Face landmarks (fpenet)

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi! i am using the model Fpenet to get face landmarks in deepstream, but i dont know how get the landmarks, im using this line:
landmarks = buffer_as_nparray(layer.buffer,(80,))
this return negative values and only a list with 80 values ,

image
in the nvidia documentation it tells me that you can get an output of (N,2) where you get the coordinates of
the landmarks, I would like to know how or what command I should use to obtain those landmarks

3

do you still need support? please refer to this code: deepstream_tao_apps/deepstream_faciallandmark_app.cpp at master · NVIDIA-AI-IOT/deepstream_tao_apps · GitHub

4

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

5

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