Skip to content

Latest commit

 

History

History
39 lines (31 loc) · 1.2 KB

README.md

File metadata and controls

39 lines (31 loc) · 1.2 KB
Raw

DenseNet-Tensorflow

Reimplementation of DenseNet on Image Recognition

Densely Connected Convolutional Networks(DenseNet), won the Best Paper Award on CVPR 2017.

This is an (re-)implementation of DenseNet in TensorFlow for image recognition tasks. The (re-)implementation is based on official Torch DenseNet with Tensorflow Slim.

DenseNet Table

In the paper, DenseNet-264 seems to be a typo, since there is no way the number of layers to be an even number. See 121, 169, 201, if you add up, which is 1 + 6 x 2 + 1 + 12 x 2 + 1 + 64 x 2 + 1 + 48 x 2 + 1 + 1 = 265.

Features

  • DenseNet-B, DenseNet-C, DenseNet-BC
  • DenseNet-121, DenseNet-169, DenseNet-201, DenseNet-265
  • Training on CIFAR
  • Training on SVHN
  • Training on ImageNet

Requirement

Tensorflow 1.4

python 3.5
tensorflow 1.4
CUDA  8.0
cuDNN 6.0

Tensorflow 1.2

python 3.5
tensorflow 1.2
CUDA  8.0
cuDNN 5.1

Installation

pip3 install -r requirements.txt