NVIDIA Developer Forums

After converting ssdMobilnet from the examples, the model is slower

Robotics & Edge Computing Jetson & Embedded Systems Jetson Xavier NX

AastaLLL August 19, 2020, 6:57am 6

Hi,

This should depends on the layers used in your model.
Do you also use ssd_mobilenet_v1 as the authors?

If yes, it’s recommended to convert the model into pure TensorRT engine for performance.

Thanks.

Topic		Replies	Views	Activity
Lower performance with TRT than plain TF? Jetson Xavier NX tensorrt , jetson-inference	14	2003	October 18, 2021
No performance improvement for Tensorflow TensorRT model on converted on Jetsons Xavier NX Jetson Xavier NX tensorrt , tensorflow	2	688	October 18, 2021
SSD-MobilenetV2 bad performance on XavierNX using Tensorflow + TF_TRT Jetson Xavier NX tensorrt , opencv , cuda , tensorflow	5	1889	October 18, 2021
Inference Speed Jetson Xavier NX pytorch	6	904	April 12, 2023
I am trying to convert the ONNX SSD mobilnet v3 model into TensorRT Engine. I am getting the below error Jetson TX2 tensorrt , tensorflow	24	3804	February 17, 2022
Human pose detection model (MoveNet) TensorRT conversion on NVIDIA Jetson Jetson Xavier NX tensorrt , tensorflow , jetson-inference	7	2693	June 16, 2022
Help converting a pytorch model to TensorRT Jetson Xavier NX tensorrt , pytorch	6	2930	October 18, 2021
Convert tensorflow model Jetson TX2	4	1782	October 18, 2021
No improvements from TensorRT on NVIDIA-AI-IOT/tf_trt_models TensorRT	3	1573	February 21, 2019
Process killed during tensorrt conversion on Jetson orin NX (8 GB) Jetson Orin NX tensorrt	15	797	April 30, 2024