NvDsInferParseCustomBodyPose3DNet seems unused

• Hardware Platform dGPU
• DeepStream Version 6.1
• TensorRT Version 8.4.1
• NVIDIA GPU Driver Version 515.65.01
• Issue Type question

I am reading the BodyPose3DNet sample and I noticed that there is a bounding box parsing function in the sample.

First of all, why is there a bounding box parsing function for a body pose model? Then, why isn’t the function specified in the config with parse-bbox-func-name? The sample adds a probe anyway to process the tensor meta, so why have both?

Yes, they are parsed in the sgie_src_pad_buffer_probe function. The NvDsInferParseCustomBodyPose3DNet is a reserved sample interface and is not used. We’ll consider deleting the useless codes in the next version.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.