Version problems occurs when deserializing engine plane file

liumin2086 · February 23, 2023, 6:30am

Description

I have intalled TensorRT8.5.3.1 in Windows, but still got the error as below

Environment

TensorRT Version: 8.5.3.1
GPU Type: GeForce RTX 4090
Nvidia Driver Version: 31.0.15.2756
CUDA Version: 11.8
CUDNN Version: 8.60
Operating System + Version: Windows11专业版操作系统版本 22621.1265
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

more details please find below:
https://cxr7ii2pbr.feishu.cn/docx/MwEZdXzo6oKQAwxuP1Bcfa3PnNg

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 · February 23, 2023, 6:37am

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 8.5 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!

liumin2086 · February 23, 2023, 7:14am

The prolem still exist, if any more specifically suggestion can be given?

AakankshaS · February 28, 2023, 7:22am

Hi @liumin2086 ,
Please follow the installation steps from the below link along with the compatibility matrix to have the setup ready.

Thanks

Topic		Replies	Views
Engine upgrade TensorRT	2	342	March 27, 2023
TensorRT, result error in fp16 TensorRT	1	706	October 19, 2021
nVidia release versions compatibility TensorRT	4	1006	September 20, 2023
TensorRT version for CUDA 12.0 TensorRT tensorrt , cuda	1	1828	March 14, 2023
Comaptibility Of TensorRT with Windows 11 Professional TensorRT	2	2314	December 6, 2021
The engine plan file is not compatible with this version of TensorRT, expecting library version 5.1.... TensorRT	8	1878	October 12, 2021
Installed TRT version is not matched with downloaded TRT version? TensorRT	6	637	August 23, 2023
TensorRT C++ engine deserealization failed. Windows 10 TensorRT	3	601	June 28, 2022
TensorRT TensorRT	1	741	September 4, 2021
nvonnxparser::IParse::parse() fail,and trt report paramenter check fail TensorRT tensorrt	7	1202	July 12, 2021

Version problems occurs when deserializing engine plane file

Description

Environment

Relevant Files

Steps To Reproduce

Related topics