Comparison of DeepStream SSD Object Detection Performance on NVIDIA Xavier NX and AGX Xavier

Comparison of DeepStream SSD Object Detection Performance on NVIDIA Xavier NX and AGX Xavier

Jetson AGX Xavier | Jetson Xavier NX

17 February 2021

In this tutorial, we tested our NVIDIA Xavier NX and AGX Xavier's DeepStream performance in object detector sample. Our test sources are a video file (FPS:60, resolution:1920x1080, type:MP4) and 4 different cameras (FPS:25, resolution:1920x1080, type:RTSP).

NVIDIA Xavier NX Info:

NVIDIA AGX Xavier Info:

 
Performance Test Setup

To begin with, let's set our test environment with maximum power mode:

(for Xavier NX)

(for AGX Xavier)

Type these commands and continue other steps in both of them:


 

Then, copy sample_ssd_relu6.uff, ssd_coco_labels.txt and all configuration text files into /opt/nvidia/deepstream/deepstream/sources/objectDetector_SSD/ folder.

Change source URL (for source0, source1, source2 and source3) in each deepstream_app_config_ssd_rtsp... file (3 files).

 

 

Xavier NX Test Results

The performance of each test command:









 

AGX Xavier Test Results

The performance of each test command:








 

Comparison of Results

Xavier NX - Video Results (1080p, 60 FPS)
FP32 -> 12-13 FPS * 4 (48-52 FPS)
FP16 -> ~36 FPS * 4 (~144 FPS)

Xavier NX - RTSP Results (1080p, 25 FPS)
FP32 -> 12-13 FPS * 4 (48-52 FPS)
FP16 -> ~25 FPS (max) * 4 (~100 FPS)

AGX Xavier - Video Results (1080p, 60 FPS)
FP32 -> 21-22 FPS * 4 (84-88 FPS)
FP16 -> 55-56 FPS * 4 (220-224 FPS)

AGX Xavier - RTSP Results (1080p, 25 FPS)
FP32 -> 21-22 FPS * 4 (84-88 FPS)
FP16 -> 25-26 FPS (max) * 4 (100-104 FPS)

 You can find the zip here.