DarkNet

The DarkNet model is based on the “You Only Look Once: Unified, Real-Time Object Detection” paper.

Architecture overview

This paper introduces a highway network with powerful feature representation abilities.

The key takeaways from the paper are the following:

• improves the Inception architecture by using conv1x1

• replaces ReLU by LeakyReLU

Model builders

The following model builders can be used to instantiate a DarknetV1 model, with or without pre-trained weights. All the model builders internally rely on the holocron.models.classification.darknet.DarknetV1 base class. Please refer to the source code for more details about this class.

darknet24([pretrained, progress])

Darknet-24 from "You Only Look Once: Unified, Real-Time Object Detection"