Engine upgrade

user53799 · March 27, 2023, 5:12am

Description

A clear and concise description of the bug or issue.

Environment

TensorRT Version: 8.4
GPU Type: NX
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version: 8.0
Operating System + Version:
Python Version (if applicable): 3.6
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 1.7
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.)

I have several engine files generated from tensorrt 7.1.3 and tensorflow, now I need to convert them for tensorrt 8.5, is that possible if I have no original weights files?

NVES · March 27, 2023, 5:38am

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 8.6 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)

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!

user53799 · March 27, 2023, 7:06am

Thank you. I am checking.

Topic		Replies	Views
When to update a tensorrt engine file? TensorRT	5	912	May 11, 2022
nVidia release versions compatibility TensorRT	4	877	September 20, 2023
The engine plan file is not compatible with this version of TensorRT, expecting library version 5.1.... TensorRT	8	1830	October 12, 2021
Question regarding Tensorrt engine build vs inference environment (TensorRT version, Platform, etc) TensorRT	4	897	October 21, 2021
Version problems occurs when deserializing engine plane file TensorRT	3	722	February 28, 2023
TensorRT, result error in fp16 TensorRT	1	693	October 19, 2021
TensorRT version for CUDA 12.0 TensorRT tensorrt , cuda	1	1722	March 14, 2023
Error (Could not find any implementation for node ArgMax_260.) TensorRT	9	3488	May 17, 2022
Converting onnx to trt: [8] No importer registered for op: OneHot TensorRT tensorrt	3	2886	February 2, 2021
Onnx to tensorrt plugin for NonMaxSuppression TensorRT tensorrt , tensorflow	1	2450	April 26, 2020

Engine upgrade

Description

Environment

Relevant Files

Related topics