Is it possible to export YOLO8 to TensorRT 10.7 for RTX 3080 TI (Ampere)?

rajhlinux · January 3, 2025, 2:00am

Hello,

Is it possible to export YOLO v8 to TensorRT 10.7 for object detection which will be hardware accelerated in RTX 3080 TI? Any guides will be obliged.

I use C++ and can not find any documentations on how to go about this. Everything on the internet shows about YOLO8 with older deprecated versions compared to TensorRT 10.7 support matrix. Everything is discussed in python which is unfavorable.

Thanks.

AakankshaS · January 31, 2025, 1:19pm

Hi @rajhlinux ,
I will convey the availability req of samples in c++ to the team.
Thank you for the feedback

Topic		Replies	Views
C++ Yolov3_ONNX output parsing TensorRT	5	1362	January 6, 2025
YOLOv4 TensorRT inference results wayy off, but onnxruntime is not TensorRT tensorrt	7	936	June 7, 2022
TensorRT Batch Inference: different results TensorRT	4	4204	December 1, 2021
Have engine file but how can use it for object detection? Jetson Nano tensorrt , cuda	2	1083	June 14, 2023
TensorRT Jetson Nano ONNX Inference TensorRT	1	541	August 25, 2020
TensorRT Inference form a .etlt model on Python TAO Toolkit tensorrt	7	1218	November 16, 2021
Tenssorrt INT8 precision engine build failed for the models having custom layer (BatchedNMSDynamic_TRT) TensorRT	11	1911	June 29, 2021
Use pre-trained object detection TF2 models with TensorRT ONNX TensorRT	9	1923	May 31, 2021
Unable to export hdf5 to etlt after Tao Training on Colab TAO Toolkit yolo	11	710	March 21, 2024
0.3fps when using yolov3_onnx in TensorRT examples provided by Nvidia in Jetson Nano Jetson Nano	8	1771	October 14, 2021

Is it possible to export YOLO8 to TensorRT 10.7 for RTX 3080 TI (Ampere)?

Related topics