Exercise (Designing a Darknet-19 Architecture)
Explore how to design and implement the Darknet-19 backbone architecture used in YOLOv2 and YOLOv7. Understand convolutional blocks, batch normalization, activation functions, pooling layers, and forward pass logic to build a foundational neural network component for object detection.
We'll cover the following...
Let’s dive into the practical applications of various architectural concepts, like the backbone and neck.
Supplemental reading materials
YOLO v1 by Joseph Redmon, Santosh Divvala, Ali Farhadi, and Ross Girshick is the first research paper of the YOLO series, which is an easy-to-read paper and highly recommended to get an in-depth knowledge of YOLO fundamentals.1
Darknet-19 is a backbone that was used in YOLOv2. The YOLOv2 paper contains the architecture of the backbone, which helps in implementing the backbone from scratch. This is an interesting paper that explains in detail the approaches tried before finalizing the YOLOv2 model ...