FCIS https://github.com/msracver/FCIS COCO2016分割比賽冠軍python
安裝依賴linux
pip install Cython pip install opencv-python==3.2.0.6 pip install easydict==1.6 pip install hickle
下載mxnet 文中明確說過,測試的時候使用[MXNet@(commit 62ecb60)](https://github.com/apache/incubator-mxnet/tree/62ecb60 "MXNet@(commit 62ecb60),訓練的時候使用[MXNet@(commit 998378a)](https://github.com/apache/incubator-mxnet/tree/998378a "MXNet@(commit 998378a)git
咱們這裏直接使用[MXNet@(commit 998378a)](https://github.com/apache/incubator-mxnet/tree/998378a "MXNet@(commit 998378a),github
git clone --recursive https://github.com/dmlc/mxnet.git git checkout 998378a git submodule update --init --recursive
複製文件apache
cp -r $(FCIS_ROOT)/fcis/operator_cxx/channel_operator* $(MXNET_ROOT)/src/operator/contrib/
編譯測試
cd ${MXNET_ROOT} make -j $(nproc) USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1
可能出現問題:code
編譯pythonip
cd python sudo python setup.py install
下載已有模型百度雲密碼tmd4, 將模型放在model文件夾下,相似ci
./model/fcis_coco-0000.params
而後運行get
python ./fcis/demo.py