deploy.prototxt和之前的train.prototxt文件内容差不多,因此可以不需要用代码进行生成,直接将不一样的地方进行修改即可
下面是用代码生成的deploy.prototxt
# -*- coding: utf-8 -*-
__author__ = 'xuy'
import caffe
def creat_deploy():
net = caffe.NetSpec()
net.conv1 = caffe.layers.Convolution(bottom = 'data', kernel_size = 5, num_output = 20,
weight_filler = dict(type = 'xavier'))
net.pool1 = caffe.layers.Pooling(net.conv1, kernel_size = 2, stride = 2,
pool = caffe.params.Pooling.MAX)
net.conv2 = caffe.layers.Convolution(net.pool1, kernel_size = 5, num_output = 50,
weight_filler = dict(type = 'xavier'))
net.pool2 = caffe.layers.Pooling(net.conv2, kernel_size = 2, stride = 2,
pool = caffe.params.Pooling.MAX)
net.fc1 = caffe.layers.InnerProduct(net.pool2, num_output = 500,
weight_filler = dict(type = 'xavier'))
net.relu1 = caffe.layers.ReLU(net.fc1, in_place = True)
net.score = caffe.layers.InnerProduct(net.relu1, num_output = 10,
weight_filler = dict(type = 'xavier'))
net.prob = caffe.layers.Softmax(net.score)
return net.to_proto()
def write_net(deploy_proto):
#写入deploy.prototxt文件
with open(deploy_proto, 'w') as f:
#写入第一层数据描述
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(creat_deploy()))
if __name__ == '__main__':
my_project_root = "/home/xuy/桌面/code/python/caffe/python_mnist/" #my-caffe-project目录
deploy_proto = my_project_root + "mnist/deploy.prototxt"
write_net(deploy_proto)
----------------------------------------------------------------------------------------------------------------------------------------
最后对于训练的模型caffemodel进行预测,随机找出测试集当中的一张图片进行测试
# -*- coding: utf-8 -*-
__author__ = 'xuy'
'''
labels_filename的作用是:将数字标签转换回类别名称
'''
import caffe
import os
import numpy as np
# Caffe_root='/home/xuy/caffe-master'
# os.chdir(Caffe_root)#将当前的路径换成了~/caffe
def test(my_project_root, deploy_proto):#对于已经训练好的caffemodel进行测试
caffe_model = my_project_root + 'mnist_iter_9380.caffemodel' #caffe_model文件的位置
img = my_project_root + 'mnist/test/8/00542.png' #随机找的一张待测图片
labels_filename = my_project_root + 'mnist/test/labels.txt' #类别名称文件,将数字标签转换回类别名称
net = caffe.Net(deploy_proto, caffe_model, caffe.TEST) #加载model和deploy
#图片预处理设置
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape}) #设定图片的shape格式(1,3,28,28)
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)
transformer.set_raw_scale('data', 255) # 缩放到【0,255】之间
transformer.set_channel_swap('data', (2,1,0)) #交换通道,将图片由RGB变为BGR
im = caffe.io.load_image(img) #加载测试图片
net.blobs['data'].data[...] = transformer.preprocess('data',im) #执行上面设置的图片预处理操作,也就是上面四步:1)设定图片格式2)改变维度顺序3)缩放到【0,255】之间4)换颜色通道:RGB->BGR,并将图片载入到blob中
out = net.forward() #执行测试,对于deploy.prototxt进行前向传播测试
labels = np.loadtxt(labels_filename, str, delimiter='\t') #读取类别名称文件当中的所有labels内容
prob = net.blobs['prob'].data[0].flatten() #取出最后一层(Softmax)属于某个类别的概率值
# print net.blobs['prob'].data
order = prob.argsort()[-1] #将概率值排序,取出最大值所在的序号
print '图片数字为:',labels[order] #将该序号转换成对应的类别名称,并打印
if __name__ == '__main__':
my_project_root = "/home/xuy/桌面/code/python/caffe/python_mnist/" #my-caffe-project目录
deploy_proto = my_project_root + "mnist/deploy.prototxt" #保存deploy.prototxt文件的位置
test(my_project_root, deploy_proto)