Torch_tensorrt compile doesn't support pretrained torchvision Mask_RCNN model

pradnya.m · August 11, 2022, 5:22pm

Description

Torch_tensorrt compile doesn’t support pretrained torchvision Mask_RCNN model.

Error:
RuntimeError:
temporary: the only valid use of a module is looking up an attribute but found = prim::SetAttr[name=“_has_warned”](%self, %178)
:

Environment

TensorRT Version: 1.2.0a0 (torch_tensorrt)
GPU Type: GeForce RTX 3070
Nvidia Driver Version: 470.141.03
CUDA Version: 11.4
CUDNN Version:
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.8.13
TensorFlow Version (if applicable): -
PyTorch Version (if applicable): 1.13.0a0+08820cb
Baremetal or Container (if container which image + tag): Nvidia NGC Container [nvcr.io/nvidia/pytorch:22.07-py3]

Relevant Files

Steps To Reproduce

Please execute the .ipynb file provided above.

NVES · August 11, 2022, 5:38pm

Hi ,
We recommend you to check the supported features from the below link.

You can refer below link for all the supported operators list.
For unsupported operators, you need to create a custom plugin to support the operation

github.com

onnx/onnx-tensorrt/blob/main/docs/operators.md

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

# Supported ONNX Operators

TensorRT 8.4 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)

TensorRT supports the following ONNX data types: DOUBLE, FLOAT32, FLOAT16, INT8, and BOOL

> Note: There is limited support for INT32, INT64, and DOUBLE types. TensorRT will attempt to cast down INT64 to INT32 and DOUBLE down to FLOAT, clamping values to `+-INT_MAX` or `+-FLT_MAX` if necessary.

See below for the support matrix of ONNX operators in ONNX-TensorRT.

## Operator Support Matrix

| Operator                  | Supported  | Supported Types | Restrictions                                                                                                           |
|---------------------------|------------|-----------------|------------------------------------------------------------------------------------------------------------------------|
| Abs                       | Y          | FP32, FP16, INT32 |
| Acos                      | Y          | FP32, FP16 |
| Acosh                     | Y          | FP32, FP16 |
| Add                       | Y          | FP32, FP16, INT32 |

This file has been truncated. show original

Thanks!

pradnya.m · August 11, 2022, 6:00pm

Thank you for the response. However, I am using torch_tensorrt (via a NGC container) which I don’t think uses onnx.

spolisetty · August 12, 2022, 1:49pm

Hi,

We recommend you to please reach out to Issues · pytorch/TensorRT · GitHub to get better help.

Thank you.