_num.jpg']]
 
 with gr.Blocks(title='RapidOCR') as demo:
  gr.Markdown("""
@@ -112,10 +128,8 @@ with gr.Blocks(title='RapidOCR') as demo:
  - **unclip_ratio**: 控制文本检测框的大小，值越大，检测框整体越大。在出现框截断文字的情况，调大该值。取值范围：[1.5, 2.0]
  - **text_score**: 文本识别结果是正确的置信度，值越大，显示出的识别结果更准确。存在漏检时，调低该值。取值范围：[0, 1.0]
  ### 运行环境：
- - Python: 3.8
- - onnxruntime: 1.14.1
- - rapidocr_onnxruntime: 1.2.5""")
- gr.Markdown('### 超参数调节')
+ Python: 3.8 | onnxruntime: 1.14.1 | rapidocr_onnxruntime: 1.2.5""")
+ gr.Markdown('**超参数调节**')
  with gr.Row():
  box_thresh = gr.Slider(minimum=0, maximum=1.0, value=0.5,
  label='box_thresh', step=0.1,
@@ -130,7 +144,7 @@ with gr.Blocks(title='RapidOCR') as demo:
  interactive=True,
  info='[0, 1.0]')
 
- gr.Markdown('### 模型选择')
+ gr.Markdown('**模型选择**')
  with gr.Row():
  text_det = gr.Dropdown(['ch_PP-OCRv3_det_infer.onnx',
  'ch_PP-OCRv2_det_infer.onnx',
@@ -138,6 +152,7 @@ with gr.Blocks(title='RapidOCR') as demo:
  label='选择文本检测模型',
  value='ch_PP-OCRv3_det_infer.onnx',
  interactive=True)
+
  text_rec = gr.Dropdown(['ch_PP-OCRv3_rec_infer.onnx',
  'ch_PP-OCRv2_rec_infer.onnx',
  'ch_ppocr_server_v2.0_rec_infer.onnx'],
@@ -151,9 +166,11 @@ with gr.Blocks(title='RapidOCR') as demo:
  out_txt = gr.outputs.Textbox(type='text', label='RecText')
  button = gr.Button('Submit')
  button.click(fn=inference,
- inputs=[input_img, box_thresh, unclip_ratio, text_score],
+ inputs=[input_img, box_thresh, unclip_ratio, text_score,
+ text_det, text_rec],
  outputs=[out_img, out_txt])
  gr.Examples(examples=examples,
- inputs=[input_img, box_thresh, unclip_ratio, text_score],
+ inputs=[input_img, box_thresh, unclip_ratio, text_score,
+ text_det, text_rec],
  outputs=[out_img, out_txt], fn=inference)
 demo.launch(debug=True, enable_queue=True)