Keras

Data Augmentation

In Keras this can be done via the keras.preprocessing.image.ImageDataGenerator class. This class allows you to:configure random transformations and normalization operations to be done on your image data during training instantiate generators of augmented image batches (and their labels) via .flow(data, labels) or .flow_from_directory(directory). These generators can then be used with the Keras model methods that accept data generators as inputs, fit_generator, evaluate_generator and predict_generator.

How can I interrupt training when the validation loss isn’t decreasing anymore?

from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(monitor='val_loss', patience=2)
model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])

How can I obtain the output of an intermediate layer?

from keras.models import Model
model = ...  # create the original model
layer_name = 'my_layer'
intermediate_layer_model = Model(inputs=model.input,
                                 outputs=model.get_layer(layer_name).output)
intermediate_output = intermediate_layer_model.predict(data)

Build a Keras function that will return the output of a certain layer given a certain input

from keras import backend as K
# with a Sequential model
get_3rd_layer_output = K.function([model.layers[0].input],
                                  [model.layers[3].output])
layer_output = get_3rd_layer_output([X])[0]

If your model has a different behavior in training and testing phase (e.g. if it uses Dropout, BatchNormalization, etc.), you will need to pass the learning phase flag to your function:

get_3rd_layer_output = K.function([model.layers[0].input,  K.learning_phase()],                                 [model.layers[3].output])
layer_output = get_3rd_layer_output([X, 0])[0]
layer_output = get_3rd_layer_output([X, 1])[0]

How can I use pre-trained models in Keras?

from keras.applications.xception import Xception
from keras.applications.vgg16 import VGG16
from keras.applications.vgg19 import VGG19
from keras.applications.resnet50 import ResNet50
from keras.applications.inception_v3 import InceptionV3
model = VGG16(weights='imagenet', include_top=True)