Please provide complete information as applicable to your setup. **• Hardware Platform (Jetson / GPU): Xavier AGX / Orin NX **• DeepStream Version: 6.0 / 6.2 **• JetPack Version (valid for Jetson only): 4.6 / 5.1 **• TensorRT Version: 8.0.1.6 / 8.5.2.2 **• NVIDIA GPU Driver Version (valid for GPU only): Xavier AGX / Orin NX **• Issue Type( questions, new requirements, bugs): Question We use the same weights to convert the trt engine through the “objectDetector_Yolo” plugin in Deepstream SDK. Afterwards, we use Deepstream for image inference. However, the same image gets different inference results on different machines.

This is my config file, and I executed the result using deepstream-image-decode-app. dstest_image_decode_pgie_config.txt (818 Bytes)

Can you share the application deepstream config? Want to check the pre-processing part, e.g. if using VIC or GPU to do the processing.

I am using the deepstream-image-decode-app application and it only has this config, dstest_image_decode_pgie_config.txt. This is a sample application of the Deepstream SDK, and its path is /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-image-decode-test.

Hi @kpernos9 , Could you try to use GPU instead of VIC to do scaling and conversion for nvinfer, nvstreammux and nvvideoconvert plugins? https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html [image] https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvstreammux.html [image] https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvvideoconvert.html [image]

Hi @mchi , We observed that the input file dumped varies on different scaling-compute-hw values which means GPU/VIC is used. We want to clarify that why the same settings get different scaling input. And it leads to different detection results.

[image] kpernos9: dstest_image_decode_pgie_config.txt (818 Bytes) I’m sorry, I uploaded the wrong configuration file earlier. This correct one is dstest_image_decode_pgie_config.txt (780 Bytes), which doesn’t have the settings for scaling-filter and scaling-compute-hw.

Hi @mchi, I tried modifying the code and config file to use GPU, and this is my output data. Detection_result_different_io_data_gpu.7z (1.4 MB)

Hi @kpernos9 @lin.bruno What’s the DeepStream version are you using? [image]

Both are used, Xavier AGX using DS6.0 and Orin NX using DS6.2.

Hi @mchi , Is the difference of scaled input resulted from DS version or HW platform? please advise. Thanks.

Detection result is different between Xavier and Orin for the same model and weights

Accelerated Computing Intelligent Video Analytics DeepStream SDK

kpernos9 May 16, 2023, 1:37am 25

Hi @junshengy,
Here is the output data based on the patch you provided, including the content of the patch linke to DeepStream SDK FAQ - #9 by mchi.
Detection_result_different_io_data_with_plugin.7z (2.8 MB)

Topic		Replies	Views
Different result with same code and video on Xavier NX DeepStream SDK nvbugs	10	717	October 20, 2022
Detections change in Deepstream 6.2 DeepStream SDK tensorrt , camera , cuda , kernel , gstreamer , yolo , python , deepstream , deepstream61	21	2264	July 31, 2023
Custom detection ONNX model gives wrong outputs using nvinfer with DeepStream 5.1 DeepStream SDK	16	3273	September 27, 2021
Classifier result on onnx doesn't match Deepstream result DeepStream SDK tensorrt , tensorflow , nvbugs , onnx	34	4097	July 28, 2021
Deepstream and TensorRT inference results difference DeepStream SDK deepstream	7	426	December 9, 2025
Difference output when using Deepstream pipeline on difference GPU cards DeepStream SDK	1	484	March 16, 2022
NVIDIA-OCDR tensorrt worked on dGPU but no on Jetson Xavier DeepStream SDK	24	1600	January 7, 2024
Why is inferencing result different on dGPU vs Jetson given same model and input source? DeepStream SDK tensorrt , gstreamer	4	1666	December 8, 2021
Output of tensorflow model in deepstream not accurately same to python inference DeepStream SDK	10	1068	December 15, 2020
AGX Orin DeepStream 6.1.1 FPS of deepstream-app use DLA low than AGX Xavier DeepStream SDK	18	1392	November 2, 2022

Detection result is different between Xavier and Orin for the same model and weights

Related topics