ubuntu深度学习环境配置+mnist训练

 

ubuntu caffe cpu版本的安装

https://blog.youkuaiyun.com/luteresa/article/details/79820493

1. 将opencv的路径打开   OPENCV_VERSION := 3

2. 安装依赖包问题：

ERROR: pandas 0.24.2 has requirement python-dateutil>=2.5.0, but you'll have python-dateutil 1.5 which is incompatible.
ERROR: matplotlib 2.2.4 has requirement python-dateutil>=2.1, but you'll have python-dateutil 1.5 which is incompatible.
解决办法：

但其实python-dateutil已经安装为2.7.3版本。

sudo gedit requirements.txt

将requirements.txt里面的python-dateutil>=1.4,<2删除，保存，重新安装requirement就可以了

3. 安装pycaffe遇到问题：

fatal error: numpy/arrayobject.h: No such file or directory  #include <numpy/arrayobject.h>

解决办法：

命令行输入如下

python 

import numpy as np

np.get_include()

得到路径'/usr/local/lib/python2.7/dist-packages/numpy/core/include'

将Makefile.config中PYTHON_INCLUDE中增加一个local

保存后，重新sudo make pycaffe -j16即可

 

mnist测试

1、在安装的caffe目录下执行

./data/mnist/get_mnist.sh

./examples/mnist/create_mnist.sh

./examples/mnist/train_lenet.sh

GPU版

./build/tools/caffe.bin test -model=examples/mnist/lenet_train_test.prototxt -weights=examples/mnist/lenet_iter_10000.caffemodel -gpu=0  

CPU版

./build/tools/caffe.bin test -model=examples/mnist/lenet_train_test.prototxt -weights=examples/mnist/lenet_iter_10000.caffemodel