Segnet分割网络caffe教程（一）

segnet分割网络的地址说明：http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
在这个里面主要讲解如何使用segnet以及每一步的步骤，对于里面所介绍的只有一些关键部分，对于一些细节有点缺失，博主将会一步一步的说明一下如何利用segnet对自己的数据进行分割。
segnet代码的github地址：https://github.com/alexgkendall/SegNet-Tutorial

一些博文对segnet的讲解
（1）http://blog.csdn.net/fate_fjh/article/details/53467948
（2）http://blog.csdn.net/u014451076/article/details/70741629

首先对原来segnet网络实验的说明：

/SegNet/
    CamVid/
        test/
        testannot/
        train/
        trainannot/
        test.txt
        train.txt
    Models/
        # SegNet and SegNet-Basic model files for training and testing
    Scripts/
        compute_bn_statistics.py
        test_segmentation_camvid.py
    caffe-segnet/
        # caffe implementation

这些是对用到的github公布的segnet代码的一个介绍。大家可以按步骤看一下

之后的操作，（1）创建训练所用的list，即train.txt,test.txt这两个文件，这两个文件的生成方法代码我在下一个博文里面写；
（2）开始训练，用到的文件：segnet_train.prototxt，segnet_solver.prototxt。
（3）训练，三种形式

1  ./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt  # This will begin training SegNet on GPU 0
2  ./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_basic_solver.prototxt  # This will begin training SegNet-Basic on GPU 0
3  ./SegNet/caffe-segnet/build/tools/caffe train -gpu 0 -solver /SegNet/Models/segnet_solver.prototxt -weights /SegNet/Models/VGG_ILSVRC_16_layers.caffemodel  # This will begin training SegNet on GPU 0 with a pretrained encoder

不要忘了建立保存，训练模型的地方
（4）测试，测试有点小烦，主要用的文件有：compute_bn_statistics.py，test_segmentation_camvid.py这连个文件会中的compute_bn_statistics.py会生成test_weights.caffemodel，生成的命令语句如下：

1、python /Segnet/Scripts/compute_bn_statistics.py /SegNet/Models/segnet_train.prototxt /SegNet/Models/Training/segnet_iter_10000.caffemodel /Segnet/Models/Inference/  # compute BN statistics for SegNet
2、python /Segnet/Scripts/compute_bn_statistics.py /SegNet/Models/segnet_basic_train.prototxt /SegNet/Models/Training/segnet_basic_iter_10000.caffemodel /Segnet/Models/Inference/  # compute BN statistics for SegNet-Basic

（5）显示测试结果，文件有test_segmentation_camvid.py，segnet_inference.prototxt ，test_weights.caffemodel，命令如下

1、python /SegNet/Scripts/test_segmentation_camvid.py --model /SegNet/Models/segnet_inference.prototxt --weights /SegNet/Models/Inference/test_weights.caffemodel --iter 233  # Test SegNet
2、python /SegNet/Scripts/test_segmentation_camvid.py --model /SegNet/Models/segnet_basic_inference.prototxt --weights /SegNet/Models/Inference/test_weights.caffemodel --iter 233  # Test SegNetBasic

按照上面步骤大家就可以看见官网公布的数据以及网络的结果喽。下一篇博客讲解自己的数据是如何从头开始操作。