We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
在ARM架构,910B的环境下。 执行PaddleOCR.text_detector(),速度比CPU还慢。 CPU一张图片大概0.5s NPU一张图片,2s-1s左右
PaddleOCR.text_detector()
已经使用环境变量: export FLAGS_npu_jit_compile=0
export FLAGS_npu_jit_compile=0
请问这种情况下,text_detector如何进行加速。
text_detector
注:text_recognizer很快。
text_recognizer
CPU:ARM NPU:910B CANN:8.0.RC2
使用PaddleOCR中的text_detector函数
The text was updated successfully, but these errors were encountered:
有人员支持嘛
Sorry, something went wrong.
YanhuiDua
No branches or pull requests
🔎 Search before asking
🐛 Bug (问题描述)
在ARM架构,910B的环境下。
执行
PaddleOCR.text_detector()
,速度比CPU还慢。CPU一张图片大概0.5s
NPU一张图片,2s-1s左右
已经使用环境变量:
export FLAGS_npu_jit_compile=0
请问这种情况下,
text_detector
如何进行加速。注:
text_recognizer
很快。🏃♂️ Environment (运行环境)
CPU:ARM
NPU:910B
CANN:8.0.RC2
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
使用PaddleOCR中的text_detector函数
The text was updated successfully, but these errors were encountered: