fixed that getting x and y from network.

cedriclmenard / irislandmarks.pytorch

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.

Apache License 2.0

65 stars 21 forks source link

fixed that getting x and y from network. #4

Open MainForm opened 2 years ago

MainForm commented 2 years ago

shape of eye is (1,5,3) so, "[ : , 0]" is need to be fixed to "[0, : , 0]".