Question about LPR net

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hello,

I have a question concerning the Nvidia pipeline for licence plate detection and recognition given in TAO samples.

Between licence plate detection and recognition, do you use any “plate rectification” algorithm?
In many LPR pipelines, plate rectification is used so that the character recognition module process straight / rectified characters.

If not, it means that the LPRNet can read tiled characters ?
I didn’t find any sample code that uses the different models to check that point.

Thanks for your help.

2

Hi,
Please refer to the below link for Sample guide.

Refer to the installation steps from the link if in case you are missing on anything

However suggested approach is to use TRT NGC containers to avoid any system dependency related issues.

In order to run python sample, make sure TRT python packages are installed while using NGC container.
/opt/tensorrt/python/python_setup.sh

In case, if you are trying to run custom model, please share your model and script with us, so that we can assist you better.
Thanks!

4

Thanks for your answer.

In the NGC container, I find one container for plate detection, and another one for plate characters recognition.

But nothing that uses the two models together.
Where could I find a sample that uses the two models ?

Thanks

5

Hi,

Please refer https://docs.nvidia.com/tao/tao-toolkit/text/character_recognition/lprnet.html for more details. If you still need further assistance, we recommend you to please move this post to TAO forum.

Thank you.