接上篇caffe将用训练好的caffemodel和train_val.prototxt文件分类新的一张图片-上篇
得到deploy.prototxt文件之后,我们可以自己编写python代码实现对单个图片的分类预测,先贴代码再分析:
#coding=utf-8
import caffe
import numpy as np
root=root='/home/dltest/caffe/' #根目录
deploy=root + 'examples/cifar10/cifar10_quick.prototxt' #deploy文件
caffe_model=root + 'examples/cifar10/cifar10_quick_iter_4000.caffemodel.h5' #训练好的 caffemodel
mean_file= #自己的python格式的meanfile路径
img=root+'examples/sgg_datas/images/1.jpg' #随机找的一张待测图片
labels_filename = root +'data/cifar10/batches.meta.txt' #类别名称文件,将数字标签转换回类别名称
net = caffe.Net(deploy,caffe_model,caffe.TEST) #加载model和network
#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_mean('data', np.load(mean_file).mean(1).mean(1)) #减去均值
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) #加载图片
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
#执行测试
out = net.forward()
labels = np.loadtxt(labels_filename, str, delimiter='\t') #读取类别名称文件
prob= net.blobs['prob'].data[0].flatten() #取出最后一层(prob)属于某个类别的概率值,并打印
print prob
order=prob.argsort()[-1] #将概率值排序,取出最大值所在的序号
#argsort()函数是从小到大排列
print 'the class is:',labels[order] #将该序号转换成对应的类别名称,并打印
对于图片的预处理,可参考caffe官网的例子,
关键代码如下:
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
# load input and configure preprocessing
im = caffe.io.load_image('images/cat.jpg')
transformer = caffe.io.Transformer({'data': net_full_conv.blobs['data'].data.shape})
transformer.set_mean('data', np.load('../python/caffe/imagenet/ilsvrc_2012_mean.npy').mean(1).mean(1))
transformer.set_transpose('data', (2,0,1))
transformer.set_channel_swap('data', (2,1,0))
transformer.set_raw_scale('data', 255.0)
# make classification map by forward and print prediction indices at each location
out = net_full_conv.forward_all(data=np.asarray([transformer.preprocess('data', im)]))
print out['prob'][0].argmax(axis=0)
# show net input and confidence map (probability of the top prediction at each location)
plt.subplot(1, 2, 1)
plt.imshow(transformer.deprocess('data', net_full_conv.blobs['data'].data[0]))
plt.subplot(1, 2, 2)
plt.imshow(out['prob'][0,281])