对测试集test中的图片进行预测

最新推荐文章于 2023-01-27 17:45:38 发布

吃我老猪一钉耙

最新推荐文章于 2023-01-27 17:45:38 发布

阅读量846

点赞数

分类专栏：深度学习caffe-pycaffe

本文链接：https://blog.csdn.net/zlf19910726/article/details/79176702

版权

深度学习caffe-pycaffe 专栏收录该内容

9 篇文章 0 订阅

订阅专栏

对测试集test中的图片进行预测

#!/usr/bin/env python
import numpy as np
import matplotlib.pyplot as plt
import sys,os
import pylab  
caffe_root = "C:\\MYCaffe\\caffe-master\\Build\\x64\\Release\\pycaffe"
sys.path.insert(0, caffe_root)
import caffe

print('import success')

#######################################################################################


os.chdir(caffe_root)  
if not os.path.isfile("D:\CaffeInfo\D_TrainVal\VGG19_layers_prelu_iter_40000.caffemodel"):  
    print "caffemodel is not exist..."  
else:  
    print "Ready to Go ..."  
caffe.set_mode_gpu()  
  

net = caffe.Net("D:\CaffeInfo\D_TrainVal\VGG19_deploy_1.prototxt",  
                "D:\CaffeInfo\D_TrainVal\VGG19_layers_prelu_iter_40000.caffemodel",  
                caffe.TEST)

print('fdsadfasdfasdfsadfsdfasdfsadf\nfasdfsadfsadf\n')

    
print(net.blobs['data'].data.shape)

  
feat = [ [0 for i in range(3)] for j in range(96768)]  
k = 0  
right=0  
imagePath = "D:/CaffeInfo/B_DataCreate/test_image/" 
for filename in os.listdir(imagePath): 
    print('\n\n\n')  
    print(filename)  
    im = caffe.io.load_image(imagePath + filename)  
    if filename[0] == 'N' :  
        label = 0  
    else:  
        label = 1      
      
      
    ################################################################################  
    def convert_mean(binMean,npyMean):  
        blob = caffe.proto.caffe_pb2.BlobProto()  
        bin_mean = open(binMean, 'rb' ).read()  
        blob.ParseFromString(bin_mean)  
        arr = np.array( caffe.io.blobproto_to_array(blob) )  
        npy_mean = arr[0]  
        np.save(npyMean, npy_mean )  
    binMean="D:\\CaffeInfo\\B_DataCreate\\mean.binaryproto" 
    npyMean="D:\\CaffeInfo\\B_DataCreate\\mean.binaryproto.npy"  
    convert_mean(binMean,npyMean)  
    #print(np.load(npyMean))  
    #print("np.load(npyMean).shape")  
    #print(np.load(npyMean).shape)  
      
    ################################################################################  
    transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})  
    transformer.set_transpose('data', (2,0,1))  
    transformer.set_mean('data', np.load(npyMean).mean(1).mean(1))   
    transformer.set_raw_scale('data', 255)    
    transformer.set_channel_swap('data', (2,1,0))  
    net.blobs['data'].data[...] = transformer.preprocess('data',im)  
    inputData=net.blobs['data'].data  
      
    ################################################################################  

    net.forward()  
#     for layer_name, blob in net.blobs.iteritems():  
#         print layer_name + '\t' + str(blob.data.shape)  
      
      
    feat12 = net.blobs['prob'].data[0].flatten()  
    feat[k][0] = feat12[0]  #probability of normal   
    feat[k][1] = feat12[1]  #probability of cancer  
    feat[k][2] = label      #original standard label  
    aa = label == 1 & int(feat12[1] > feat12[0])  
    bb = label == 0 & int(feat12[1] < feat12[0])  
    if aa | bb :  
        right = right + 1  
  
      
    print('right = ' + str(right) )  
    k = k + 1  
    accu = float( right/k );  
    print('ALL = ' + str(k))
    print(label)  
    print( '       normal           cancer' )  
    print(feat12)  
    ################################################################################  
  
  

y_true = [ x[2] for x in feat ]  
y_scores = [ x[1] for x in feat ] 
  

np.savetxt('D:/CaffeInfo/D_TrainVal/' + 'y_true.txt', y_true);  
np.savetxt('D:/CaffeInfo/D_TrainVal/' + 'y_scores.txt', y_scores);  
#np.savetxt('D:/CaffeInfo/D_TrainVal/' + 'rightsumaccuAUC.txt', rightsumaccuAUC);