https://github.com/erogol/seg-torch

Segmentation with deep learning
https://github.com/erogol/seg-torch

deep-learning image-segmentation lua seg-torch segmentation torch

Last synced: 2 months ago
JSON representation

Segmentation with deep learning

• Host: GitHub
• URL: https://github.com/erogol/seg-torch
• Owner: erogol
• Created: 2016-12-21T22:53:11.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2016-12-29T20:22:17.000Z (almost 8 years ago)
• Last Synced: 2024-10-03T12:36:01.836Z (3 months ago)
• Topics: deep-learning, image-segmentation, lua, seg-torch, segmentation, torch
• Language: Lua
• Size: 51.2 MB
• Stars: 37
• Watchers: 7
• Forks: 10
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Seg-Torch for Image Segmentation with Torch

This work was sparked by my personal research on simple segmentation methods based on deep learning. It is the harvest of two great predecessors;

* https://github.com/e-lab/ENet-training

* https://github.com/fedor-chervinskii/segnet-torch

  * (real project page) http://mi.eng.cam.ac.uk/projects/segnet/

However this code includes radical differences (such as data loading, augmentation, memory optimization) and it has more generic type of implementation suitable for use in any custom project. You only need to modify data-loader files data/custom-gen.lua and data/custom.lua.

Be warned this is susceptible to bugs. Any pull request is appreciated.

Check train_scripts/ for example execution.

# Models

* SegNet: Very simple encoder-decoder network, segmenting end2end

* EroNet: Very similar but it chops Batch-Normalization and uses ELU activation. It is lower in accuracy but faster in training.

# Example Results

exp_model/ includes a proof of concept on CamVid dataset. If you compare the results with the real-project this implementation has higher values interestingly (at least for me) :) .

Model will be shared on Dropbox, as soon as I find some time to do so.