Converting Pytorch model through ONNX: "UNSUPPORTED_NODE: No importer registered for op: Greater"

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

Hi,
I’m trying to convert an ONNX model, built from Pytorch, into TensorRT 5.1.2.2.
Unfortunately, it can’t handle a “Greater” layer.

How can I solve this issue? is it possible to implement this layer myself, when loading from ONNX? Is there another recommended way to convert a Pytorch model to TensorRT in which a straightforward layer such as “Greater” has an implementation, or a way to implement it myself?

Thanks.

2

Hi,

It looks like the model you are converting to TensorRT contains unsupported layers and operation.

For a list of supported operations, please reference: https://docs.nvidia.com/deeplearning/sdk/tensorrt-support-matrix/index.html#supported-ops

For unsupported layers, users can extend TensorRT functionalities by implementing custom layers using the IPluginV2 class for the C++ and Python API. Custom layers, often referred to as plugins, are implemented and instantiated by an application, and their lifetime must span their use within a TensorRT engine. https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#extending

Thanks,
NVIDIA Enterprise Support