Why get a fault result from lprnet in jetson but right in dGPU

NVIDIA-AI-IOT / deepstream_lpr_app

Sample app code for LPR deployment on DeepStream

MIT License

209 stars 62 forks source link

Why get a fault result from lprnet in jetson but right in dGPU #20

Open fygroup opened 2 years ago

fygroup commented 2 years ago

I Test this app with Chinese plate that get a right result, But in jetson the result_label is fault Why?

huihui308 commented 2 years ago

It can solve this by changing streammux's MUXER_OUTPUT_WIDTH and MUXER_OUTPUT_HEIGHT to 1280*720 or more large, the precise will increase, but it will run slowly.