This repository modified by Ziqi Tang is mainly based on FCIS.
pip install Cython
pip install opencv-python==3.2.0.6
pip install easydict==1.6
pip install hickle
For Linux: run
sh ./init.sh
For Windows: run
cmd .\init.bat
无cuda用户需安装cuda8.0才能使用GPU运行程序
安装基本依赖
sudo apt-get update
sudo apt-get install -y build-essential git libblas-dev libopencv-dev
Clone MXNet and checkout to MXNet@(commit 998378a) by
git clone --recursive https://github.com/dmlc/mxnet.git
git checkout 998378a
git submodule update
Copy channel operators in
cp -r $(FCIS_ROOT)/fcis/operator_cxx/channel_operator* $(MXNET_ROOT)/src/operator/contrib/
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
Install the MXNet Python binding by
cd ${MXNET_ROOT}python
sudo python setup.py install
For advanced users, you may put your Python packge into ./external/mxnet/$(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.*
在BaiduYun下载pretrained model。提取密码:tmd4
下载后的模型目录:
./model/fcis_coco-0000.params
python ./babycam/segbaby.py