First release of aistron
Major features:
-
Data pipeline: We aim to standardize the annotations of existing AIS datasets so that the methods can be easily implemented and generalized. This diagram illustrates the data pipeline of aistron
-
Amodal Instance Segmentation Evaluator: AIStron helps compute the performance of both visible and amodal masks. If a method provides both pred_visible_masks and pred_amodal_masks in its predictions, both performances will be computed. If only the conventional pred_masks are provided, only the amodal performance is computed.
-
Utilities: We offer an amodal visualizer utility that allows you to visualize the ground truth or predictions with option to choose between visible masks, occluder masks and amodal masks.
-
Builtin-Methods: Amodal Mask R-CNN