search

DoubangoTelecom / ultimateALPR-SDK

World's fastest ANPR / ALPR implementation for CPUs, GPUs, VPUs and NPUs using deep learning (Tensorflow, Tensorflow lite, TensorRT, OpenVX, OpenVINO). Multi-Charset (Latin, Korean, Chinese) & Multi-OS (Jetson, Android, Raspberry Pi, Linux, Windows) & Multi-Arch (ARM, x86).
https://www.doubango.org/webapps/alpr/
Other
597 stars 157 forks source link

Error with GPU enabled #206

Closed gio2375 closed 2 years ago

gio2375 commented 2 years ago

Hello, I'm testing the sample application Recognizer (Java version). All works well if I use CPU but, if I try GPU I get the errors you can see in attacched file. My Video card is an Nvidia Gforce GTX 950M.

Thanks Giovanni

GPU_error.txt

DoubangoTelecom commented 2 years ago

Hello, Do not use "openvino_device": "GPU" on NVIDIA GPUs. Use OpenVINO GPU computing on Intel GPUs only (e.g. NCS2). You have an Nvidia Geforce GTX 950M with support for CUDA. Tensorflow supports CUDA and you can check https://github.com/DoubangoTelecom/ultimateALPR-SDK/tree/master/samples/c%2B%2B#gpu-acceleration. Please note that you have to correctly install CUDA libraries and drivers first.

DoubangoTelecom commented 2 years ago

Please also note that you have a very low end GPU (https://www.techpowerup.com/gpu-specs/geforce-gtx-950m.c2642). You'll not see significant boost