liuzhuang13/DenseNet
DenseNet is a deep convolutional neural network architecture for image classification introduced in a CVPR 2017 best paper.
Velocity · 7d
+1.4
★ / day
Trend
→steady
star history
This repository implements DenseNet, a dense connection architecture where each layer receives direct input from all preceding layers. The implementation is built on fb.resnet.torch (Lua/Torch7) and includes memory-efficient variants. DenseNet has been influential in computer vision, with multiple community implementations in PyTorch, TensorFlow, Caffe, and MXNet.