'''This script goes along the blog post

"Building powerful image classification models using very little data"

from blog.keras.io.

It uses data that can be downloaded at:

https://www.kaggle.com/c/dogs-vs-cats/data

In our setup, we:

- created a data/ folder

- created train/ and validation/ subfolders inside data/

- created cats/ and dogs/ subfolders inside train/ and validation/

- put the cat pictures index - in data/train/cats

- put the cat pictures index - in data/validation/cats

- put the dogs pictures index - in data/train/dogs

- put the dog pictures index - in data/validation/dogs

So that we have  training examples for each class, and  validation examples for each class.

In summary, this is our directory structure:

```

data/

    train/

        dogs/

            dog001.jpg

            dog002.jpg

            ...

        cats/

            cat001.jpg

            cat002.jpg

            ...

    validation/

        dogs/

            dog001.jpg

            dog002.jpg

            ...

        cats/

            cat001.jpg

            cat002.jpg

            ...

```

'''

import numpy as np

from keras.preprocessing.image import ImageDataGenerator

from keras.models import Sequential

from keras.layers import Dropout, Flatten, Dense

from keras import applications

# dimensions of our images.

img_width, img_height = , 

top_model_weights_path = 'bottleneck_fc_model.h5'

data_root = 'M:/dataset/dog_cat/'

train_data_dir =data_root+ 'data/train'

validation_data_dir = data_root+'data/validation'

nb_train_samples =

nb_validation_samples =

epochs =

batch_size = 

def save_bottlebeck_features():

    datagen = ImageDataGenerator(rescale=. / )

    # build the VGG16 network

    model = applications.VGG16(include_top=False, weights='imagenet')

    generator = datagen.flow_from_directory(

        train_data_dir,

        target_size=(img_width, img_height),

        batch_size=batch_size,

        class_mode=None,

        shuffle=False)

    bottleneck_features_train = model.predict_generator(

        generator, nb_train_samples // batch_size) #####2000//batch_size！！！！！！！！！！

    np.save('bottleneck_features_train.npy',

            bottleneck_features_train)

    generator = datagen.flow_from_directory(

        validation_data_dir,

        target_size=(img_width, img_height),

        batch_size=batch_size,

        class_mode=None,

        shuffle=False)

    bottleneck_features_validation = model.predict_generator(

        generator, nb_validation_samples // batch_size)

    np.save('bottleneck_features_validation.npy',

            bottleneck_features_validation)

def train_top_model():

    train_data = np.load('bottleneck_features_train.npy')

    train_labels = np.array([] * int(nb_train_samples / ) + [] * int(nb_train_samples / ))

    validation_data = np.load('bottleneck_features_validation.npy')

    validation_labels = np.array([] * int(nb_validation_samples / ) + [] * int(nb_validation_samples / ))

    model = Sequential()

    model.add(Flatten(input_shape=train_data.shape[:]))

    model.add(Dense(, activation='relu'))

    model.add(Dropout(0.5))

    model.add(Dense(, activation='sigmoid'))

    model.compile(optimizer='rmsprop',

                  loss='binary_crossentropy', metrics=['accuracy'])

    model.fit(train_data, train_labels,

              epochs=epochs,

              batch_size=batch_size,

              validation_data=(validation_data, validation_labels))

    model.save_weights(top_model_weights_path)

#save_bottlebeck_features()

train_top_model()

'''This script goes along the blog post

"Building powerful image classification models using very little data"

from blog.keras.io.

It uses data that can be downloaded at:

https://www.kaggle.com/c/dogs-vs-cats/data

In our setup, we:

- created a data/ folder

- created train/ and validation/ subfolders inside data/

- created cats/ and dogs/ subfolders inside train/ and validation/

- put the cat pictures index - in data/train/cats

- put the cat pictures index - in data/validation/cats

- put the dogs pictures index - in data/train/dogs

- put the dog pictures index - in data/validation/dogs

So that we have  training examples for each class, and  validation examples for each class.

In summary, this is our directory structure:

```

data/

    train/

        dogs/

            dog001.jpg

            dog002.jpg

            ...

        cats/

            cat001.jpg

            cat002.jpg

            ...

    validation/

        dogs/

            dog001.jpg

            dog002.jpg

            ...

        cats/

            cat001.jpg

            cat002.jpg

            ...

```

'''

# thanks sove bug @http://blog.csdn.net/aggresss/article/details/78588135

from keras import applications

from keras.preprocessing.image import ImageDataGenerator

from keras import optimizers

from keras.models import Sequential

from keras.layers import Dropout, Flatten, Dense

from keras.models import Model

from keras.regularizers import l2

# path to the model weights files.

weights_path = '../keras/examples/vgg16_weights.h5'

top_model_weights_path = 'bottleneck_fc_model.h5'

# dimensions of our images.

img_width, img_height = , 

data_root = 'M:/dataset/dog_cat/'

train_data_dir =data_root+ 'data/train'

validation_data_dir = data_root+'data/validation'

nb_train_samples =

nb_validation_samples =

epochs =

batch_size = 

# build the VGG16 network

base_model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(,,)) # train 指定训练大小

print('Model loaded.')

# build a classifier model to put on top of the convolutional model

top_model = Sequential()

top_model.add(Flatten(input_shape=base_model.output_shape[:]))  # base_model.output_shape[:])

top_model.add(Dense(, activation='relu',kernel_regularizer=l2(0.001),))

top_model.add(Dropout(0.8))

top_model.add(Dense(, activation='sigmoid'))

# note that it is necessary to start with a fully-trained

# classifier, including the top classifier,

# in order to successfully do fine-tuning

top_model.load_weights(top_model_weights_path)

# add the model on top of the convolutional base

# model.add(top_model) # bug

model = Model(inputs=base_model.input, outputs=top_model(base_model.output))

# set the first  layers (up to the last conv block)

# to non-trainable (weights will not be updated)

for layer in model.layers[:]:  # : bug

    layer.trainable = False

# compile the model with a SGD/momentum optimizer

# and a very slow learning rate.

model.compile(loss='binary_crossentropy',

              optimizer=optimizers.SGD(lr=1e-, momentum=0.9),

              metrics=['accuracy'])

# prepare data augmentation configuration

train_datagen = ImageDataGenerator(

    rescale=. / ,

    shear_range=0.2,

    zoom_range=0.2,

    horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=. / )

train_generator = train_datagen.flow_from_directory(

    train_data_dir,

    target_size=(img_height, img_width),

    batch_size=batch_size,

    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(

    validation_data_dir,

    target_size=(img_height, img_width),

    batch_size=batch_size,

    class_mode='binary')

model.summary() # prints a summary representation of your model.

# let's visualize layer names and layer indices to see how many layers

# we should freeze:

for i, layer in enumerate(base_model.layers):

    print(i, layer.name)

from keras.utils import plot_model

plot_model(model, to_file='model.png')

from keras.callbacks import History

from keras.callbacks import ModelCheckpoint

import keras

history = History()

model_checkpoint = ModelCheckpoint('temp_model.hdf5', monitor='loss', save_best_only=True)

tb_cb = keras.callbacks.TensorBoard(log_dir='log', write_images=, histogram_freq=)

# 设置log的存储位置，将网络权值以图片格式保持在tensorboard中显示，设置每一个周期计算一次网络的

# 权值，每层输出值的分布直方图

callbacks = [

        history,

        model_checkpoint,

        tb_cb

    ]

# model.fit()

# fine-tune the model

history=model.fit_generator(

    train_generator,

    steps_per_epoch=nb_train_samples // batch_size,

    epochs=epochs,

    callbacks=callbacks,

    validation_data=validation_generator,

    validation_steps=nb_validation_samples // batch_size,

    verbose = )

model.save('fine_tune_model.h5')

model.save_weights('fine_tune_model_weight')

print(history.history)

from matplotlib import pyplot as plt

history=history

plt.plot()

plt.plot(history.history['val_acc'])

plt.title('model accuracy')

plt.ylabel('accuracy')

plt.xlabel('epoch')

plt.legend(['train', 'test'], loc='upper left')

plt.show()

# summarize history for loss

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model loss')

plt.ylabel('loss')

plt.xlabel('epoch')

plt.legend(['train', 'test'], loc='upper left')

plt.show()

import  numpy as np

accy=history.history['acc']

np_accy=np.array(accy)

np.savetxt('save_acc.txt',np_accy)

Model loaded.

Found  images belonging to  classes.

Found  images belonging to  classes.

_________________________________________________________________

Layer (type)                 Output Shape              Param #

=================================================================

input_1 (InputLayer)         (None, , , )

_________________________________________________________________

block1_conv1 (Conv2D)        (None, , , )

_________________________________________________________________

block1_conv2 (Conv2D)        (None, , , )

_________________________________________________________________

block1_pool (MaxPooling2D)   (None, , , )

_________________________________________________________________

block2_conv1 (Conv2D)        (None, , , )

_________________________________________________________________

block2_conv2 (Conv2D)        (None, , , )

_________________________________________________________________

block2_pool (MaxPooling2D)   (None, , , )

_________________________________________________________________

block3_conv1 (Conv2D)        (None, , , )

_________________________________________________________________

block3_conv2 (Conv2D)        (None, , , )

_________________________________________________________________

block3_conv3 (Conv2D)        (None, , , )

_________________________________________________________________

block3_pool (MaxPooling2D)   (None, , , )

_________________________________________________________________

block4_conv1 (Conv2D)        (None, , , )

_________________________________________________________________

block4_conv2 (Conv2D)        (None, , , )

_________________________________________________________________

block4_conv3 (Conv2D)        (None, , , )

_________________________________________________________________

block4_pool (MaxPooling2D)   (None, , , )

_________________________________________________________________

block5_conv1 (Conv2D)        (None, , , )

_________________________________________________________________

block5_conv2 (Conv2D)        (None, , , )

_________________________________________________________________

block5_conv3 (Conv2D)        (None, , , )

_________________________________________________________________

block5_pool (MaxPooling2D)   (None, , , )

_________________________________________________________________

sequential_1 (Sequential)    (None, )

=================================================================

Total params: ,,

Trainable params: ,,

Non-trainable params: ,,

_________________________________________________________________

 input_1

 block1_conv1

 block1_conv2

 block1_pool

 block2_conv1

 block2_conv2

 block2_pool

 block3_conv1

 block3_conv2

 block3_conv3

 block3_pool

 block4_conv1

 block4_conv2

 block4_conv3

 block4_pool

 block5_conv1

 block5_conv2

 block5_conv3

 block5_pool

Backend TkAgg is interactive backend. Turning interactive mode on.