irislandmarks.pytorch
irislandmarks.pytorch copied to clipboard
PyTorch implementation of Google's Mediapipe Iris Landmark model. The original code uses TFLite and their mediapipe workflow, which wouldn't work well with my codebase.
shape of eye is (1,5,3) so, "[ : , 0]" is need to be fixed to "[0, : , 0]".
Hi cedriclmenard, Could you please provide the training code for this repo that would be very helpful. Thanks
do you know the "Standard Score Filter" part?, what does the F-influnce and F-annealing stand for?