Skip to content
DenseNet tensorflow Implementation.
Branch: master
Clone or download
Latest commit 0dba62c Nov 14, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
datasets bugfix. Nov 14, 2017
models
utils
.gitignore gitignore .idea Oct 15, 2017
README.md
cnn_mnist_main.py
main.sh
requirements.txt fix bug. Oct 19, 2017
train_densenet_cifar.py
train_densenet_imagenet.py

README.md

Tensorflow Implementation of DenseNets

Two types of Densely Connected Convolutional Networks (DenseNets) are available:

  • DenseNet - without bottleneck layers
  • DenseNet-BC - with bottleneck layers

Each model can be tested on such datasets:

  • Cifar10
  • Cifar10+ (with data augmentation)
  • Cifar100
  • Cifar100+ (with data augmentation)
  • ImageNet

Example run:

python train_densenet_cifar.py

There are also many other implementations - they may be useful also.

Citation:

@article{Huang2016Densely,
       author = {Huang, Gao and Liu, Zhuang and Weinberger, Kilian Q.},
       title = {Densely Connected Convolutional Networks},
       journal = {arXiv preprint arXiv:1608.06993},
       year = {2016}
}

Dependencies

  • Model was tested with Python 2.7 with and without CUDA.
  • Model should work as expected with TensorFlow >= 1.4.

Repo supported with requirements file - so the easiest way to install all just run pip install -r requirements.txt.

You can’t perform that action at this time.