initial commit

.gitignore

@@ -0,0 +1,19 @@
+caffe
+
+# data for training
+*.png
+*.jpg
+*.txt
+
+# files created in training directory
+*.caffemodel
+training_log
+testing_log
+snapshot
+
+# temporarily created files
+*~
+*.swp
+*.tar.gz
+*.tar
+*.zip

LICENSE

@@ -0,0 +1,56 @@
+Copyright Pohang University of Science and Technology. All rights reserved.
+
+Contact persons:
+Hyeonowo Noh (hyeonwoonoh_ <at> postech.ac.kr)
+
+This software is being made available for individual research use only.
+Any commercial use or redistribution of this software requires a license from
+the Pohang University of Science and Technology.
+
+You may use this work subject to the following conditions:
+
+1. This work is provided "as is" by the copyright holder, with
+absolutely no warranties of correctness, fitness, intellectual property
+ownership, or anything else whatsoever.  You use the work
+entirely at your own risk.  The copyright holder will not be liable for
+any legal damages whatsoever connected with the use of this work.
+
+2. The copyright holder retain all copyright to the work. All copies of
+the work and all works derived from it must contain (1) this copyright
+notice, and (2) additional notices describing the content, dates and
+copyright holder of modifications or additions made to the work, if
+any, including distribution and use conditions and intellectual property
+claims.  Derived works must be clearly distinguished from the original
+work, both by name and by the prominent inclusion of explicit
+descriptions of overlaps and differences.
+
+3. The names and trademarks of the copyright holder may not be used in
+advertising or publicity related to this work without specific prior
+written permission. 
+
+4. In return for the free use of this work, you are requested, but not
+legally required, to do the following:
+
+* If you become aware of factors that may significantly affect other
+  users of the work, for example major bugs or
+  deficiencies or possible intellectual property issues, you are
+  requested to report them to the copyright holder, if possible
+  including redistributable fixes or workarounds.
+
+* If you use the work in scientific research or as part of a larger
+  software system, you are requested to cite the use in any related
+  publications or technical documentation. The work is based upon:
+
+    Hyeonwoo Noh, Seunghoon Hong, Bohyung Han.
+    Learning Deconvolution Network for Semantic Segmentation
+    arXiv:1505.04366, 2015.
+
+    @article{noh2015learning,
+      title={Learning Deconvolution Network for Semantic Segmentation},
+      author={Noh, Hyeonwoo and Hong, Seunghoon and Han, Bohyung},
+      journal={arXiv preprint arXiv:1505.04366},
+      year={2015}
+    }
+
+This copyright notice must be retained with all copies of the software,
+including any modified or derived versions.

README.md

@@ -0,0 +1,68 @@
+## DeconvNet: *Learning Deconvolution Network for Semantic Segmentation*
+
+Created by Hyeonwoo Noh, Seunghoon Hong and Bohyung Han at POSTECH
+
+Acknowledgements: Thanks to Yangqing Jia and the BVLC team for creating Caffe.
+
+### Introduction
+
+DeconvNet is state-of-the-art semantic segmentation system that combines bottom-up region proposals with multi-layer decovolution network.
+
+Detailed description of the system will be provided by our technical report [arXiv tech report] http://arxiv.org/abs/1505.04366
+
+### Citation
+
+If you're using this code in a publication, please cite our papers.
+
+Hyeonwoo Noh, Seunghoon Hong, Bohyung Han.
+
+Learning Deconvolution Network for Semantic Segmentation
+
+arXiv:1505.04366, 2015.
+
+    @article{noh2015learning,
+      title={Learning Deconvolution Network for Semantic Segmentation},
+      author={Noh, Hyeonwoo and Hong, Seunghoon and Han, Bohyung},
+      journal={arXiv preprint arXiv:1505.04366},
+      year={2015}
+    }
+
+
+### Licence
+
+This software is being made available for research purpose only.
+
+check LICENSE file for details.
+
+### System Requirements
+
+This software is tested on Ubuntu 14.04 LTS (64bit).
+
+**Prerequisites** 
+  0. MATLAB (tested with 2014b on 64-bit Linux)
+  0. prerequisites for caffe(http://caffe.berkeleyvision.org/installation.html#prequequisites)
+
+### Installing DeconvNet
+
+** By running "setup.sh" you can download all the necessary file for training and inference include: **
+0. caffe: you need modified version of caffe which support DeconvNet - https://github.com/HyeonwooNoh/caffe.git
+0. data: data used for training stage 1 and 2
+0. model: caffemodel of trained DeconvNet and other caffemodels required for training
+
+### Training DeconvNet
+
+Training scripts are included in "./training/" directory
+
+You can simply run following scripts in order to train DeconvNet
+0. 001\_start\_train.sh : script for first stage training
+0. 002\_start\_train.sh : script for second stage training
+0. 003\_start\_make\_bn\_layer\_testable : script converting trained DeconvNet with bn layer to inference mode
+
+
+
+
+
+
+
+
+

data/VOC2012/README.md

@@ -0,0 +1 @@
+**This directory should contain data used for training stage 1 and 2**

data/get_data.sh

@@ -0,0 +1,31 @@
+# download and extract data necessary for training
+cd VOC2012
+
+# download and extract stage 1 training data
+wget http://cvlab.postech.ac.kr/research/deconvnet/data/VOC_OBJECT.tar.gz
+tar -zxvf VOC_OBJECT.tar.gz
+rm -rf VOC_OBJECT.tar.gz
+
+# download and extract stage 2 training data
+wget http://cvlab.postech.ac.kr/research/deconvnet/data/VOC2012_SEG_AUG.tar.gz
+tar -zxvf VOC2012_SEG_AUG.tar.gz
+rm -rf VOC2012_SEG_AUG.tar.gz
+
+cd ..
+
+# download and extract imagesets necessary for training
+cd imagesets
+
+# download and extract stage 1 training data
+wget http://cvlab.postech.ac.kr/research/deconvnet/data/stage_1_train_imgset.tar.gz
+tar -zxvf stage_1_train_imgset.tar.gz
+rm -rf stage_1_train_imgset.tar.gz
+
+# download and extract stage 2 training data
+wget http://cvlab.postech.ac.kr/research/deconvnet/data/stage_2_train_imgset.tar.gz
+tar -zxvf stage_2_train_imgset.tar.gz
+rm -rf stage_2_train_imgset.tar.gz
+
+cd ..
+
+

data/imagesets/README.md

@@ -0,0 +1 @@
+**This directory contains image sets used for training stage 1 and 2**