Issue with protobuf library

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hello, I am trying to convert a custom trained model (.pb) to a TensorRT model for faster inference on the NVIDIA Jetson Xavier-NX. I’ve just experienced the bellow error message, when i convert it to ONNX format.

raise _DecodeError(‘Wrong wire type in tag.’)
google.protobuf.message.DecodeError: Wrong wire type in tag.

Do you know how to solve it?Thanks.

3

Hi @shahizat ,
This could be either the issue with your TF model or Jetson Xavier.
Hence we recommend you to raise it to respective forum.

Thanks!