SK-TDA4VM: Help for postprocessing depth estimation model

Hareendran M G

Part Number: SK-TDA4VM
Other Parts Discussed in Thread: TDA4VM

Hello experts,

Is there any examples code for postprocessing the depth estimation model (fast depth) in the TDA4VM.
I have compiled the model artifacts and then i realized there is only support for classification, segmentation and object detection.
I looked into this repo for adding custom postprocessing, but it did focussing on drawing boudaries over the image. i want to get the depth map of the image.

Thank you in advance for your support.

Regards,
Hareendran

over 2 years ago

0 Manu Mathew over 2 years ago

TI__Genius 11376 points

It seems this question was previously asked in another discussion thread. Adding that here for context. https://github.com/TexasInstruments/edgeai-modelzoo/issues/12

0 Manu Mathew over 2 years ago in reply to Manu Mathew

TI__Genius 11376 points

Currently we do not have depth post processing support in https://github.com/TexasInstruments/edgeai-gst-apps

edgeai-gst-apps has popular usecases such as classification, segmentation and detection. The customers are expected to extend/modify it for other applications. It is python code and you can easily modify it.

Several people who used edgeai-gst-apps have also published their own forks that extends the basic capability. Here are the extensions. You can use these as examples for how to extend it.

https://github.com/TexasInstruments/edgeai-gst-apps-barcode-reader

https://github.com/TexasInstruments/edgeai-gst-apps-retail-checkout

https://github.com/TexasInstruments/edgeai-gst-apps-defect-detection

https://github.com/TexasInstruments/edgeai-gst-apps-6d-pose

https://github.com/TexasInstruments/edgeai-gst-apps-human-pose

https://github.com/TexasInstruments/edgeai-gst-apps-lpr