Onnx model not running on jetson

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

I have converted a keas model to onnx model through keras2onnx library and then I was trying to run onnx model on jetson through this command:
trtexec --onnx=/home/model.onnx --saveEngine=/home/model.engine

Model file: keras-recognize-model.onnx - Google Drive

I am getting error:

[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 1:1: Invalid control characters encountered in text.
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:11: Invalid control characters encountered in text.
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:16: Already saw decimal point or exponent; can’t have another one.
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:13: Message type “onnx2trt_onnx.ModelProto” has no field named “keras2onnx”.
Failed to parse ONNX model from file/home/model.onnx
[08/01/2020-11:58:27] [E] [TRT] Network must have at least one output
[08/01/2020-11:58:27] [E] [TRT] Network validation failed.
[08/01/2020-11:58:27] [E] Engine creation failed
[08/01/2020-11:58:27] [E] Engine set up failed

What can be the issue please help…

OS: ubuntu
TensorRT version: 7.1.x

3

Hi,

Please check if this topic helps first. https://groups.google.com/g/protobuf/c/8wXDCCWyzz4

Thanks.