NVIDIA-AI-IOT / deepstream_lpr_app is not working when only using LPD and LPR model

[akash.singh1]

@Fiona.Chen

pre-trained LP

But when running trafficamnet model + LPD (DetectNet_v2) and LPR model it is returning OCR output.

[Fiona.Chen]

@akash.singh1

SGIE:

[property]
gpu-id=0
model-engine-file=/home/deepstream-python/models/lpr_us_onnx_b16.engine
labelfile-path=/home/deepstream-python/models/us_lp_characters.txt
tlt-encoded-model=/home/deepstream-python/models/us_lprnet_baseline18_deployable.etlt
tlt-model-key=nvidia_tlt
batch-size=16
network-mode=2
num-detected-classes=3
gie-unique-id=1
output-blob-names=output_bbox/BiasAdd;output_cov/Sigmoid
#0=Detection 1=Classifier 2=Segmentation
network-type=1
parse-classifier-func-name=NvDsInferParseCustomNVPlate
custom-lib-path=/home/deepstream-python/nvinfer_custom_lpr_parser/libnvdsinfer_custom_impl_lpr.so
process-mode=2
operate-on-gie-id=2
net-scale-factor=0.00392156862745098
#net-scale-factor=1.0
#0=RGB 1=BGR 2=GRAY
model-color-format=0

[class-attrs-all]
threshold=0.5

Your PGIE’s gie-unique-id=1, please set operate-on-gie-id=1 here

[Fiona.Chen]

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

Please read the document for the meaning of the parameters, Gst-nvinfer — DeepStream 6.2 Release documentation