【pytorch+cocoapi+detectron】安装记录

官方安装指导

1. 通过pytorch安装caffe2
2. detectron安装

0. 安装Cuda9.0+cuDNN7.4

1. anaconda创建虚拟环境：conda create -n detectron python=3.6.7，进入环境，conda activate detectron
2. 进入pytorch官网https://pytorch.org/get-started/locally/ 安装pytorch： conda install pytorch torchvision cudatoolkit=9.0 -c pytorch

3. 验证pytorch内含的caffe2和能否用GPU：

我的笔记本安装pytorch能够import caffe2，但是from caffe2.python import core失败提示没有google模块。。。pip install google 还是提示报错。。后来按照Detectron安装配置与训练自己的数据文中的方法安装。

不过这里遇到了 No module named google.protobuf.internal 需要装2个包 protobuf
和feature

conda install protobuf 
 conda install future

验证通过

python -c 'from caffe2.python import core' 2>/dev/null && echo "Success" || echo "Failure"
Success
python -c 'from caffe2.python import workspace; print(workspace.NumCudaDevices())'
1

4. 安装cocoapi
在环境里提前安装好cython pip install cython

	# COCOAPI=/path/to/clone/cocoapi
	git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
	cd $COCOAPI/PythonAPI
    # Install into global site-packages
    make install
    # Alternatively, if you do not have permissions or prefer
    # not to install the COCO API into global site-packages
    python setup.py install --user

5. 安装detectron：

# Clone the Detectron repository:
# DETECTRON=/path/to/clone/detectron
git clone https://github.com/facebookresearch/detectron $DETECTRON

# Install Python dependencies:
pip install -r $DETECTRON/requirements.txt

# Set up Python modules:
cd $DETECTRON && make

# Check that Detectron tests pass (e.g. for SpatialNarrowAsOp test):
python $DETECTRON/detectron/tests/test_spatial_narrow_as_op.py