ReXNet

The ResNet model is based on the “ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network” paper.

Architecture overview

This paper investigates the effect of channel configuration in convolutional bottlenecks.

The key takeaways from the paper are the following:

• increasing the depth ratio of conv 1x1 and inverted bottlenecks

• replace ReLU6 with SiLU

Model builders

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

rexnet1_0x([pretrained, checkpoint, progress])	ReXNet-1.0x from "ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network"
rexnet1_3x([pretrained, checkpoint, progress])	ReXNet-1.3x from "ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network"
rexnet1_5x([pretrained, checkpoint, progress])	ReXNet-1.5x from "ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network"
rexnet2_0x([pretrained, checkpoint, progress])	ReXNet-2.0x from "ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network"
rexnet2_2x([pretrained, checkpoint, progress])	ReXNet-2.2x from "ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network"