Res2Net

The Res2Net model is based on the “Res2Net: A New Multi-scale Backbone Architecture” paper.

Architecture overview

This paper replaces the bottleneck block of ResNet architectures by a multi-scale version.

The key takeaways from the paper are the following:

• switch to efficient multi-scale convolutions using a cascade of conv 3x3

• adapt the block for cardinality & SE blocks

Model builders

The following model builders can be used to instantiate a Res2Net model, with or without pre-trained weights. All the model builders internally rely on the holocron.models.classification.resnet.ResNet base class. Please refer to the source code for more details about this class.

res2net50_26w_4s([pretrained, checkpoint, ...])

Res2Net-50 26wx4s from "Res2Net: A New Multi-scale Backbone Architecture"