I am new to Tensorflow (absolut beginner). I am researching solutions for a project i’m working on and was wondering if someone could point me in the right direction.
I used the model movenet/singlepose/thunder for pose estimation in images where only the lower body is seen (from hip downwards). The images are rather dark and the results are not really good yet.
So my question is basically: Is it possible (even easy maybe) to improve existing models for this specific situation? Would it be better/necessary to train an new model? I would really appreciate any tips where I can find the best information about how time consuming it is to train or modify a model and where to start.