Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) RTX3050 • DeepStream Version 6.4 • JetPack Version (valid for Jetson only) • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) • Issue Type( questions, new requirements, bugs) • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
I am trying the sample LPR app using deepstream using my own rtsp stream. However, i noticed that sometimes when the vehicle is detected, the license plate is detected but there were no inference output from the LPRnet. Any advice why LPRnet will not generate any predictions even when the license plate is detected?
The pretrained models are trained with U.S. California car plate licenses and the China mainland car plate licenses, it will be poor to other types of car license plates.
License Plate Recognition | NVIDIA NGC
If you want to get better output, please re-train the model with enough car license images which match your requirement.
However, may i know what is the reason why LPR isnt giving any output? I have set the confidence score threshold at 0.0 but there is no output from the LPR model. Just wanna understand is it the image did not undergo inference or the model couldn’t inference the license plate due to its blurriness / not enough training data.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
