API aggregate_deep

The aggregate-deep strategies are end-to-end strategies that include an aggregation-like layer in the architecture of the computer vision model.

All computer vision models that can be used for training are available through the Torchvision library and can be found running:

peerannot modelinfo

All aggregation-based strategies are available running:

peerannot agginfo

All strategies are located at this direction on GitHub <https://github.com/peerannot/peerannot/tree/main/peerannot/models/agg_deep>

CoNAL.CoNAL	CoNAL (Common Noise Adaptation Layer), Chu et.al 2021 Implementation based from the unofficial repository https://github.com/seunghyukcho/CoNAL-pytorch
Crowdlayer.Crowdlayer	Crowdlayer (Rodrigues et. al 2018)

For more specifications on the architectures and blocks of the networks, please visit the strategy file documentation on GitHub <https://github.com/peerannot/peerannot/tree/main/peerannot/models/agg_deep>.