ResNet

The ResNet model is based on the “Deep Residual Learning for Image Recognition” paper.

Architecture overview

This paper introduces a few tricks to maximize the depth of convolutional architectures that can be trained.

The key takeaways from the paper are the following:

• add a shortcut connection in bottleneck blocks to ease the gradient flow

• extensive use of batch normalization layers

Model builders

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

resnet18([pretrained, checkpoint, progress])	ResNet-18 from "Deep Residual Learning for Image Recognition"
resnet34([pretrained, checkpoint, progress])	ResNet-34 from "Deep Residual Learning for Image Recognition"
resnet50([pretrained, checkpoint, progress])	ResNet-50 from "Deep Residual Learning for Image Recognition"
resnet50d([pretrained, checkpoint, progress])	ResNet-50-D from "Bag of Tricks for Image Classification with Convolutional Neural Networks"
resnet101([pretrained, checkpoint, progress])	ResNet-101 from "Deep Residual Learning for Image Recognition"
resnet152([pretrained, checkpoint, progress])	ResNet-152 from "Deep Residual Learning for Image Recognition"