Isolate mask

[jesus.parejo]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): Jetson
• DeepStream Version: 6.3
• JetPack Version (valid for Jetson only): 5.1
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs): Question
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hi there,

I am building a custom pipeline with Python in Deepstream. I use yolo-pose estimation to obtain keypoints of videos.

My end-goal is to feed another model with the mask output of the yolo-pose. In other words, the frame must be black with yolo skeletons. Is there any examples or “simple” way to archieve that?

Ty ^^

[junshengy]

You can refer to this sample.

people --> bodypose  --> preprocess --> bodypose classifer
                      |              |
          convert output tensor   NVDS_OBJ_META to classifer input tensor
              to NVDS_OBJ_META   

[jesus.parejo]

Sorry about that but I am not familiar with C, could you be a little more specific?

[junshengy]

There is no more advice. If you want to feed the output of the yolo-pose model into another model, set output-tensor-meta=1 in the yolo-pose configuration file, extract NvDsInferTensorMeta, and then do the preprocessing you need. This is the process of the example above.

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks