Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) jetson agx orin
• DeepStream Version 6.3
**• JetPack Version (valid for Jetson only)**5.1
• TensorRT Version8.5
I want to know how long it takes for each frame of the image to be processed by the model. What should I do? Where can I find the code for model processing of images?
I want to output the inference time for each frame of an image in my application. I made the modification in the code of/deepstream/deepstream-6.3/sources/apps/sample_apps/deepstream-app,Where should I add timestamp records? How to achieve printing of inference time for each frame of image?
I want to output the inference time for each frame of an image in my application. I made the modification in the code of/deepstream/deepstream-6.3/sources/apps/sample_apps/deepstream-app,Where should I add timestamp records? How to achieve printing of inference time for each frame of image?
Please refer to this FAQ to obtain latency
thank！it worked.by the way ,could you Please tell me what the unit of this time is? Microseconds?
Comp name = primary_gie in_system_timestamp = 1726637073085.069092 out_system_timestamp = 1726637073095.926025 component latency= 10.856934
Comp name = tiled_display_tiler in_system_timestamp = 1726637073103.399902 out_system_timestamp = 1726637073112.745117 component latency= 9.345215
Comp name = osd_conv in_system_timestamp = 1726637073112.947021 out_system_timestamp = 1726637073115.423096 component latency= 2.476074
Comp name = nvosd0 in_system_timestamp = 1726637073115.521973 out_system_timestamp = 1726637073115.541992 component latency= 0.020020
Yes,This is the time acquired using gettimeofday. This is the time spent processing in element, which is slightly longer than the time spent on tensorrt.
You can also refer to this answer to get more precise results
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.