Skip to content

[This project has moved to ChainerCV] Chainer Implementation of Fully Convolutional Instance-aware Semantic Segmentation

License

Notifications You must be signed in to change notification settings

knorth55/chainer-fcis

Repository files navigation

This project has moved to ChainerCV.

chainer-fcis - FCIS

PyPI Version Build Status

Example

This is Chainer implementation of Fully Convolutional Instance-aware Semantic Segmentation.

Original Mxnet repository is msracver/FCIS.

Requirement

Additional Requirement

Notification

  • Only GPU implementation, No CPU implementation yet.

TODO

  • VOC
    • Reproduce original repo training accuracy
  • COCO
    • Reproduce original repo training accuracy
    • Refine evaluation code

Installation

We recommend to use Anacoda.

# Requirement installation
conda create -n fcis python=2.7
conda install -c menpo opencv
source activate fcis
pip install cupy

# Installation
pip install fcis

Inference

cd examples/coco/
python demo.py

Above is our implementation output, and below is original.

Training

cd examples/voc/
python train.py

LICENSE

MIT LICENSE

Powered by DL HACKS