DarkNetV3

The DarkNetV3 model is based on the “YOLOv3: An Incremental Improvement” 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:

• adds residual connection compared to DarkNetV2

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.darknetv3.DarknetV3 base class. Please refer to the source code for more details about this class.

darknet53([pretrained, checkpoint, progress])

Darknet-53 from "YOLOv3: An Incremental Improvement"