How to create two custom layers with the same layer name when converting CAFFE model to TRT model?

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

Description

When I use TRT to covert CAFFE model, I need to add two repeated custom layers. In the prototxt, I set same layer name for the two layers. When generating the model using buildEngineWithConfig() API, it gives error: Repeated layer anme ***, layers must have distinct names.

Environment

TensorRT Version: 7.0.0
GPU Type: GeForce GTX 1080
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version:
Operating System + Version: Ubuntu 18.04.4 LTS
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

2

Hi, UFF and Caffe Parser have been deprecated from TensorRT 7 onwards, hence request you to try ONNX parser.

Please check the below link for the same.

Thanks!

3

Hi @TUMSchieben,

You need to give distinct name to the each layer.

Thank you.