https://github.com/divelab/deepem3d

https://github.com/divelab/deepem3d

Last synced: 2 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/divelab/deepem3d
• Owner: divelab
• License: mit
• Created: 2017-02-15T07:12:12.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-02-03T00:03:35.000Z (almost 7 years ago)
• Last Synced: 2023-10-20T19:22:04.652Z (about 1 year ago)
• Language: Matlab
• Size: 26.4 KB
• Stars: 17
• Watchers: 4
• Forks: 4
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# DeepEM3D

This is the implementation code for paper submitted to Bioinformatics: **"DeepEM3D: Approaching human-level performance on 3D anisotropic EM image segmentation "**

# Required environment:

C++, bash shell, matlab, Cuda7.5

# Data

(1). Register at:

http://brainiac2.mit.edu/SNEMI3D/user/register

(2). Login in and download data at:

http://brainiac2.mit.edu/SNEMI3D/downloads

(3) Convert image files into h5 file that contains **\data** and **\label** sets.

# Code

1. To generate boundary labels:  

run matlab scripts:  */scripts/create_new_vertical_closed_label.m*

2. To generate all data h5 files (train, valid, test):   

run matlab scripts: */scripts/read_data_write_data_with_enhanced_labels.m*

3. To train and predict netwroks models:  

run shell scripts:  */model/inception_residual_train_prediction_xfm/train.sh* **or** *predict.sh*

4. To generate segmentation on test set:  

run matlab scripts */model/inception_residual_train_prediction_3fm/run_segmentation_on_test_set.m*