My device is Jetson. I want to install TRT in docker container.deb package, but when I installed it, I run /usr/src/tensorrt/bin/trtexec it was 8.2.0.3
But when I check TRT Python API, it was 8.2.3.0. Is this mistake in /usr/src/tensorrt/bin/trtexec? (8.2.3.0 and 8.2.0.3)
I need TRT8.2.3.0 in /usr/src/tensorrt/bin/trtexec. What should I do?
When installing I followd the guide Installation Guide :: NVIDIA Deep Learning TensorRT Documentation , but in the step 4 there is only Release.gpg and I run dpkg -i *deb, because when I run apt update && apt install tensorrt, it install TRT8.6.
I refer this link TensorRT Container Release Notes and download PC container. This container container TRT8.2.3.0.
After checking I suprised that Python TRT version is 8.2.3.0 and TRT version in /usr/src/tensorrt/bin/trtexec is 8.2.0.3.
This is image on PC.
Please check this for me in both PC and Jetson. Thanks.
Hi ,
These support matrices provide a look into the supported platforms, features, and hardware capabilities of the NVIDIA TensorRT 8.6.1 APIs, parsers, and layers.
You can refer below link for all the supported operators list.
<!--- 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 |
show original
Thanks!
@junshengy
Hi,
We recommend that you use the latest version.
Thank you.
@spolisetty
Also, please check “TensorRT version” in trtexec logs.
Yeah, when I checked “TensorRT version” so it is correct. It makes me confused.
system
September 6, 2023, 8:41am
8
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.
