ubuntu 14.04+ GTX 1070+cuda 8.0 + cudnn 5.1+opencv3.0+caffe-SSD配置一步到位

ubuntu 14.04+ GTX 1070+cuda 8.0 + cudnn 5.1+opencv3.0的安装参见我前两篇博客，详细介绍了！

上一篇写了如何接着配置caffe框架.    本文重点为caffe-ssd的安装与配置细节(注意此时电脑的配置为ubuntu 14.04+ GTX 1070+cuda 8.0 + cudnn 5.1+opencv3.0+caffe)

一、安装ssd（大部分依赖库已经在配置caffe的时候完成）

在/home下新建文件夹caffe-ssd（区别于caffe）

cd caffe-ssd
git clone https://github.com/weiliu89/caffe.git
cd caffe
git checkout ssd

一、配置ssd

cd /home/**（您服务器的名字）/caffe
cp Makefile.config.example Makefile.config

打开Makefile.config，修改之处为

use_cudnn:=1取消注释

opencv_version:=3取消注释

with_python_layer:=1取消注释

INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include

改为

INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include  /usr/include/hdf5/serial/

修改Makefile文件

LIBRARIES += glog gflags protobuf boost_system boost_filesystem boost_regex m hdf5_hl hdf5

改为

LIBRARIES += glog gflags protobuf boost_system boost_filesystem boost_regex m hdf5_hl hdf5 opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs

然后编译

用下面的方法开始不成功就放弃了

cd /home//caffe
mkdir build
cd build
cmake ..
make all -j16
make install
make runtest
make pycaffe

其中在cmake  ..的时候发现opencv还是找的opencv2.4.8版本，在caffe-ssd/caffe里面的CMakeLists.txt添加

set(OpenCV_DIR /home/shan/opencv-3.0.0/build)

这样就能找到3.0版本的了，改完之后接着用下面的方法：

根据readme.md里的指令编译

make -j8
make py
make test -j8
make runtest -j8

在Make -j8 过程会出现error：

1、json_parser_read.hpp:257:264: error: ‘type name’ declared as function returning an array escape
解决：sudo gedit/usr/include/boost/property_tree/detail/json_parser_read.hpp将257行的escape代码段注释掉即可

2、cannot find -lopencv_videoio

     cannot find -lopenblas

像这种问题是找不到libopencv_videoio.so、libopenblas.so等文件

解决方法是：首先在计算机中查找看是否有libopencv_videoio等文件

若没有，就sudo apt-get install libopencv_videoio-dev

若有，就把文件拷贝到/usr/lib下  ，如果不行，就拷贝到/usr/local/lib

对于我的问题libopencv_videoio.so能找到，进行拷贝

sudo cp /home/shan/opencv-3.0.0/build/lib/libopencv_videoio.so /usr/lib
sudo cp /home/shan/opencv-3.0.0/build/lib/libopencv_videoio.so.3.0 /usr/lib
sudo cp /home/shan/opencv-3.0.0/build/lib/libopencv_videoio.so.3.0.0 /usr/lib
sudo cp /home/shan/opencv-3.0.0/build/lib/libopencv_videoio_pch_dephelp.a /usr/lib

而libopenblas找不到，

sudo apt-get install libopenblas-dev

再make -j8没问题

make py

make test -j8

make runtest -j8
出现问题： error while loading shared libraries: libcudart.so.8.0: cannot open shared object file: No such file or directory
解决办法：首先确认/etc/profile中的路径包含了cuda8.0的安装路径及相应的库文件

sudo gedit /etc/profile  
export PATH=$PATH:/usr/local/cuda-8.0/bin  
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-8.0/lib64  
export LIBRARY_PATH=$LIBRARY_PATH:/usr/local/cuda-8.0/lib64

export PYTHONPATH=~/caffe-ssd/caffe/python:$PYTHONPATH  

export PKG_CONFIG_PATH=/usr/local/cuda-8.0/pkgconfig:/usr/local/lib/pkgconfig:$PKG_CONFIG_PATH

$source /etc/profile

使配置文件生效，再次执行。
若仍提示相同的错误，则执行以下命令，将相应的库文件复制到/usr/lib

sudo cp /usr/local/cuda-8.0/lib64/libcudart.so.8.0 /usr/local/lib/libcudart.so.8.0 && sudo ldconfig  
sudo cp /usr/local/cuda-8.0/lib64/libcublas.so.8.0 /usr/local/lib/libcublas.so.8.0 && sudo ldconfig  
sudo cp /usr/local/cuda-8.0/lib64/libcurand.so.8.0 /usr/local/lib/libcurand.so.8.0 && sudo ldconfig  

还是不行！！！

sudo cp /usr/local/cuda-8.0/lib64/libcudart.so.8.0 /usr/lib/libcudart.so.8.0 && sudo ldconfig  

成功！！！

到了第二天不知道动了什么，。，不好使了，，删除caffe-ssd包，重新下载编译，编译不过去了，，又用这个法编译过去了，，真是醉了

cd /home//caffe
mkdir build
cd build
cmake ..
make all -j16
make install
make runtest
make pycaffe

接下来，下载数据集和训练

### Preparation
1. Download [fully convolutional reduced (atrous) VGGNet](https://gist.github.com/weiliu89/2ed6e13bfd5b57cf81d6). By default, we assume the model is stored in `$CAFFE_ROOT/models/VGGNet/`

2. Download VOC2007 and VOC2012 dataset. By default, we assume the data is stored in `$HOME/data/`
  ```Shell
  # Download the data.
  cd $HOME/data
  wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
  wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
  wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
  # Extract the data.
  tar -xvf VOCtrainval_11-May-2012.tar
  tar -xvf VOCtrainval_06-Nov-2007.tar
  tar -xvf VOCtest_06-Nov-2007.tar
  数据集的获取：通过解压数据集到/data下最靠谱，如果通过拷贝以前保存的数据集到/data下，在/VOC2012/JPEGImage下2011_001232.jpg是拷贝不过来的

3.生成LMDB文件
  cd $CAFFE_ROOT
  # Create the trainval.txt, test.txt, and test_name_size.txt in data/VOC0712/
  ./data/VOC0712/create_list.sh
  # You can modify the parameters in create_data.sh if needed.
  # It will create lmdb files for trainval and test with encoded original image:
  #   - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_trainval_lmdb
  #   - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_test_lmdb
  # and make soft links at examples/VOC0712/
  ./data/VOC0712/create_data.sh
  ```
### 训练
1. Train your model and evaluate the model on the fly.
  ```Shell
  # It will create model definition files and save snapshot models in:
  #   - $CAFFE_ROOT/models/VGGNet/VOC0712/SSD_300x300/
  # and job file, log file, and the python script in:
  #   - $CAFFE_ROOT/jobs/VGGNet/VOC0712/SSD_300x300/
  # and save temporary evaluation results in:
  #   - $HOME/data/VOCdevkit/results/VOC2007/SSD_300x300/
  # It should reach 72.* mAP at 60k iterations.
  python examples/ssd/ssd_pascal.py 训练模型
  ```

打开caffe/examples/ssd/ssd_pascal.py这个文件，找到gpus=’0,1,2,3’这一行，如果您的服务器有一块显卡，则将123删去，如果有两个显卡，则删去23，以此类推。如果您服务器没有gpu支持，则注销以下几行，程序会以cpu形式训练。（这个是解决问题cudasuccess（10vs0）的方法）
#Ifnum_gpus >0:

                # batch_size_per_device =int(math.ceil(float(batch_size) / num_gpus))

#iter_size =int(math.ceil(float(accum_batch_size) / (batch_size_per_device * num_gpus)))

 # solver_mode =P.Solver.GPU
  # device_id =int(gpulist[0])
保存后终端运行：
cd  /home/**（您服务器的名字）/caffe
python examples/ssd/ssd_pascal.py

如果出现问题cudasuccess（2vs0）则说明您的显卡计算量有限，再次打开caffe/examples/ssd/ssd_pascal.py这个文件，找到batch_size =32这一行，修改数字32，可以修改为16，或者8，甚至为4（相信大家这个修改可以理解，我就不作说明了），保存后再次终端运行python examples/ssd/ssd_pascal.py

  If you don't have time to train your model, you can download a pre-trained model at [here](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_VOC0712_SSD_300x300.tar.gz).


2. Evaluate the most recent snapshot.
  # If you would like to test a model you trained, you can do:
  python examples/ssd/score_ssd_pascal.py演示detection的训练结果，数值在0.718左右
  ```
3. Test your model using a webcam. Note: press <kbd>esc</kbd> to stop.
  # If you would like to attach a webcam to a model you trained, you can do:
  python examples/ssd/ssd_pascal_webcam.py演示网络摄像头识别效果
  ```
4. Check out `examples/ssd_detect.ipynb` or `examples/ssd/ssd_detect.cpp` on how to detect objects using a SSD model.

### Models
1. Models trained on VOC0712: [SSD300](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_VOC0712_SSD_300x300.tar.gz), [SSD500](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_VOC0712_SSD_500x500.tar.gz)


2. Models trained on MSCOCO trainval35k: [SSD300](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_coco_SSD_300x300.tar.gz), [SSD500](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_coco_SSD_500x500.tar.gz)


3. Models trained on ILSVRC2015 trainval1: [SSD300](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_ilsvrc15_SSD_300x300.tar.gz), [SSD500](http://www.cs.unc.edu/~wliu/projects/SSD/models_VGGNet_ilsvrc15_SSD_500x500.tar.gz) (46.4 mAP on val2)

########################################################################

在python examples/ssd/ssd_pascal.py时有一些小问题产生，按照网上的都解决，，但具体的忘了，好像

sudo python examples/ssd/ssd_pascal.py  这样就可以训练数据了

运行python examples/ssd/score_ssd_pascal.py  和  python examples/ssd/ssd_pascal_webcam.py出现错误：

层与层之间的维度信息不匹配，这时候训练迭代次数将近40000次，然后继续运行

Python example/ssd/ssd_pascal.py等到迭代到了68000多次，再次运行，成功！！！

至此，所有配置工作圆满完成！！！