Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/knorth55/chainer-fcis
[This project has moved to ChainerCV] Chainer Implementation of Fully Convolutional Instance-aware Semantic Segmentation
https://github.com/knorth55/chainer-fcis
chainer chainercv chainermn computer-vision convolutional-neural-networks deep-learning inference instance-segmentation machine-learning python training
Last synced: about 2 months ago
JSON representation
[This project has moved to ChainerCV] Chainer Implementation of Fully Convolutional Instance-aware Semantic Segmentation
- Host: GitHub
- URL: https://github.com/knorth55/chainer-fcis
- Owner: knorth55
- License: mit
- Created: 2017-08-09T16:09:31.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2020-05-08T17:51:54.000Z (over 4 years ago)
- Last Synced: 2024-04-26T09:20:39.591Z (8 months ago)
- Topics: chainer, chainercv, chainermn, computer-vision, convolutional-neural-networks, deep-learning, inference, instance-segmentation, machine-learning, python, training
- Language: Python
- Homepage:
- Size: 5.06 MB
- Stars: 43
- Watchers: 5
- Forks: 8
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# This project has moved to [ChainerCV](https://github.com/chainer/chainercv).
chainer-fcis - FCIS
===================
[![PyPI Version](https://img.shields.io/pypi/v/fcis.svg)](https://pypi.python.org/pypi/fcis)
![Build Status](https://travis-ci.org/knorth55/chainer-fcis.svg?branch=master)![Example](static/coco_example.png)
This is [Chainer](https://github.com/chainer/chainer) implementation of [Fully Convolutional Instance-aware Semantic Segmentation](https://arxiv.org/abs/1611.07709).
Original Mxnet repository is [msracver/FCIS](https://github.com/msracver/FCIS).
Requirement
------------ [CuPy](https://github.com/cupy/cupy)
- [Chainer](https://github.com/chainer/chainer)
- [ChainerCV](https://github.com/chainer/chainercv)
- OpenCV2Additional Requirement
----------------------
- For COCO Dataset class
- [Cython](http://cython.org/)
- [pycocotools](https://github.com/cocodataset/cocoapi)
- For COCO Training
- [OpenMPI](https://www.open-mpi.org/)
- [nccl](https://developer.nvidia.com/nccl)
- [ChainerMN](https://github.com/chainer/chainermn)Notification
------------
- Only GPU implementation, No CPU implementation yet.TODO
----
- VOC
- [ ] Reproduce original repo training accuracy
- COCO
- [ ] Reproduce original repo training accuracy
- [ ] Refine evaluation codeInstallation
------------We recommend to use [Anacoda](https://anaconda.org/).
```bash
# 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
---------
```bash
cd examples/coco/
python demo.py
```Above is our implementation output, and below is original.
Training
--------```bash
cd examples/voc/
python train.py
```LICENSE
-------
[MIT LICENSE](LICENSE)Powered by [DL HACKS](http://deeplearning.jp/hacks/)