Paddle-Inference-Demo icon indicating copy to clipboard operation
Paddle-Inference-Demo copied to clipboard

Paddle-Inference 资源加载速度过慢

Open onenerve opened this issue 6 months ago • 1 comments

请问在windows10上,采用paddle inference对PaddleOCR做GPU版本的C++部署,链接了cuda和tensorrt,在加载资源这个过程中速度非常慢,是因为什么原因导致的呢?

onenerve avatar Aug 22 '24 06:08 onenerve