Skip to content
This repository has been archived by the owner on Jul 1, 2023. It is now read-only.

Latest commit

 

History

History
19 lines (14 loc) · 1.02 KB

README.md

File metadata and controls

19 lines (14 loc) · 1.02 KB
Raw

CNN Level Set

Official source code of our paper:

  • Kristiadi, Agustinus, and Pranowo Pranowo. "Deep Convolutional Level Set Method for Image Segmentation." Journal of ICT Research and Applications 11.3 (2017): 284-298. [pdf]

Setup

  1. Install miniconda
  2. Do conda env create
  3. Enter the env source activate cnn-levelset
  4. Install TensorFlow
  5. For TF installation without GPU, run chmod +x tools/tf_setup.sh && sh tools/tf_setup.sh
  6. Download Pascal VOC 2012 dataset, from: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/#devkit

Reproducing experimental results

  1. Download dataset that is being used for the paper. Download from here, then unzip it in the main project directory. See data/README.txt for documentations of these features
  2. Change cnnlevelset/config.py
  3. Run python experiment.py