AI Based Object Redaction/Performance: Difference between revisions

From RidgeRun Developer Wiki
(Replaced content with "<noinclude> {{AI Based Object Redaction/Head|previous=|next=|metakeywords=}} </noinclude> <!---- {{DISPLAYTITLE:AI Based Object Redaction/AI Based Object Redaction - Overview|noerror}} ----> The library has two major components: the detection of the desired object done by the ONNX model and the application of the redaction effect done either by the CPU or GPU. For testing purposes, take into account the following points: * Jetpack 5.1.X * Tested with GPU+CPU and...")
Tag: Replaced
mNo edit summary
 
(6 intermediate revisions by 3 users not shown)
Line 1: Line 1:
<noinclude>
<noinclude>
{{AI Based Object Redaction/Head|previous=|next=|metakeywords=}}
{{AI Based Object Redaction/Head|previous=Examples/GStreamer Pipelines|next=Performance/Jetson_Xavier_NX|metakeywords=}}
</noinclude>
</noinclude>


<!----
<!----
{{DISPLAYTITLE:AI Based Object Redaction/AI Based Object Redaction - Overview|noerror}}
{{DISPLAYTITLE:AI Based Object Redaction - Performance|noerror}}
---->
---->




The library has two major components: the detection of the desired object done by the ONNX model and the application of the redaction effect done either by the CPU or GPU.
The library has four major consuming methods: convert the input buffer to the desired format and size of the AI model, the detection of the desired object done by the ONNX model, tracking and the application of the redaction effect.


For testing purposes, take into account the following points:
For testing purposes, take into account the following points:
* Jetpack 5.1.X
* Jetpack 5.1.X
* Tested with GPU+CPU and CPU only. For GPU, execution is done with TensorRT and CUDA.
* Tested with GPU and CPU only. For GPU, execution is done with TensorRT and CUDA.
* The library offers two approaches: each method used separately and all together using the apply method.  
* The library offers two approaches: each method used separately and all together using the apply method.  
* The metrics measured are CPU and GPU consumption, processing time, and FPS.
* The metrics measured are CPU and GPU consumption, processing time, and FPS.
* The tracker is implemented only with support for CPU.  
* The tracker is implemented only with support for CPU.  


Check the following links for performance on:  
Check the following links for performance:
* [[https://developer.ridgerun.com/wiki/index.php/AI_Based_Object_Redaction/Performance/Jetson_Xavier_AGX#Xavier_AGX|Jetson Xavier NX]]
 
*;[[AI_Based_Object_Redaction/Performance/Jetson_Xavier_NX|Jetson Xavier NX]]
*;[[AI_Based_Object_Redaction/Performance/Jetson_Xavier_AGX|Jetson Xavier AGX]]


<noinclude>
<noinclude>
{{AI Based Object Redaction/Foot||}}
{{AI Based Object Redaction/Foot|Examples/GStreamer Pipelines|Performance/Jetson_Xavier_NX}}
</noinclude>
</noinclude>

Latest revision as of 19:36, 2 January 2024


Index






The library has four major consuming methods: convert the input buffer to the desired format and size of the AI model, the detection of the desired object done by the ONNX model, tracking and the application of the redaction effect.

For testing purposes, take into account the following points:

  • Jetpack 5.1.X
  • Tested with GPU and CPU only. For GPU, execution is done with TensorRT and CUDA.
  • The library offers two approaches: each method used separately and all together using the apply method.
  • The metrics measured are CPU and GPU consumption, processing time, and FPS.
  • The tracker is implemented only with support for CPU.

Check the following links for performance:


Index