https://github.com/t-hanya/chainer-DenseNet
Densely Connected Convolutional Networks by Chainer
https://github.com/t-hanya/chainer-DenseNet
Last synced: about 2 months ago
JSON representation
Densely Connected Convolutional Networks by Chainer
- Host: GitHub
- URL: https://github.com/t-hanya/chainer-DenseNet
- Owner: t-hanya
- Created: 2016-09-03T04:40:59.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2017-11-12T14:41:27.000Z (over 7 years ago)
- Last Synced: 2024-11-18T10:34:46.128Z (7 months ago)
- Language: Python
- Size: 186 KB
- Stars: 5
- Watchers: 3
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.rst
Awesome Lists containing this project
- awesome-very-deep-learning - Chainer Implementation
README
===================================================
Densely Connected Convolutional Networks by Chainer
===================================================
This is an experimental implementation of `Densely Connected Convolutional Networks `_ using Chainer framework.
- Original paper: https://arxiv.org/abs/1608.06993
- Official implementation: https://github.com/liuzhuang13/DenseNet
Requirements
============
- `Chainer `_ 2.0+
- `CuPy `_ 1.0+
Usage
=====
Train a DenseNet on CIFAR-10 dataset using::
python code/train.py --gpu 0 -o result
Visualize training result using::
python code/visualize.py result/log -o result
Sample Result
=============
.. image:: img/training_loss.png
:width: 400
.. image:: img/test_error.png
:width: 400
- Model parameters: L = 40, k = 12
- Batch size: 64
- Dataset: C10 (CIFAR-10 dataset without data augmentation)