ERROR: ModelImporter.cpp:134 In function parseGraph: [8] No importer registered for op: ReverseSequence

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

Description

Using Bidirectional LSTM in my network and when trying to create cuda engine with my converted onnx file:

engine.reset(createCudaEngine(onnxModelPath, batchSize));
if (!engine)
    return 1;

I’m getting this error:

ERROR: ModelImporter.cpp:134 In function parseGraph:
[8] No importer registered for op: ReverseSequence
ERROR: could not parse input engine.

Environment

TensorRT Version : 7.0.0-1
GPU Type : RTX
Nvidia Driver Version :
CUDA Version : 11.0
CUDNN Version :
Operating System + Version : Ubuntu 18.04
Python Version (if applicable) : 3.6
TensorFlow Version (if applicable) : 2.3
PyTorch Version (if applicable) :
Baremetal or Container (if container which image + tag) :

2

Hi @shir,
I am afraid, ReverseSequence operation is currently not supported in tensorRT.
However the team is working on this, and this will be available in future releases.
Please stay tuned.

Thanks!