https://github.com/armyja/CHAOS_GCN

https://github.com/armyja/CHAOS_GCN

gcn pytorch

Last synced: 28 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/armyja/CHAOS_GCN
• Owner: armyja
• License: mit
• Created: 2019-03-28T06:51:37.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-05-23T07:15:42.000Z (over 5 years ago)
• Last Synced: 2024-08-03T06:01:13.992Z (4 months ago)
• Topics: gcn, pytorch
• Language: Python
• Size: 1.47 MB
• Stars: 5
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome_medical - CHAOS_GCN - |[Global Convolutional Network](https://github.com/SConsul/Global_Convolutional_Network)|-| (Segmentation)

README

        
# CHAOS_GCN

The impementation of [CHAOS - Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://chaos.grand-challenge.org/), using GCN([Global_Convolutional_Network

](https://github.com/SConsul/Global_Convolutional_Network))

## Dataset

## Data Analysis

## Model Optimization

weight: 1, 4, 8, 8, 4

learning rate: 1e-3

adagrad

google-net boundary refine

## TODO

Training set merge to one.(from training.txt)

Testing set generate one.(folders)

data agumentation

change 3 layer to 4 layer

multi-scale feature

SE-Block

liver

left kidney

right kidney

spleen

## Requirements