Replies: 4 comments
-
在使用DB++作为模型检测训练时,自定义模型启动的时候,paddleocr.py内SUPPORT_DET_MODEL参数会限制你只能使用DB模型,这种情况会不会有问题? |
Beta Was this translation helpful? Give feedback.
0 replies
-
我也是在PaddleLabel使用DB++模型就无法检测,请问你解决了吗? |
Beta Was this translation helpful? Give feedback.
0 replies
-
@Sencc 在你PaddleLabel install之后的路径里面,找到paddleocr.py,修改SUPPORT_DET_MODEL参数,改成如图: |
Beta Was this translation helpful? Give feedback.
0 replies
-
@gubinjie 感谢分享 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
PaddleOCR V2.7

1、使用DB++训练了检测模型,并将模型通过tools/export_model.py导出为inference模型。
2、在使用命令行:
python3 tools/infer/predict_det.py --det_algorithm="DB++" --det_model_dir="./output/yinzhang_det_240227/det_db_inference/" --image_dir="./train_data/yinzhang_240227/target/img/094_18.png" --use_gpu=True
检测时,能够检测图片中目标区域。3、但是使用PaddleLabel加载导出来的模型时,一直无法识别目标区域。
4、启动命令及修改代码:
python ./PPOCRLabel.py --lang ch
,修改文件:PPOCRLabel.py
self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=gpu, lang=lang, show_log=True, rec_image_shape="3, 160, 1600", det_max_side_len=1600, det_model_dir='D:\\JetBrains\\PycharmProjects\\PaddleOCR\\output\\yinzhang_det_240227\\det_db_inference') self.table_ocr = PPStructure(use_pdserving=False, use_gpu=gpu, lang=lang, layout=False, show_log=True, rec_image_shape="3, 160, 1600", det_max_side_len=1600, det_model_dir='D:\\JetBrains\\PycharmProjects\\PaddleOCR\\output\\yinzhang_det_240227\\det_db_inference')
5、模型文件截图:
6、启动之后,在UI界面点击自动标注,但是并没有检测出目标区域
请问这是bug还是由于什么原因?
Beta Was this translation helpful? Give feedback.
All reactions