from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
datagen = ImageDataGenerator(
rotation_range=40,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
fill_mode='nearest')
img = load_img('data/train/cats/cat.0.jpg') # this is a PIL image
x = img_to_array(img) # this is a Numpy array with shape (3, 150, 150)
x = x.reshape((1,) + x.shape) # this is a Numpy array with shape (1, 3, 150, 150)
# the .flow() command below generates batches of randomly transformed images
# and saves the results to the `preview/` directory
i = 0
for batch in datagen.flow(x, batch_size=1,
save_to_dir='preview', save_prefix='cat', save_format='jpeg'):
i += 1
if i > 20:
break # otherwise the generator would loop indefinitely
batch_size = 16
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)
# this is a generator that will read pictures found in
# subfolers of 'data/train', and indefinitely generate
# batches of augmented image data
train_generator = train_datagen.flow_from_directory(
'data/train', # this is the target directory
target_size=(150, 150), # all images will be resized to 150x150
batch_size=batch_size,
class_mode='binary') # since we use binary_crossentropy loss, we need binary labels
# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(
'data/validation',
target_size=(150, 150),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=2000 // batch_size,
epochs=50,
validation_data=validation_generator,
validation_steps=800 // batch_size)
model.save_weights('first_try.h5') # always save your weights after training or during training
batch_size = 16
generator = datagen.flow_from_directory(
'data/train',
target_size=(150, 150),
batch_size=batch_size,
class_mode=None, # this means our generator will only yield batches of data, no labels
shuffle=False) # our data will be in order, so all first 1000 images will be cats, then 1000 dogs
# the predict_generator method returns the output of a model, given
# a generator that yields batches of numpy data
bottleneck_features_train = model.predict_generator(generator, 2000)
# save the output as a Numpy array
np.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)
generator = datagen.flow_from_directory(
'data/validation',
target_size=(150, 150),
batch_size=batch_size,
class_mode=None,
shuffle=False)
bottleneck_features_validation = model.predict_generator(generator, 800)
np.save(open('bottleneck_features_validation.npy', 'w'), bottleneck_features_validation)
然后我们可以加载我们保存的数据并训练一个小的完全连接的模型：
train_data = np.load(open('bottleneck_features_train.npy'))
# the features were saved in order, so recreating the labels is easy
train_labels = np.array([0] * 1000 + [1] * 1000)
validation_data = np.load(open('bottleneck_features_validation.npy'))
validation_labels = np.array([0] * 400 + [1] * 400)
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(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(train_data, train_labels,
epochs=50,
batch_size=batch_size,
validation_data=(validation_data, validation_labels))
model.save_weights('bottleneck_fc_model.h5')
# build a classifier model to put on top of the convolutional model
top_model = Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
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)
然后我们继续将所有卷积层冻结到最后一个卷积块：
# set the first 25 layers (up to the last conv block)
# to non-trainable (weights will not be updated)
for layer in model.layers[:25]:
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'])
