I am implementing Tensorflow-lite for pose detection using webcam's live feed.
I am familiar with Posenet implementation using javascript from https://github.com/tensorflow/tfjs-models/tree/master/posenet
I was expecting when i call output_data = interpreter.get_tensor(output_details[0]['index'])
I would get the same size array as what the posenet javascript version is giving back. What I get is an array of (1,23,17,17) size.
How do I go about converting that output array into one similar to what is found in that posenet website?
I tried to use the code snippet from this person's Java implementation but it does not seem to be working correctly: How to use outputs of posenet model in tflite
