首页 > 代码库 > caffe-mnist别手写数字

caffe-mnist别手写数字

【来自:http://www.cnblogs.com/denny402/p/5685909.html】

整个工作目录建在:/home/ubunt16041/caffe/examples/abc_mnist/

再建一个mnist目录,所有的都放在mnist目录下。

(/home/ubuntu16041/caffe/examples/abc_mnist/mnist/)

图片下载好,test.txt,train.txt都有了。

mnist.py用来生成训练需要的文件:

# -*- coding: utf-8 -*-

import caffe
from caffe import layers as L,params as P,proto,to_proto
#设定文件的保存路径
root=‘/home/ubuntu16041/caffe/examples/abc_mnist/‘                           #根目录
train_list=root+‘mnist/train/train.txt‘     #训练图片列表
test_list=root+‘mnist/test/test.txt‘        #测试图片列表
train_proto=root+‘mnist/train.prototxt‘     #训练配置文件
test_proto=root+‘mnist/test.prototxt‘       #测试配置文件
solver_proto=root+‘mnist/solver.prototxt‘   #参数文件

#编写一个函数,生成配置文件prototxt
def Lenet(img_list,batch_size,include_acc=False):
    #第一层,数据输入层,以ImageData格式输入
    data, label = L.ImageData(source=img_list, batch_size=batch_size, ntop=2,root_folder=root,
        transform_param=dict(scale= 0.00390625))
    #第二层:卷积层
    conv1=L.Convolution(data, kernel_size=5, stride=1,num_output=20, pad=0,weight_filler=dict(type=‘xavier‘))
    #池化层
    pool1=L.Pooling(conv1, pool=P.Pooling.MAX, kernel_size=2, stride=2)
    #卷积层
    conv2=L.Convolution(pool1, kernel_size=5, stride=1,num_output=50, pad=0,weight_filler=dict(type=‘xavier‘))
    #池化层
    pool2=L.Pooling(conv2, pool=P.Pooling.MAX, kernel_size=2, stride=2)
    #全连接层
    fc3=L.InnerProduct(pool2, num_output=500,weight_filler=dict(type=‘xavier‘))
    #激活函数层
    relu3=L.ReLU(fc3, in_place=True)
    #全连接层
    fc4 = L.InnerProduct(relu3, num_output=10,weight_filler=dict(type=‘xavier‘))
    #softmax层
    loss = L.SoftmaxWithLoss(fc4, label)
    
    if include_acc:             # test阶段需要有accuracy层
        acc = L.Accuracy(fc4, label)
        return to_proto(loss, acc)
    else:
        return to_proto(loss)
    
def write_net():
    #写入train.prototxt
    with open(train_proto, ‘w‘) as f:
        f.write(str(Lenet(train_list,batch_size=64)))

    #写入test.prototxt    
    with open(test_proto, ‘w‘) as f:
        f.write(str(Lenet(test_list,batch_size=100, include_acc=True)))

#编写一个函数,生成参数文件
def gen_solver(solver_file,train_net,test_net):
    s=proto.caffe_pb2.SolverParameter()
    s.train_net =train_net
    s.test_net.append(test_net)
    s.test_interval = 938    #60000/64,测试间隔参数:训练完一次所有的图片,进行一次测试  
    s.test_iter.append(500)  #50000/100 测试迭代次数,需要迭代500次,才完成一次所有数据的测试
    s.max_iter = 9380       #10 epochs , 938*10,最大训练次数
    s.base_lr = 0.01    #基础学习率
    s.momentum = 0.9    #动量
    s.weight_decay = 5e-4  #权值衰减项
    s.lr_policy = ‘step‘   #学习率变化规则
    s.stepsize=3000         #学习率变化频率
    s.gamma = 0.1          #学习率变化指数
    s.display = 20         #屏幕显示间隔
    s.snapshot = 938       #保存caffemodel的间隔
    s.snapshot_prefix = root+‘mnist/lenet‘   #caffemodel前缀
    s.type =‘SGD‘         #优化算法
    s.solver_mode = proto.caffe_pb2.SolverParameter.CPU    #加速
    #写入solver.prototxt
    with open(solver_file, ‘w‘) as f:
        f.write(str(s))
  
#开始训练
def training(solver_proto):
    solver = caffe.SGDSolver(solver_proto)
    solver.solve()
#
if __name__ == ‘__main__‘:
    write_net()
    gen_solver(solver_proto,train_proto,test_proto) 
    training(solver_proto)

运行:python mnist.py

接下来就是生成deploy.prototxt文件:

deploy.py

# -*- coding: utf-8 -*-

from caffe import layers as L,params as P,to_proto
root=‘/home/ubuntu16041/caffe/examples/abc_mnist/‘
deploy=root+‘mnist/deploy.prototxt‘    #文件保存路径

def create_deploy():
    #少了第一层,data层
    conv1=L.Convolution(bottom=‘data‘, kernel_size=5, stride=1,num_output=20, pad=0,weight_filler=dict(type=‘xavier‘))
    pool1=L.Pooling(conv1, pool=P.Pooling.MAX, kernel_size=2, stride=2)
    conv2=L.Convolution(pool1, kernel_size=5, stride=1,num_output=50, pad=0,weight_filler=dict(type=‘xavier‘))
    pool2=L.Pooling(conv2, pool=P.Pooling.MAX, kernel_size=2, stride=2)
    fc3=L.InnerProduct(pool2, num_output=500,weight_filler=dict(type=‘xavier‘))
    relu3=L.ReLU(fc3, in_place=True)
    fc4 = L.InnerProduct(relu3, num_output=10,weight_filler=dict(type=‘xavier‘))
    #最后没有accuracy层,但有一个Softmax层
    prob=L.Softmax(fc4)
    return to_proto(prob)
def write_deploy(): 
    with open(deploy, ‘w‘) as f:
        f.write(‘name:"Lenet"\n‘)
        f.write(‘input:"data"\n‘)
        f.write(‘input_dim:1\n‘)
        f.write(‘input_dim:3\n‘)
        f.write(‘input_dim:28\n‘)
        f.write(‘input_dim:28\n‘)
        f.write(str(create_deploy()))
if __name__ == ‘__main__‘:
    write_deploy()

 照样运行,就可以生成了。

最后就是测试:test.py

技术分享
 1 #coding=utf-8
 2 
 3 import caffe
 4 import numpy as np
 5 root=/home/ubuntu16041/caffe/examples/abc_mnist/   #根目录
 6 deploy=root + mnist/deploy.prototxt    #deploy文件
 7 caffe_model=root + mnist/lenet_iter_9380.caffemodel   #训练好的 caffemodel
 8 img=root+mnist/test/8/00061.png    #随机找的一张待测图片
 9 labels_filename = root + mnist/test/labels.txt  #类别名称文件,将数字标签转换回类别名称
10 
11 net = caffe.Net(deploy,caffe_model,caffe.TEST)   #加载model和network
12 
13 #图片预处理设置
14 transformer = caffe.io.Transformer({data: net.blobs[data].data.shape})  #设定图片的shape格式(1,3,28,28)
15 transformer.set_transpose(data, (2,0,1))    #改变维度的顺序,由原始图片(28,28,3)变为(3,28,28)
16 #transformer.set_mean(‘data‘, np.load(mean_file).mean(1).mean(1))    #减去均值,前面训练模型时没有减均值,这儿就不用
17 transformer.set_raw_scale(data, 255)    # 缩放到【0,255】之间
18 transformer.set_channel_swap(data, (2,1,0))   #交换通道,将图片由RGB变为BGR
19 
20 im=caffe.io.load_image(img)                   #加载图片
21 net.blobs[data].data[...] = transformer.preprocess(data,im)      #执行上面设置的图片预处理操作,并将图片载入到blob中
22 
23 #执行测试
24 out = net.forward()
25 
26 labels = np.loadtxt(labels_filename, str, delimiter=\t)   #读取类别名称文件
27 prob= net.blobs[Softmax1].data[0].flatten() #取出最后一层(Softmax)属于某个类别的概率值,并打印
28 print prob
29 order=prob.argsort()[-1]  #将概率值排序,取出最大值所在的序号 
30 print the class is:,labels[order]   #将该序号转换成对应的类别名称,并打印
View Code

至此,完成对某个手写字的识别。要想识别另外的手写字,就在test.py里面改!

-----

显示曲线效果的:【http://www.cnblogs.com/denny402/p/5686067.html】

look.py

技术分享
 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Tue Jul 19 16:22:22 2016
 4 
 5 @author: root
 6 """
 7 
 8 import numpy as np
 9 import matplotlib.pyplot as plt  
10 import caffe   
11 
12 #caffe.set_device(0)  
13 #caffe.set_mode_gpu()   
14 
15 # 使用SGDSolver,即随机梯度下降算法  
16 solver = caffe.SGDSolver(/home/ubuntu16041/caffe/examples/abc_mnist/mnist/solver.prototxt)  
17   
18 # 等价于solver文件中的max_iter,即最大解算次数  
19 niter = 9380  
20 # 每隔100次收集一次数据  
21 display= 100  
22   
23 # 每次测试进行100次解算,10000/100  
24 test_iter = 100  
25 # 每500次训练进行一次测试(100次解算),60000/64  
26 test_interval =938  
27   
28 #初始化 
29 train_loss = np.zeros(np.ceil(niter * 1.0 / display))   
30 test_loss = np.zeros(np.ceil(niter * 1.0 / test_interval))  
31 test_acc = np.zeros(np.ceil(niter * 1.0 / test_interval))  
32   
33 # iteration 0,不计入  
34 solver.step(1)  
35   
36 # 辅助变量  
37 _train_loss = 0; _test_loss = 0; _accuracy = 0  
38 # 进行解算  
39 for it in range(niter):  
40     # 进行一次解算  
41     solver.step(1)  
42     # 每迭代一次,训练batch_size张图片  
43     _train_loss += solver.net.blobs[SoftmaxWithLoss1].data  
44     if it % display == 0:  
45         # 计算平均train loss  
46         train_loss[it // display] = _train_loss / display  
47         _train_loss = 0  
48   
49     if it % test_interval == 0:  
50         for test_it in range(test_iter):  
51             # 进行一次测试  
52             solver.test_nets[0].forward()  
53             # 计算test loss  
54             _test_loss += solver.test_nets[0].blobs[SoftmaxWithLoss1].data  
55             # 计算test accuracy  
56             _accuracy += solver.test_nets[0].blobs[Accuracy1].data  
57         # 计算平均test loss  
58         test_loss[it / test_interval] = _test_loss / test_iter  
59         # 计算平均test accuracy  
60         test_acc[it / test_interval] = _accuracy / test_iter  
61         _test_loss = 0  
62         _accuracy = 0  
63   
64 # 绘制train loss、test loss和accuracy曲线  
65 print \nplot the train loss and test accuracy\n  
66 _, ax1 = plt.subplots()  
67 ax2 = ax1.twinx()  
68   
69 # train loss -> 绿色  
70 ax1.plot(display * np.arange(len(train_loss)), train_loss, g)  
71 # test loss -> 黄色  
72 ax1.plot(test_interval * np.arange(len(test_loss)), test_loss, y)  
73 # test accuracy -> 红色  
74 ax2.plot(test_interval * np.arange(len(test_acc)), test_acc, r)  
75   
76 ax1.set_xlabel(iteration)  
77 ax1.set_ylabel(loss)  
78 ax2.set_ylabel(accuracy)  
79 plt.show()
View Code

就会出现一个:

技术分享

ok,接下来就要读读代码啦,今天我叫搬运工:)。。。

【windows可以参考这个:http://blog.csdn.net/zb1165048017/article/details/52217772

http://www.cnblogs.com/yixuan-xu/p/5862657.html

caffe-mnist别手写数字