NVIDIA Developer Forums

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	Activity
Different result with same code and video on Xavier NX DeepStream SDK nvbugs	11	526	October 20, 2022
Custom detection ONNX model gives wrong outputs using nvinfer with DeepStream 5.1 DeepStream SDK	17	2929	October 12, 2021
Classifier result on onnx doesn't match Deepstream result DeepStream SDK tensorrt , tensorflow , nvbugs , onnx	35	3443	October 2, 2021
Output of tensorflow model in deepstream not accurately same to python inference DeepStream SDK	11	839	October 12, 2021
NvDsInferLayerInfo not giving expected no. of outputs DeepStream SDK	60	2197	October 12, 2021
Difference output when using Deepstream pipeline on difference GPU cards DeepStream SDK	2	367	March 16, 2022
Why is inferencing result different on dGPU vs Jetson given same model and input source? DeepStream SDK tensorrt , gstreamer	5	1510	December 28, 2021
Different segmentation mask between Jetson Nano and Desktop GPU DeepStream SDK	19	1756	October 12, 2021
Accuracy decreases when deploying darknet on jetson tx2 Jetson TX2	16	1304	October 18, 2021
Output of deepstream doesn't match with output of onnx model DeepStream SDK tensorrt , onnx	4	645	October 12, 2021