TensorRT inference in Windows7 system

shivaprasad123m · March 22, 2019, 7:45am

If I have a trained model in Caffe C++, Can we create a TensorRT inference for the application running in the Windows operating system.

NVES · March 22, 2019, 2:29pm

Hello,

yes, TensorRT does support the Windows platform. Specifically, Tensorrt supports Windows 10. For a full support matrix, please reference: https://developer.download.nvidia.com/compute/machine-learning/tensorrt/docs/5.0/GA_5.0.4.3/TensorRT-Support-Matrix-Guide.pdf

shivaprasad123m · March 25, 2019, 1:27pm

My question is, can we build a TensorRT Engine in Windows7 system. From the above link it is clear that it will support only windows10… Is there a mechanism to use TensorRT in Windows7 ?

NVES · March 25, 2019, 2:45pm

Hello,

Microsoft has recently announced end of life for Windows 7 at start of 2020. TensorRT supports Windows 10. https://www.microsoft.com/en-us/windowsforbusiness/end-of-windows-7-support

91dana · April 20, 2021, 1:56am

I’ve also tried to run TensorRT on Windows 7 but it seemed impossible.

NVES · April 20, 2021, 2:07am

Hi,
Can you try running your model with trtexec command, and share the “”–verbose"" log in case if the issue persist
https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec

You can refer below link for all the supported operators list, in case any operator is not supported you need to create a custom plugin to support that 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

Also, request you to share your model and script if not shared already so that we can help you better.

Thanks!