Skip to content

tsingjinyun/caffe-fcn

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FCN

This is a simple, working example of "image segmentation" using a neural net trained by Jonathan Long and Evan Shelhamer, as described in Fully Convolutional Networks for Semantic Segmentation.

Trained model weights are from the Caffe Model Zoo.

Setup

Clone this repo, then:

# download weights from model zoo
CAFFE_ROOT=/path/to/caffe/repo make fcn-8s/fcn-8s-pascalcontext.caffemodel
# build docker container
make build-docker

Usage (iPython/Jupyter Notebook)

If you're running docker host in a VM (i.e., on a Mac), make sure to forward port 8888.

Then do:

docker run -it --rm -v $(pwd):/workspace -p 8888:8888 caffe-fcn ./notebook.sh

Then go to http://localhost:8888

About

Run Long and Shelhamer's FCN image segmentation network using Caffe

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 98.0%
  • Python 1.6%
  • Other 0.4%