Deepstream_lpr_app ERROR: [TRT]: INVALID_ARGUMENT: Cannot find binding of given name: output_bbox/BiasAdd

I repruduced the project lpr(GitHub - NVIDIA-AI-IOT/deepstream_lpr_app: Sample app code for LPR deployment on DeepStream),when i ran the sample of Chinese car plate recognition command on NX , i got the error like below.It seems the output format is wrong.
./deepstream-lpr-app 2 2 0 42501806746120190805070823.mp4 42501806746120190805070823.mp4 output.264

Request sink_0 pad from streammux
Request sink_1 pad from streammux
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.
Now playing: 2
Opening in BLOCKING MODE
Opening in BLOCKING MODE
Opening in BLOCKING MODE
Opening in BLOCKING MODE
INFO: [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT image_input 3x48x96 min: 1x3x48x96 opt: 4x3x48x96 Max: 16x3x48x96
1 OUTPUT kINT32 tf_op_layer_ArgMax 24 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT tf_op_layer_Max 24 min: 0 opt: 0 Max: 0

ERROR: [TRT]: INVALID_ARGUMENT: Cannot find binding of given name: output_bbox/BiasAdd
ERROR: [TRT]: INVALID_ARGUMENT: Cannot find binding of given name: output_cov/Sigmoid
ERROR: No output layers specified. Need atleast one output layer
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
Segmentation fault (core dumped)

i don’t know why.

Did you follow GitHub - NVIDIA-AI-IOT/deepstream_lpr_app: Sample app code for LPR deployment on DeepStream ?
Is there any change on your steps?

I cannot reproduce your error. Please double check your steps.

There was not any changes. i follow the step of the project in the link.
i ran with Jetpack4.5
can you shou me your "lpr_config_sgie_ch.txt "?

I did not change lpr_config_sgie_ch.txt

[property]
gpu-id=0
model-engine-file=../models/LP/LPR/lpr_ch_onnx_b16.engine
labelfile-path=../models/LP/LPR/labels_ch.txt
batch-size=16
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=2
num-detected-classes=3
gie-unique-id=3
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=../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
maintain-aspect-ratio=0
#scaling-compute-hw=2

[class-attrs-all]
threshold=0.5

Can you attach the full log when you run all the steps?

Make sure you run below step correctly.

For Chinese car plate recognition

    ./download_ch.sh
    // DS5.0.1 gst-nvinfer cannot generate TRT engine for LPR model, so generate it with tlt-converter
    ./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 \
           models/LP/LPR/ch_lprnet_baseline18_deployable.etlt -t fp16 -e models/LP/LPR/lpr_ch_onnx_b16.engine

Hi, why is num-detected-classes 3 instead of 67? There are 67 items in the labels_ch.txt file?