DarkNetV4

The DarkNetV4 model is based on the “CSPNet: A New Backbone that can Enhance Learning Capability of CNN” paper.

Architecture overview

This paper makes a more powerful version than its predecedors by increasing depth and using ResNet tricks.

The key takeaways from the paper are the following:

• add cross-path connections to its predecessors

• explores newer non-linearities

Model builders

The following model builders can be used to instantiate a DarknetV3 model, with or without pre-trained weights. All the model builders internally rely on the holocron.models.classification.darknetv4.DarknetV4 base class. Please refer to the source code for more details about this class.

cspdarknet53([pretrained, checkpoint, progress])	CSP-Darknet-53 from "CSPNet: A New Backbone that can Enhance Learning Capability of CNN"
cspdarknet53_mish([pretrained, checkpoint, ...])	Modified version of CSP-Darknet-53 from "CSPNet: A New Backbone that can Enhance Learning Capability of CNN" with Mish as activation layer and DropBlock as regularization layer.