作者:28划生12_928 | 来源:互联网 | 2023-08-27 21:17
一.caffe2安装依照caffe2官网进行caffe2安装,环境:ubuntu16.04+python2.7+cuda9.0+cudnn7.3.0+opencv3.5.4(ope
一. caffe2安装
依照caffe2 官网进行caffe2安装,环境:ubuntu16.04 +python2.7+cuda 9.0+cudnn 7.3.0+opencv 3.5.4(opencv安装,详见以下链接)
知乎用户 www.zhihu.com
Install caffe2.ai
1.首先安装依赖包
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
build-essential \
git \
libgoogle-glog-dev \
libgtest-dev \
libiomp-dev \
libleveldb-dev \
liblmdb-dev \
libopencv-dev \
libopenmpi-dev \
libsnappy-dev \
libprotobuf-dev \
openmpi-bin \
openmpi-doc \
protobuf-compiler \
python-dev \
python-pip
pip install --user \
future \
numpy \
protobuf \
typing \
hypothesis
sudo apt-get install -y --no-install-recommends \
libgflags-dev \
cmake
2.下载源码和编译(由于下载速度原因,我们在百度云提供下载好的依赖库和源码)
*******百度云链接:链接:https://pan.baidu.com/s/1k1nGIXeCbQhKM1fFCTcZvg
提取码:o8l9
git clone https://github.com/pytorch/pytorch.git && cd pytorch ##下载caffe2源码
git submodule update --init --recursive ##下载第三方依赖库
python setup.py install ##安装
3.进入pytorch 根目录
cd pytorch
mkdir build
cd build
cmake ..
############################################################################################
(若是报‘no module yaml’ 错误,需要安装sudo pip install pyyaml ,然后重新 cmake ..)
############################################################################################
sudo make -j8 install
4.编译完成,进行测试,出现success,即为成功。
cd ~ && python -c 'from caffe2.python import core' 2>/dev/null && echo "Success" || echo "Failure"
####检测caffe2是否安装成功,出现大于0,就是成功安装
python -c 'from caffe2.python import workspace; print(workspace.NumCudaDevices())'
二.COCOAPI 安装
5.安装cocoapi,进入cocoapi/pythonAPI,执行以下命令
sudo make install
sudo python setup.py install
6.修改环境变量
sudo gedit ~/.bashrc
COCOAPI=/path/to/install/cocoapi
source ~/.bashrc
三.安装Mask r-cnn
7.下载,并进入文件夹
# DETECTRON=/path/to/clone/detectron
git clone https://github.com/facebookresearch/detectron $DETECTRON
pip install -r requirements.txt
8.编译,并测试
make
python /detectron/tests/test_spatial_narrow_as_op.py
##################根据自己路径修改对应的地方,并执行指令
python tools/infer_simple.py \
--cfg configs/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml \
--output-dir /tmp/detectron-visualizations \
--image-ext jpg \
--wts https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/e2e_mask_rcnn_R-101-FPN_2x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl \
demo