I’m using a detection model that has been converted to TensorRT on a TX2. A few days ago, it started to run extremely slow - original speed ~40[msec] now over 2 [sec] or slower I tried to restart the TX2 - that didn’t help. I tried to use a different model or use the same one but with a differ…

Hi, We will recommend you to use pure TensorRT for inference instead. TF-TRT use TensorFlow interface so by default it occupies most of GPU memory to allow fast algorithm. You can try to export model .pb->.uff(.onnx)->.trt to get a better performance with pure TensorRT. Here is an example for yo…

Detection tesnorRT takes seconds to run on TX2

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2

AastaLLL June 23, 2020, 7:03am 5

Hi,

Do you install any package or adjust the clock recently?
Suppose you should get the similar speed if the software stay the same.

You can also try to maximize the system performance to see if helps.

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

Thanks.

Orin NX tensorflow - high memory use

Topic		Replies	Views
Slow inference on jetson TX2 with tensorflow Jetson TX2	2	599	October 18, 2021
TensorRT model consuming more amount of RAM on Jetson TX2 Jetson TX2 tensorrt	5	1074	October 18, 2021
Jetson TX2 working at full capacity for a object detection model Inference Jetson TX2 jetson-inference	4	790	March 9, 2022
Object detection models are very slow Jetson TX2	5	1459	October 18, 2021
TensorRT inference Time TensorRT	1	758	September 20, 2018
TensorRT model consuming more amount of RAM Jetson TX2 tensorrt	3	883	October 18, 2021
Slow inference using tensorrt sampleFasterRCNN, 320ms/frame Jetson TX2	5	1397	October 18, 2021
Low Compute utilization of converted TensorFlow model during inference Jetson TX2	19	1694	October 18, 2021
Inference slow using nvInfer and TensorRT directly into PX2 General	6	754	April 17, 2019
Inference is so slow with torch1.6 Jetson Xavier NX nvbugs , pytorch	12	3534	October 23, 2020

Detection tesnorRT takes seconds to run on TX2

Related topics