新建文本文档_VGG16_迁移学习_卷积神经网络_多分类_迁移图像分类_

import numpy as np import os,random,shutil np.random.seed(7) train_data_dir='C:/Users/Administrator/Desktop/p and j and w/train' val_data_dir='C:/Users/Administrator/Desktop/p and j and w/validation' train_samples_num=90 val_samples_num=60 IMG_W,IMG_H,IMG_CH=224,224,3 batch_size=6 epochs=20 class_num=3 save_folder='C:/Users/Administrator/Desktop/many classfier' from keras.preprocessing.image import ImageDataGenerator from keras.models import Sequential from keras import layers from keras.layers import Dropout,Flatten,Dense from keras import applications def save_bottlebeck_features(): datagen=ImageDataGenerator(rescale=1./255) model=applications.VGG16(include_top=False,weights='imagenet') generator=datagen.flow_from_directory(train_data_dir,target_size=(IMG_W,IMG_H),batch_size=batch_size,class_mode='categorical',shuffle=False) bottleneck_features_train=model.predict_generator(generator,train_samples_num//batch_size) np.save(os.path.join(save_folder,'bottleneck_features_train.npy'),bottleneck_features_train) print('bottleneck features of train set is saved.') generator = datagen.flow_from_directory(val_data_dir, target_size=(IMG_W, IMG_H), batch_size=batch_size, class_mode='categorical', shuffle=False) #多分类问题 class_mode='categorical' bottleneck_features_validation=model.predict_generator(generator,val_samples_num//batch_size) np.save(os.path.join(save_folder,'bottleneck_features_val.npy'),bottleneck_features_validation) print('bottleneck features of test set is saved.') save_bottlebeck_features() from keras import optimizers def my_model(): model=Sequential() model.add(Flatten(input_shape=train_data.shape[1:])) model.add(Dense(256,activation='relu')) model.add(Dropout(0.5)) model.add(Dense(class_num,activation='softmax')) rms=optimizers.RMSprop(lr=0.00001) model.compile(optimizer=rms,loss='categorical_crossentropy',metrics=['acc']) return model from keras.utils import to_categorical train_data=np.load(os.path.join(save_folder,'bottleneck_features_train.npy')) train_labels=np.array([0]*int((train_samples_num/class_num))+[1]*int((train_samples_num/class_num))+[2]*int((train_samples_num/class_num))) train_labels=to_categorical(train_labels,class_num) validation_data=np.load(os.path.join(save_folder,'bottleneck_features_val.npy')) validation_labels=np.array([0]*int((val_samples_num/class_num))+[1]*int((val_samples_num/class_num))+[2]*int((val_samples_num/class_num))) validation_labels=to_categorical(validation_labels,class_num) #构建模型分类器 clf_model=my_model() history_ft=clf_model.fit(train_data,train_labels,epochs=epochs,batch_size=batch_size,validation_data=(validation_data,validation_labels)) import matplotlib.pyplot as plt def plot_training(history): plt.figure(12) plt.subplot(121) train_acc=history.history['acc'] val_acc=history.history['val_acc'] epochs=range(1,len(train_acc)+1) plt.plot(epochs,train_acc,'b',label='train_acc') plt.plot(epochs,val_acc,'r',label='test_acc') plt.title('train and test acc') plt.legend() plt.subplot(122) train_loss=history.history['loss'] val_loss=history.history['val_loss'] epochs=range(1,len(train_loss)+1) plt.plot(epochs,train_loss,'b',label='train_loss') plt.plot(epochs,val_loss,'r',label='test_loss') plt.title('train and test loss') plt.legend() plt.show() plot_training(history_ft) clf_model.save_weights(os.path.join(save_folder,'top_FC_model'))