titu1994/DenseNet
A Keras implementation of DenseNet, a deep learning convolutional neural network architecture.
Not currently ranked — collecting fresh signals.
star history
This repository provides an implementation of DenseNet (Densely Connected Convolutional Networks) in Keras, supporting both standard and BC (Bottleneck-Compressed) variants. The architecture features dense connectivity where each layer receives feature maps from all preceding layers, and uses growth rate parameters to control feature map expansion. The implementation achieves state-of-the-art performance on CIFAR-10 and CIFAR-100 datasets, with DenseNet-BC-190-40 reaching 3.46% error on CIFAR-10.
Frequently asked
- What is titu1994/DenseNet?
- A Keras implementation of DenseNet, a deep learning convolutional neural network architecture.
- Is DenseNet open source?
- Yes — titu1994/DenseNet is open source, released under the MIT license.
- What language is DenseNet written in?
- titu1994/DenseNet is primarily written in Python.
- How popular is DenseNet?
- titu1994/DenseNet has 709 stars on GitHub.
- Where can I find DenseNet?
- titu1994/DenseNet is on GitHub at https://github.com/titu1994/DenseNet.