Skip to content
developmentseedPublic

About

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

Resources

Code of conduct

Security policy

Stars

34 stars

Watchers

46 watching

Forks

Latest commit

 

History

8 Commits

Folders and files

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

Code of conduct

Security policy

Stars

34 stars

Watchers

46 watching

Forks

Releases

Packages

Used by

Contributors

Languages