ResNeXt#
The ResNeXt model is based on the “Aggregated Residual Transformations for Deep Neural Networks” paper.
Architecture overview#
This paper improves the ResNet architecture by increasing the width of bottleneck blocks
The key takeaways from the paper are the following:
increases the number of channels in bottlenecks
switches to group convolutions to balance the number of operations
Model builders#
The following model builders can be used to instantiate a ResNet 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.
|
ResNeXt-50 from "Aggregated Residual Transformations for Deep Neural Networks" |
|
ResNeXt-101 from "Aggregated Residual Transformations for Deep Neural Networks" |