Does tensorrt suport op like "expand_as" or "tile" for dynamic shape input?

zq_ins_seu · August 13, 2021, 9:09am

Description

I have a model include op expand_as/tile, which does things like:
input_x_tensor_shape = (1,256,1,1)
input_y_tensor_shape=(1,256,h,w)
out = input_x.expand_as(input_y) or out = tile(input_x,repeat_times=(1,1,h,w))
out_shape=(1,256,h,w)

which dynamic shape means h,w is not fixed while inference,
Does tensorrt supoort this situation？

A clear and concise description of the bug or issue.

Environment

TensorRT Version:
tensorrt 7.2.3.4
GPU Type:
T4
Nvidia Driver Version:
nvidia440.33
CUDA Version:
10.2
CUDNN Version:
cudnn 8.1.1
Operating System + Version:
centos 7.9
Python Version (if applicable):

TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

Exact steps/commands to build your repro
Exact steps/commands to run your repro
Full traceback of errors encountered

NVES · August 13, 2021, 9:37am

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!

1055057679 · November 11, 2021, 7:24am

It should support