keras孿生網(wǎng)絡(luò)的圖片相似度怎么計(jì)算？-創(chuàng)新互聯(lián)

不懂keras孿生網(wǎng)絡(luò)的圖片相似度怎么計(jì)算？？其實(shí)想解決這個(gè)問題也不難，下面讓小編帶著大家一起學(xué)習(xí)怎么去解決，希望大家閱讀完這篇文章后大所收獲。

成都創(chuàng)新互聯(lián)是專業(yè)的巴南網(wǎng)站建設(shè)公司，巴南接單;提供網(wǎng)站制作、網(wǎng)站建設(shè),網(wǎng)頁(yè)設(shè)計(jì),網(wǎng)站設(shè)計(jì),建網(wǎng)站,PHP網(wǎng)站建設(shè)等專業(yè)做網(wǎng)站服務(wù);采用PHP框架,可快速的進(jìn)行巴南網(wǎng)站開發(fā)網(wǎng)頁(yè)制作和功能擴(kuò)展;專業(yè)做搜索引擎喜愛的網(wǎng)站,專業(yè)的做網(wǎng)站團(tuán)隊(duì),希望更多企業(yè)前來(lái)合作!

我就廢話不多說(shuō)了，大家還是直接看代碼吧！

import keras
from keras.layers import Input,Dense,Conv2D
from keras.layers import MaxPooling2D,Flatten,Convolution2D
from keras.models import Model
import os
import numpy as np
from PIL import Image
from keras.optimizers import SGD
from scipy import misc
root_path = os.getcwd()
train_names = ['bear','blackswan','bus','camel','car','cows','dance','dog','hike','hoc','kite','lucia','mallerd','pigs','soapbox','stro','surf','swing','train','walking']
test_names = ['boat','dance-jump','drift-turn','elephant','libby']
 
def load_data(seq_names,data_number,seq_len): 
#生成圖片對(duì)
  print('loading data.....')
  frame_num = 51
  train_data1 = []
  train_data2 = []
  train_lab = []
  count = 0
  while count < data_number:
    count = count + 1
    pos_neg = np.random.randint(0,2)
    if pos_neg==0:
      seed1 = np.random.randint(0,seq_len)
      seed2 = np.random.randint(0,seq_len)
      while seed1 == seed2:
       seed1 = np.random.randint(0,seq_len)
       seed2 = np.random.randint(0,seq_len)
      frame1 = np.random.randint(1,frame_num)
      frame2 = np.random.randint(1,frame_num)
      path2 = os.path.join(root_path,'data','simility_data',seq_names[seed1],str(frame1)+'.jpg')
      path3 = os.path.join(root_path, 'data', 'simility_data', seq_names[seed2], str(frame2) + '.jpg')
      image1 = np.array(misc.imresize(Image.open(path2),[224,224]))
      image2 = np.array(misc.imresize(Image.open(path3),[224,224]))
      train_data1.append(image1)
      train_data2.append(image2)
      train_lab.append(np.array(0))
    else:
     seed = np.random.randint(0,seq_len)
     frame1 = np.random.randint(1, frame_num)
     frame2 = np.random.randint(1, frame_num)
     path2 = os.path.join(root_path, 'data', 'simility_data', seq_names[seed], str(frame1) + '.jpg')
     path3 = os.path.join(root_path, 'data', 'simility_data', seq_names[seed], str(frame2) + '.jpg')
     image1 = np.array(misc.imresize(Image.open(path2),[224,224]))
     image2 = np.array(misc.imresize(Image.open(path3),[224,224]))
     train_data1.append(image1)
     train_data2.append(image2)
     train_lab.append(np.array(1))
  return np.array(train_data1),np.array(train_data2),np.array(train_lab)
 
def vgg_16_base(input_tensor):
  net = Conv2D(64(3,3),activation='relu',padding='same',input_shape=(224,224,3))(input_tensor)
  net = Convolution2D(64,(3,3),activation='relu',padding='same')(net)
  net = MaxPooling2D((2,2),strides=(2,2))(net)
 
  net = Convolution2D(128,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(128,(3,3),activation='relu',padding='same')(net)
  net= MaxPooling2D((2,2),strides=(2,2))(net)
 
  net = Convolution2D(256,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(256,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(256,(3,3),activation='relu',padding='same')(net)
  net = MaxPooling2D((2,2),strides=(2,2))(net)
 
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = MaxPooling2D((2,2),strides=(2,2))(net)
 
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = Convolution2D(512,(3,3),activation='relu',padding='same')(net)
  net = MaxPooling2D((2,2),strides=(2,2))(net)
  net = Flatten()(net)
  return net
 
def siamese(vgg_path=None,siamese_path=None):
  input_tensor = Input(shape=(224,224,3))
  vgg_model = Model(input_tensor,vgg_16_base(input_tensor))
  if vgg_path:
    vgg_model.load_weights(vgg_path)
  input_im1 = Input(shape=(224,224,3))
  input_im2 = Input(shape=(224,224,3))
  out_im1 = vgg_model(input_im1)
  out_im2 = vgg_model(input_im2)
  diff = keras.layers.substract([out_im1,out_im2])
  out = Dense(500,activation='relu')(diff)
  out = Dense(1,activation='sigmoid')(out)
  model = Model([input_im1,input_im2],out)
  if siamese_path:
    model.load_weights(siamese_path)
  return model
 
train = True
if train:
  model = siamese(siamese_path='model/simility/vgg.h6')
  sgd = SGD(lr=1e-6,momentum=0.9,decay=1e-6,nesterov=True)
  model.compile(optimizer=sgd,loss='mse',metrics=['accuracy'])
  tensorboard = keras.callbacks.TensorBoard(histogram_freq=5,log_dir='log/simility',write_grads=True,write_images=True)
  ckpt = keras.callbacks.ModelCheckpoint(os.path.join(root_path,'model','simility','vgg.h6'),
                    verbose=1,period=5)
  train_data1,train_data2,train_lab = load_data(train_names,4000,20)
  model.fit([train_data1,train_data2],train_lab,callbacks=[tensorboard,ckpt],batch_size=64,epochs=50)
else:
  model = siamese(siamese_path='model/simility/vgg.h6')
  test_im1,test_im2,test_labe = load_data(test_names,1000,5)
  TP = 0
  for i in range(1000):
   im1 = np.expand_dims(test_im1[i],axis=0)
   im2 = np.expand_dims(test_im2[i],axis=0)
   lab = test_labe[i]
   pre = model.predict([im1,im2])
   if pre>0.9 and lab==1:
    TP = TP + 1
   if pre<0.9 and lab==0:
    TP = TP + 1
  print(float(TP)/1000)

標(biāo)題名稱：keras孿生網(wǎng)絡(luò)的圖片相似度怎么計(jì)算？-創(chuàng)新互聯(lián)
文章位置：http://muchs.cn/article6/doojig.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供網(wǎng)站內(nèi)鏈、關(guān)鍵詞優(yōu)化、定制開發(fā)、商城網(wǎng)站、品牌網(wǎng)站制作、品牌網(wǎng)站設(shè)計(jì)

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請(qǐng)盡快告知，我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng)，如需處理請(qǐng)聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時(shí)需注明來(lái)源：創(chuàng)新互聯(lián)

猜你還喜歡下面的內(nèi)容