Replies: 3 comments
-
你提供的这段python脚本是通过3.0分支的wheel包进行推理的,而cpp脚本源于2.x分支,两者在前后处理和串联细节上存在差异,所以导致推理效果会略有不同。 |
Beta Was this translation helpful? Give feedback.
0 replies
-
那C++推理3.0版本的大概多久能出来啊? |
Beta Was this translation helpful? Give feedback.
0 replies
-
PaddleOCR 3.2 版本已发布,支持 OCR 产线 C++ 本地部署方案,功能及精度效果与 Python 方案保持一致。欢迎体验: 通用 OCR 产线 C++ 部署 - Linux 如果在使用过程中有任何问题,欢迎提 issue,我们会及时跟进并解决! |
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.
Uh oh!
There was an error while loading. Please reload this page.
-
🔎 Search before asking
🐛 Bug (问题描述)
用的都是最新的PP-OCRv5模型,python跑出来的准确度要高很多。
python用的GPU,C++用的CPU,这个应该没关系吧?
🏃♂️ Environment (运行环境)
windows 10
PaddleOCR 3.0
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
python代码:
from paddleocr import PaddleOCR
ocr = PaddleOCR(
use_doc_orientation_classify=False,
use_doc_unwarping=False,
use_textline_orientation=False)
result = ocr.predict(input="test.jpg")
for res in result:
res.print()
res.save_to_img("output")
res.save_to_json("output")
ppocr命令行代码:
ppocr.exe system --det_model_dir=PP-OCRv5_mobile_det --rec_model_dir=PP-OCRv5_mobile_rec --image_dir=test.jpg
其中PP-OCRv5_mobile_det和PP-OCRv5_mobile_rec都是从python运行之后的用户文件夹.paddlex/official_models拷贝出来的
Beta Was this translation helpful? Give feedback.
All reactions