FCIS: A Cuda repository from zht022

Fully Convolutional Instance-aware Semantic Segmentation

The major contributors of this repository include Haozhi Qi, Yi Li, Guodong Zhang, Haochen Zhang, Jifeng Dai, and Yichen Wei.

Introduction

FCIS is a fully convolutional end-to-end solution for instance segmentation, which won the first place in COCO segmentation challenge 2016.

FCIS is initially described in a CVPR 2017 spotlight paper. It is worth noticing that:

FCIS provides a simple, fast and accurate framework for instance segmentation.
Different from MNC, FCIS performs instance mask estimation and categorization jointly and simultanously, and estimates class-specific masks.
We did not exploit the various techniques & tricks in the Mask RCNN system, like increasing RPN anchor numbers (from 12 to 15), training on anchors out of image boundary, enlarging the image (shorter side from 600 to 800 pixels), utilizing FPN features and aligned ROI pooling. These techniques & tricks should be orthogonal to our simple baseline.

Resources

Visual results on the first 5k images from COCO test set of our COCO 2016 challenge entry: OneDrive.
Slides in ImageNet ILSVRC and COCO workshop 2016: OneDrive.

Disclaimer

This is an official implementation for Fully Convolutional Instance-aware Semantic Segmentation (FCIS) based on MXNet. It is worth noticing that:

The original implementation is based on our internal Caffe version on Windows. There are slight differences in the final accuracy and running time due to the plenty details in platform switch.
The code is tested on official MXNet@(commit 62ecb60) with the extra operators for FCIS.
We trained our model based on the ImageNet pre-trained ResNet-v1-101 using a model converter. The converted model produces slightly lower accuracy (Top-1 Error on ImageNet val: 24.0% v.s. 23.6%).
This repository used code from MXNet rcnn example and mx-rfcn.

License

Citing FCIS

If you find FCIS useful in your research, please consider citing:

@inproceedings{li2016fully,
  Author = {Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji and Yichen Wei}
  Title = {Fully Convolutional Instance-aware Semantic Segmentation},
  Conference = {CVPR},
  year = {2017}
}

Main Results

	training data	testing data	mAP^r@0.5	mAP^r@0.7	time
FCIS, ResNet-v1-101	VOC 2012 train	VOC 2012 val	66.0	51.9	0.23s

	_{training data}	_{testing data}	_mAP^r	_mAP^r@0.5	_mAP^r@0.75	_mAP^r@S	_mAP^r@M	_mAP^r@L
_{FCIS, ResNet-v1-101, OHEM}	_{coco trainval35k}	_{coco minival}	29.2	50.8	29.7	7.9	31.4	51.1
_{FCIS, ResNet-v1-101, OHEM}	_{coco trainval35k}	_{coco test-dev}	29.6	51.4	30.2	8.0	31.0	49.7

Running time is counted on a single Maxwell Titan X GPU (mini-batch size is 1 in inference).

Requirements: Software

MXNet from the offical repository. We tested our code on MXNet@(commit 62ecb60). Due to the rapid development of MXNet, it is recommended to checkout this version if you encounter any issues. We may maintain this repository periodically if MXNet adds important feature in future release.
Python packages might missing: cython, opencv-python >= 3.2.0, easydict. If pip is set up on your system, those packages should be able to be fetched and installed by running
```
pip install Cython
pip install opencv-python==3.2.0.6
pip install easydict==1.6
pip install hickle
```
For Windows users, Visual Studio 2015 is needed to compile cython module.

Requirements: Hardware

Any NVIDIA GPUs with at least 5GB memory should be OK

Installation

Clone the FCIS repository, and we'll call the directory that you cloned FCIS as ${FCIS_ROOT}.

git clone https://github.com/msracver/FCIS.git

For Windows users, run cmd .\init.bat. For Linux user, run sh ./init.sh. The scripts will build cython module automatically and create some folders.
Install MXNet:

Note: The MXNet's Custom Op cannot execute parallelly using multi-gpus after this PR. We strongly suggest the user rollback to version MXNet@(commit 998378a) for training (following Section 3.2 - 3.6).

Quick start

3.1 Install MXNet and all dependencies by
```
pip install -r requirements.txt
```
If there is no other error message, MXNet should be installed successfully.

Build from source (alternative way)

3.2 Clone MXNet and checkout to MXNet@(commit 998378a) by
```
git clone --recursive https://github.com/dmlc/mxnet.git
git checkout 998378a
git submodule update
```
3.3 Copy channel operators in $(FCIS_ROOT)/fcis/operator_cxx to $(YOUR_MXNET_FOLDER)/src/operator/contrib by
```
cp -r $(FCIS_ROOT)/fcis/operator_cxx/channel_operator* $(MXNET_ROOT)/src/operator/contrib/
```
3.4 Compile MXNet
```
cd ${MXNET_ROOT}
make -j $(nproc) USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1
```
3.5 Install the MXNet Python binding by

Note: If you will actively switch between different versions of MXNet, please follow 3.5 instead of 3.4
```
cd python
sudo python setup.py install
```
3.6 For advanced users, you may put your Python packge into ./external/mxnet/$(YOUR_MXNET_PACKAGE), and modify MXNET_VERSION in ./experiments/fcis/cfgs/*.yaml to $(YOUR_MXNET_PACKAGE). Thus you can switch among different versions of MXNet quickly.

Demo

To run the demo with our trained model (on COCO trainval35k), please download the model manually from OneDrive (Chinese users can also get it from BaiduYun with code tmd4), and put it under folder model/.

Make sure it looks like this:
```
./model/fcis_coco-0000.params
```
Run
```
python ./fcis/demo.py
```

Preparation for Training & Testing

Please download VOC 2012 dataset with additional annotations from SBD. Move inst, cls, img folders to VOCdevit and make sure it looks like this:

Please use the train&val split in this repo, which follows the protocal of SDS.
```
.data/VOCdevkit/VOCSDS/img/
.data/VOCdevkit/VOCSDS/inst/
.data/VOCdevkit/VOCSDS/cls/
```
Please download COCO dataset and annotations for the 5k image minival subset and val2014 minus minival (val35k). Make sure it looks like this:
```
.data/coco/
.data/coco/annotations/instances_valminusminival2014.json
.data/coco/annotations/instances_minival2014.json
```
Please download ImageNet-pretrained ResNet-v1-101 model manually from OneDrive, and put it under folder ./model. Make sure it looks like this:
```
./model/pretrained_model/resnet_v1_101-0000.params
```

Usage

All of our experiment settings (GPU #, dataset, etc.) are kept in yaml config files at folder ./experiments/fcis/cfgs.
Two config files have been provided so far: FCIS@COCO with OHEM and FCIS@VOC without OHEM. We use 8 and 4 GPUs to train models on COCO and on VOC, respectively.
To perform experiments, run the python scripts with the corresponding config file as input. For example, to train and test FCIS on COCO with ResNet-v1-101, use the following command
```
python experiments/fcis/fcis_end2end_train_test.py --cfg experiments/fcis/cfgs/resnet_v1_101_coco_fcis_end2end_ohem.yaml
```
A cache folder would be created automatically to save the model and the log under output/fcis/coco/ or output/fcis/voc/.
Please find more details in config files and in our code.

Misc.

Code has been tested under:

Ubuntu 14.04 with a Maxwell Titan X GPU and Intel Xeon CPU E5-2620 v2 @ 2.10GHz
Windows Server 2012 R2 with 8 K40 GPUs and Intel Xeon CPU E5-2650 v2 @ 2.60GHz
Windows Server 2012 R2 with 4 Pascal Titan X GPUs and Intel Xeon CPU E5-2650 v4 @ 2.30GHz

zht022/FCIS