update fastai version to 2, and refactor all necessary code.
rewrite the deep learning segmentation model: instead of returning only the Lepidoptera, it now recognizes the ruler and labels as well.
rewrite the classification models: instead of two models, id_position (returning "right way up" or "upside down") and id_gender (when "right way up", returning "male" or "female"), we now have id_gender returning three classes: "upside down", "male" or "female".
In this PR, we:
id_position
(returning "right way up" or "upside down") andid_gender
(when "right way up", returning "male" or "female"), we now haveid_gender
returning three classes: "upside down", "male" or "female".