转载地址：http://blog.csdn.net/lanxuecc/article/details/52474476

接前面博客：http://blog.csdn.net/lanxuecc/article/details/52329708 我学会了用caffe训练自己的测试自己的图片，但是这里测试的是测试数据集，那么如何用训练好的caffemodel测试自己的单张图片呢。下面记录下我用训练好的lenet_iter_10000.caffemodelg来测试mnist图片的整个摸索过程：：：：

生成deploy.prototxt文件：

用训练好的caffemodel来测试单张图片需要一个deploy.prototxt文件来指定网络的模型构造。  事实上deploy.prototxt文件与lenet_train_test.prototxt文件类似，只是首尾有些差别。仿照博客http://www.cnblogs.com/denny402/p/5685818.html中的教程用deploy.py文件来生成deploy.prototxt文件。

# -*- coding: utf-8 -*- caffe_root = '/home/schao/sc_tmp/caffe/caffe-master/' import sys sys.path.insert(0, caffe_root + 'python') from caffe import layers as L,params as P,to_proto root='/home/schao/sc_tmp/caffe/caffe-master/' deploy='/home/schao/sc_tmp/caffe/caffe-master/examples/mnist/deploy.prototxt' #文件保存路径 def create_deploy(): #少了第一层，data层 conv1=L.Convolution(name='conv1',bottom='data', kernel_size=5, stride=1,num_output=20, pad=0,weight_filler=dict(type='xavier')) pool1=L.Pooling(conv1,name='pool1',pool=P.Pooling.MAX, kernel_size=2, stride=2) conv2=L.Convolution(pool1, name='conv2',kernel_size=5, stride=1,num_output=50, pad=0,weight_filler=dict(type='xavier')) pool2=L.Pooling(conv2, name='pool2',top='pool2', pool=P.Pooling.MAX, kernel_size=2, stride=2) fc3=L.InnerProduct(pool2, name='ip1',num_output=500,weight_filler=dict(type='xavier')) relu3=L.ReLU(fc3, name='relu1',in_place=True) fc4 = L.InnerProduct(relu3, name='ip2',num_output=10,weight_filler=dict(type='xavier')) #最后没有accuracy层，但有一个Softmax层 prob=L.Softmax(fc4, name='prob') return to_proto(prob) def write_deploy(): with open(deploy, 'w') as f: f.write('name:"LeNet"\n') f.write('layer {\n') f.write('name:"data"\n') f.write('type:"Input"\n') f.write('input_param { shape : {') f.write('dim:1 ') f.write('dim:3 ') f.write('dim:28 ') f.write('dim:28 ') f.write('} }\n\n') f.write(str(create_deploy())) if __name__ == '__main__': write_deploy() 1234567891011121314151617181920212223242526272829303132333435 1234567891011121314151617181920212223242526272829303132333435

生成的deploy.prototxt文件如下

name: "LeNet" /*原来训练与测试两层数据层*/ /*layer { name: "mnist" type: "Data" top: "data" top: "label" include { phase: TRAIN } transform_param { scale: 0.00390625 } data_param { source: "examples/mnist/mnist_train_lmdb" batch_size: 64 backend: LMDB } } layer { name: "mnist" type: "Data" top: "data" top: "label" include { phase: TEST } transform_param { scale: 0.00390625 } data_param { source: "examples/mnist/mnist_test_lmdb" batch_size: 100 backend: LMDB } }*/ /*被替换成如下*/ layer { name: "data" type: "Input" top: "data" input_param { shape: { dim: 1 dim: 1 dim: 28 dim: 28 } } } /*卷积层与全连接层中的权值学习率，偏移值学习率，偏移值初始化方式,因为这些值在caffemodel文件中已经提供*/ layer { name: "conv1" type: "Convolution" bottom: "data" top: "conv1" convolution_param { num_output: 20 kernel_size: 5 stride: 1 weight_filler { type: "xavier" } } } layer { name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_param { pool: MAX kernel_size: 2 stride: 2 } } layer { name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" convolution_param { num_output: 50 kernel_size: 5 stride: 1 weight_filler { type: "xavier" } } } layer { name: "pool2" type: "Pooling" bottom: "conv2" top: "pool2" pooling_param { pool: MAX kernel_size: 2 stride: 2 } } layer { name: "ip1" type: "InnerProduct" bottom: "pool2" top: "ip1" inner_product_param { num_output: 500 weight_filler { type: "xavier" } } } layer { name: "relu1" type: "ReLU" bottom: "ip1" top: "ip1" } layer { name: "ip2" type: "InnerProduct" bottom: "ip1" top: "ip2" inner_product_param { num_output: 10 weight_filler { type: "xavier" } } } /*删除了原有的测试模块的测试精度层*/ /*输出层的类型由SoftmaxWithLoss变成Softmax，训练是输出时是loss，应用时是prob。*/ layer { name: "prob" type: "Softmax" bottom: "ip2" top: "prob" } 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137

总得来说，deploy.prototxt就是在lenet_train_test.prototxt的基础上稍作改动，input_param { shape: { dim: 1 dim: 1 dim: 28 dim: 28 } } 这四个dim参数分别是  第一个：对待识别样本图片进行数据增广的数量，一个图片会变成10个，之后输入到网络进行识别。如果不进行数据增广，可以设置成1。  第二个：图片的通道数，一般灰度图片为单通道，则值为1，如果为非灰度图3通道图片则为3。  第三个：图片的高度，单位像素。  第四个：图片的宽度，单位像素。 

对deploy.prototxt的理解来源于：  http://blog.csdn.net/ddqqfree123/article/details/52389337  http://www.cnblogs.com/daihengchen/p/5761304.html  http://caffecn.cn/?/question/431  http://blog.csdn.net/sunshine_in_moon/article/details/49472901  http://stackoverflow.com/questions/36002387/channel-swap-needs-to-have-the-same-number-of-dimensions-as-the-input-channels-e/36075282  http://blog.csdn.net/u010417185/article/details/52137825  http://www.cnblogs.com/denny402/p/5685818.html

执行

python deploy.py 1 1

生成deploy.prototxt。在生成过程中我遇到以下几个报错

报错： ImportError: No module named caffe  解决：  这种情况一般是没有把caffe中的和Python相关的内容的路径添加到python的编译路径中。所以在deploy.py文件开始部位加入

caffe_root = '/home/schao/sc_tmp/caffe/caffe-master/' import sys sys.path.insert(0, caffe_root + 'python') 123 123

指定caffe源码所在路径。

报错：ImportError: liblapack.so.3 cannot open shared object file:No such file or directory  解决：  找不到这个库，但是我在系统中能找到这个库，说明已安装但找不到库位置，那么指定该库所有位置到LD_LIBRARY_PATH共享目录去,ubuntu系统在/etc/ld.so.conf.d/目录中添加lapack.conf，指定这个库目录。

报错： import numpy as npImportError: No module named numpy  解决：  用下列命令安装

apt-get install pyton-numpy 1 1

报错：libblas.so.3: cannot open shared object file: No such file or directory  解决：  因为我已经安装守OpenBlas库，所以建立一个软链接指向这个库

update-alternatives --install /usr/lib/libblas.so.3 libblas.so.3 /usr/local/OpenBlas/lib/libopenblas.so 37 1 1

报错： import skimage.ioImportError: No module named skimage.io  解决：  参考这个网页中方案解决：  http://www.linuxdiyf.com/linux/15537.html