'''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 0-999 in data/train/cats
- put the cat pictures index 1000-1400 in data/validation/cats
- put the dogs pictures index 12500-13499 in data/train/dogs
- put the dog pictures index 13500-13900 in data/validation/dogs
So that we have 1000 training examples for each class, and 400 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 = 150, 150
data_root = 'M:/dataset/dog_cat/'
train_data_dir =data_root+ 'data/train'
validation_data_dir = data_root+'data/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16
# build the VGG16 network
base_model = applications.VGG16(weights='imagenet', include_top=False, input_shape=(150,150,3)) # 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[1:])) # base_model.output_shape[1:])
top_model.add(Dense(256, activation='relu',kernel_regularizer=l2(0.001),))
top_model.add(Dropout(0.8))
top_model.add(Dense(1, 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 25 layers (up to the last conv block)
# to non-trainable (weights will not be updated)
for layer in model.layers[:15]: # :25 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-4, momentum=0.9),
metrics=['accuracy'])
# prepare data augmentation configuration
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
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=1, histogram_freq=0)
# 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 = 2)
//保存模型和权重
model.save('fine_tune_model.h5')
model.save_weights('fine_tune_model_weight')
print(history.history)
//可视化部分
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)
