keras搭建VGG、ResNet、GoogleNet InceptionV3实现图像的多分类任务

发布时间:2020-09-14 16:03:08 作者:ckllf
来源:网络 阅读:1015

  基于keras实现分类任务

  基于keras利用VGG、ResNet、GoogleNet InceptionV3实现图像的分类任务,下面会给出完整代码,但为了熟悉不同整个网络的特点,建议大家自己搭建一下每个分类网络,毕竟利用keras搭建网络还是比较简单的。

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

  import os

  from keras.utils import plot_model

  from keras.applications.resnet50 import ResNet50

  from keras.applications.vgg19 import VGG19

  from keras.applications.inception_v3 import InceptionV3

  from keras.layers import Dense,Flatten,GlobalAveragePooling2D

  from keras.models import Model,load_model

  from keras.optimizers import SGD

  from keras.preprocessing.image import ImageDataGenerator

  import matplotlib.pyplot as plt

  class PowerTransferMode:

  #数据准备

  def DataGen(self, dir_path, img_row, img_col, batch_size, is_train):

  if is_train:

  datagen = ImageDataGenerator(rescale=1./255,

  zoom_range=0.25, rotation_range=15.,

  channel_shift_range=25., width_shift_range=0.02, height_shift_range=0.02,

  horizontal_flip=True, fill_mode='constant')

  else:

  datagen = ImageDataGenerator(rescale=1./255)

  generator = datagen.flow_from_directory(

  dir_path, target_size=(img_row, img_col),

  batch_size=batch_size,

  #class_mode='binary',

  class_mode='categorical',

  shuffle=is_train)

  return generator

  #ResNet模型

  def ResNet50_model(self, lr=0.005, decay=1e-6, momentum=0.9, nb_classes=2, img_rows=197, img_cols=197, RGB=True, is_plot_model=False):

  color = 3 if RGB else 1

  base_model = ResNet50(weights='imagenet', include_top=False, pooling=None, input_shape=(img_rows, img_cols, color),

  classes=nb_classes)

  #冻结base_model所有层,这样就可以正确获得bottleneck特征

  for layer in base_model.layers:

  layer.trainable = False

  x = base_model.output

  #添加自己的全链接分类层

  x = Flatten()(x)

  #x = GlobalAveragePooling2D()(x)

  #x = Dense(1024, activation='relu')(x)

  predictions = Dense(nb_classes, activation='softmax')(x)

  #训练模型

  model = Model(inputs=base_model.input, outputs=predictions)

  sgd = SGD(lr=lr, decay=decay, momentum=momentum, nesterov=True)

  model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

  #绘制模型

  if is_plot_model:

  plot_model(model, to_file='resnet50_model.png',show_shapes=True)

  return model

  #VGG模型

  def VGG19_model(self, lr=0.005, decay=1e-6, momentum=0.9, nb_classes=18, img_rows=197, img_cols=197, RGB=True, is_plot_model=False):

  color = 3 if RGB else 1

  base_model = VGG19(weights='imagenet', include_top=False, pooling=None, input_shape=(img_rows, img_cols, color),

  classes=nb_classes)

  #冻结base_model所有层,这样就可以正确获得bottleneck特征

  for layer in base_model.layers:

  layer.trainable = False

  x = base_model.output

  #添加自己的全链接分类层

  x = GlobalAveragePooling2D()(x)

  x = Dense(1024, activation='relu')(x)

  x = Dense(1024, activation='relu')(x)

  predictions = Dense(nb_classes, activation='softmax')(x)

  #训练模型

  model = Model(inputs=base_model.input, outputs=predictions)

  sgd = SGD(lr=lr, decay=decay, momentum=momentum, nesterov=True)

  model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

  # 绘图

  if is_plot_model:

  plot_model(model, to_file='vgg19_model.png',show_shapes=True)

  return model

  # InceptionV3模型

  def InceptionV3_model(self, lr=0.005, decay=1e-6, momentum=0.9, nb_classes=18, img_rows=197, img_cols=197, RGB=True,

  is_plot_model=False):

  color = 3 if RGB else 1

  base_model = InceptionV3(weights='imagenet', include_top=False, pooling=None,

  input_shape=(img_rows, img_cols, color),

  classes=nb_classes)

  # 冻结base_model所有层,这样就可以正确获得bottleneck特征

  for layer in base_model.layers:

  layer.trainable = False

  x = base_model.output

  # 添加自己的全链接分类层

  x = GlobalAveragePooling2D()(x)

  x = Dense(1024, activation='relu')(x)

  #x = GlobalAveragePooling2D()(x)

  x = Dense(1024, activation='relu')(x)

  predictions = Dense(nb_classes, activation='softmax')(x)

  # 训练模型

  model = Model(inputs=base_model.input, outputs=predictions)

  sgd = SGD(lr=lr, decay=decay, momentum=momentum, nesterov=True)

  model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

  # 绘图

  if is_plot_model:

  plot_model(model, to_file='inception_v3_model.png', show_shapes=True)

  return model

  #训练模型

  def train_model(self, model, epochs, train_generator, steps_per_epoch, validation_generator, validation_steps, model_url, is_load_model=False):

  # 载入模型郑州人流医院 http://www.zykdfk.com/

  if is_load_model and os.path.exists(model_url):

  model = load_model(model_url)

  history_ft = model.fit_generator(

  train_generator,

  steps_per_epoch=steps_per_epoch,

  epochs=epochs,

  validation_data=validation_generator,

  validation_steps=validation_steps)

  # 模型保存

  model.save(model_url,overwrite=True)

  return history_ft

  # 画图

  def plot_training(self, history):

  acc = history.history['accuracy']

  val_acc = history.history['val_accuracy']

  loss = history.history['loss']

  val_loss = history.history['val_loss']

  epochs = range(len(acc))

  plt.plot(epochs, acc, 'b-')

  plt.plot(epochs, val_acc, 'r')

  plt.title('Training and validation accuracy')

  plt.figure()

  plt.plot(epochs, loss, 'b-')

  plt.plot(epochs, val_loss, 'r-')

  plt.title('Training and validation loss')

  plt.show()

  if __name__ == '__main__':

  #os.environ['CUDA_VISIBLE_DEVICES'] = '-1'

  image_size = 256

  batch_size = 32

  epo = 1000

  transfer = PowerTransferMode()

  num_train = 14470

  num_test = 3215

  #得到数据

  train_generator = transfer.DataGen('/home/jjin/skin_diagnosis/class_test_3/train/', image_size, image_size, batch_size, True)

  validation_generator = transfer.DataGen("/home/jjin/skin_diagnosis/class_test_3/test/", image_size, image_size, batch_size, False)

  #VGG19

  model = transfer.VGG19_model(nb_classes=18, img_rows=image_size, img_cols=image_size, is_plot_model=False)

  history_ft1 = transfer.train_model(model, epo, train_generator, num_train//batch_size, validation_generator, num_test//batch_size, 'vgg19_model_weights.h6', is_load_model=False)

  #ResNet50

  #model = transfer.ResNet50_model(nb_classes=2, img_rows=image_size, img_cols=image_size, is_plot_model=False)

  #history_ft = transfer.train_model(model, 10, train_generator, 600, validation_generator, 60, 'resnet50_model_weights.h6', is_load_model=False)

  #InceptionV3

  model = transfer.InceptionV3_model(nb_classes=18, img_rows=image_size, img_cols=image_size, is_plot_model=True)

  # 分多次进行训练,没训练100次,保存一下模型

  for _ in range(10):

  history_ft2 = transfer.train_model(model, 100, train_generator, num_train//batch_size, validation_generator, num_test//batch_size, 'inception_v3_model_weights .h6', is_load_model=False)

  # 训练的acc_loss图

  transfer.plot_training(history_ft1)

  transfer.plot_training(history_ft2)

  在这里有几点要提醒一下,虽然3个网络都搭建出来了,但我只训练了其中的两个网络,其中,在训练InceptionV3时,我把训练过程分为了10个循环,每个循环的epoch是100,这是为了每一个循环后都能保存一下模型,而不至于因为某些原因,导致训练中断,模型没有保存下来。


推荐阅读:
  1. keras 读取多标签图像数据的方法
  2. 关于keras中自定义二分类任务评价指标metrics的用法

免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。

keras ce vg

上一篇:JS中图片压缩的方法小结

下一篇:python+logging+yaml实现日志分割

相关阅读

您好,登录后才能下订单哦!

密码登录
登录注册
其他方式登录
点击 登录注册 即表示同意《亿速云用户服务条款》