LibMTL.weighting.GLS

class GLS[source]

Bases: LibMTL.weighting.abstract_weighting.AbsWeighting

Geometric Loss Strategy (GLS).

This method is proposed in MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning (CVPR 2019 workshop) and implemented by us.

backward(self, losses, **kwargs)[source]
Parameters

  • losses (list) – A list of losses of each task.

  • kwargs (dict) – A dictionary of hyperparameters of weighting methods.