TridentNet

The ResNeXt model is based on the “Scale-Aware Trident Networks for Object Detection” 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 bottleneck to a 3 branch system

• all parallel branches share the same parameters but using different dilation values

Model builders

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

tridentnet50([pretrained, progress])

TridentNet-50 from "Scale-Aware Trident Networks for Object Detection"