SKNet

The ResNet model is based on the “Selective Kernel Networks” paper.

Architecture overview

This paper revisits the concept of having a dynamic receptive field selection in convolutional blocks.

The key takeaways from the paper are the following:

• performs convolutions with multiple kernel sizes

• implements a cross-channel attention mechanism

Model builders

The following model builders can be used to instantiate a SKNet 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.

sknet50([pretrained, checkpoint, progress])	SKNet-50 from "Selective Kernel Networks"
sknet101([pretrained, checkpoint, progress])	SKNet-101 from "Selective Kernel Networks"
sknet152([pretrained, checkpoint, progress])	SKNet-152 from "Selective Kernel Networks"