Layer '/Round' did not supported in DLA

x2547268390 · June 30, 2024, 11:21am

Hi,
I’m using a Jetson AGX Orin with Jetpack 6.0 to generate a tensorrt engine for one DLA core.
however, I encountered an error.
Layer ‘/Round’ did not supported in DLA
I want my model to run independently on DLA, but this layer is essential. Is there any way to make this possible?

AastaLLL · July 1, 2024, 3:15am

Hi,

Unfortunately, the “Round” operator is not supported and doesn’t have a WAR to make it work on DLA right now.
But you can submit an RFE request with the link shared below:

github.com

NVIDIA/Deep-Learning-Accelerator-SW/blob/main/operators/README.md#onnx-operatorfunction-support-matrix

<!--- SPDX-License-Identifier: Apache-2.0 -->

# Supported ONNX Operators & Functions on Orin DLA

DLA operator functionality is exposed through the TensorRT builder, which internally links to DLA SW libraries (see [DLA Workflow](https://developer.nvidia.com/deep-learning-accelerator)). While some ONNX operators or functions may already be available in DLA SW, TensorRT may not expose them yet.
See below for the support matrix of ONNX operators & functions on Orin DLA. If you are interested in a specific DLA operator that is not supported through TensorRT yet, feel free to raise a [GitHub Issue](https://github.com/NVIDIA/Deep-Learning-Accelerator-SW/issues) and/or inform your NVIDIA representative (in particular for NVIDIA DRIVE customers).

See [General Restrictions](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla-lay-supp-rest) that apply to all operations below. Many of those ops are supported on Xavier DLA as well, see [Layer Support and Restrictions](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla-lay-supp-rest).

TensorRT 8.6 supports operators up to Opset 17. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md).

Note that the scripts in `op_reconstruction/` are intended as a recipe for how ops currently not supported on DLA can be decomposed into supported ops. Depending on your setup, you may choose to perform such op reconstructions in the ONNX domain post-training (as done here) or during the training process (for example in TensorFlow or PyTorch). The case of "Native" in the DLA SW support column and "Reconstruction" in the TensorRT support column indicates that an op can be supported through TensorRT by decomposing it into other DLA ops already supported by TensorRT.

Below Operator Support Matrix requires the following minimum system config (the OS by default gets shipped with the DLA SW and TensorRT versions to its right):

| **Hardware platform** | **OS**               | **DLA SW version** | **TensorRT version** |
| ----------------- | ---------------- | -------------- | ---------------- |
| DRIVE Orin (Automotive)        | DRIVE OS 6.0.6.0 | DLA 3.12.0     | TensorRT 8.5.10  |
| Jetson Orin (Embedded)      | JetPack 5.1.1    | DLA 3.12.1     | TensorRT 8.5.2   |
| DRIVE Orin (Automotive)        | DRIVE OS 6.0.7.0 | DLA 3.13.0     | TensorRT 8.6.10  |

This file has been truncated. show original

Thanks.

x2547268390 · July 1, 2024, 3:27am

Thank you, but I noticed that the round operator is already in the DLA SW library. So, it is not currently publicly available in TensorRT?

AastaLLL · July 3, 2024, 5:03am

Hi,

Yes, please submit the RFE so our internal team can prioritize the support.

Thanks.

system · July 30, 2024, 6:51am

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.