Caffe python接口使用
================================目录：
1. 安装python接口
2. draw_net.py可视化网络结构
===============================
1. 安装
a. 安装依赖库
库的版本要求，在$caffe-root/python中的requirements.txt
Cython>=0.19.2
numpy>=1.7.1
scipy>=0.13.2
scikit-image>=0.9.3
scikit-learn>=0.14.1
matplotlib>=1.3.1
ipython>=1.1.0
h5py>=2.2.0
leveldb>=0.191
networkx>=1.8.1
nose>=1.3.0
pandas>=0.12.0
python-dateutil>=1.4,<2
protobuf>=2.5.0
python-gflags>=2.0
pyyaml>=3.10
Pillow>=2.7.0
b. 编译 make pycaffe
c. 把caffe的python模块接入PYTHONPATH,
cd
sudo gedit~/.bashrc
加入export PYTHONPATH=/path/to/caffe/python:$PYTHONPATH
d. 测试
python
>> import caffe
2. caffe/python/draw_net.py
命令：python draw_net.py <protext> <outfile>
e.g. ./python/draw_net.py ./examples/mnist/lenet_train_test.prototxt lenet.png
注意：首先要安装了graphviz
sudo apt-get install graphviz graphviz-doc
安装了pydot
sudo pip install pydot
参考：http://www.cnblogs.com/dupuleng/articles/4242906.html
页:
[1]