Hello, I’m trying to reproduce NVIDIA benchmark with TensorRT Tiny-YOLOv3 (getting 1000 FPS) on a Jetson AGX Xavier target with the parameters below (i got only 700 FPS): Power Mode : MAXN Input resolution : 416x416 Precision Mode : INT8 (Calibration with 1000 images and IInt8EntropyCalibrator2 …

Hi, Please find an example in the below comment: [image] Difference between running the inference with trtexec and tensorrt python API Jetson AGX Xavier Hi, We reuse the calibration cache from here and the model used in jetson-benchmark . Be able to get 1088 fps on INT8+…

How can i get 1000 FPS by running the inference with TensorRT Tiny-YOLOv3 (Jetson AGX Xavier)

Robotics & Edge Computing Jetson & Embedded Systems Jetson AGX Xavier

AastaLLL June 8, 2021, 8:01am 7

Hi,

Please find an example in the below comment:

Thanks.

Topic		Replies	Views
Python sample yolov3 app on tensorrt Jetson Xavier NX tensorrt , yolo , python	9	1759	October 18, 2021
Yolov3 FPS on TensorRT Jetson AGX Xavier tensorrt	26	7350	October 18, 2021
Tensorflow model acceleration on AGX Jetson AGX Xavier tensorflow	14	1307	October 7, 2022
Difference between running the inference with trtexec and tensorrt python API Jetson AGX Xavier tensorrt , python	4	3130	October 18, 2021
No improvements from TensorRT on NVIDIA-AI-IOT/tf_trt_models TensorRT	3	1606	February 21, 2019
run yolov3-tiny with tensorRT model Jetson Nano	7	3512	January 4, 2020
Trtexec performance Jetson TX2 jetpack , tensorrt	6	3465	October 18, 2021
ONNX model with Jetson-Inference using GPU Jetson Xavier NX tensorrt , jetson-inference , onnx	38	5881	October 18, 2021
0.3fps when using yolov3_onnx in TensorRT examples provided by Nvidia in Jetson Nano Jetson Nano	8	1857	October 14, 2021
YOLOv3 TensorRT Inference Super Slow In Nano Jetson Nano	3	1117	October 14, 2021

How can i get 1000 FPS by running the inference with TensorRT Tiny-YOLOv3 (Jetson AGX Xavier)

Related topics