Viet-Anh on Software Logo

What is: Darknet-19?

SourceYOLO9000: Better, Faster, Stronger
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Darknet-19 is a convolutional neural network that is used as the backbone of YOLOv2. Similar to the VGG models it mostly uses 3×33 \times 3 filters and doubles the number of channels after every pooling step. Following the work on Network in Network (NIN) it uses global average pooling to make predictions as well as 1×11 \times 1 filters to compress the feature representation between 3×33 \times 3 convolutions. Batch Normalization is used to stabilize training, speed up convergence, and regularize the model batch.