tao-converter3.22.05 engine deploy failure

[oswanpy]

Description

I tried to run tao-converter on this file from ngc https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/pointpillarnet/files?version=deployable_v1.0 but it gives error

Environment

TensorRT Version:8.2.5

NVIDIA GPU:GTX1650

NVIDIA Driver Version:470

CUDA Version:11.4

CUDNN Version:8.2

Operating System:

Python Version: 3.8

./tao-converter -k $KEY -e /home/osman/trt.engine -p points,1x204800x4,1x204800x4,1x204800x4 -p num_points,1,1,1 -t fp16 ../pointpillars_deployable.etlt
[INFO] [MemUsageChange] Init CUDA: CPU +337, GPU +0, now: CPU 348, GPU 202 (MiB)
[INFO] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 348 MiB, GPU 202 MiB
[INFO] [MemUsageSnapshot] End constructing builder kernel library: CPU 483 MiB, GPU 234 MiB
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 1:1: Interpreting non ascii codepoint 191.
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 1:1: Expected identifier, got: �
[ERROR] ModelImporter.cpp:735: Failed to parse ONNX model from file: /tmp/file4IbqiP
[ERROR] Failed to parse the model, please check the encoding key to make sure it's correct
[ERROR] Number of optimization profiles does not match model input node number.
Aborted (core dumped)