Applications

Keras Applications are deep learning models that are made available alongside pre-trained weights. These models can be used for prediction, feature extraction, and fine-tuning.

Weights are downloaded automatically when instantiating a model. They are stored at ~/.keras/models/.

Available models

Models for image classification with weights trained on ImageNet:

VGG16
VGG19
ResNet50
InceptionV3

All of these architectures are compatible with both TensorFlow and Theano, and upon instantiation the models will be built according to the image dimension ordering set in your Keras configuration file at ~/.keras/keras.json. For instance, if you have set image_dim_ordering=tf, then any model loaded from this repository will get built according to the TensorFlow dimension ordering convention, "Width-Height-Depth".

Examples

Classify ImageNet classes with ResNet50

from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input, decode_predictions

model = ResNet50(weights='imagenet')

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
# print: [[u'n02504458', u'African_elephant']]

Extract features with VGG16

from keras.applications.vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input

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

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

features = model.predict(x)

Extract features from an arbitrary intermediate layer with VGG19

from keras.applications.vgg19 import VGG19
from keras.preprocessing import image
from keras.applications.vgg19 import preprocess_input
from keras.models import Model

base_model = VGG19(weights='imagenet')
model = Model(input=base_model.input, output=base_model.get_layer('block4_pool').output)

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

block4_pool_features = model.predict(x)

Fine-tune InceptionV3 on a new set of classes

from keras.applications.inception_v3 import InceptionV3
from keras.preprocessing import image
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras import backend as K

# create the base pre-trained model
base_model = InceptionV3(weights='imagenet', include_top=False)

# add a global spatial average pooling layer
x = base_model.output
x = GlobalAveragePooling2D()(x)
# let's add a fully-connected layer
x = Dense(1024, activation='relu')(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(200, activation='softmax')(x)

# this is the model we will train
model = Model(input=base_model.input, output=predictions)

# first: train only the top layers (which were randomly initialized)
# i.e. freeze all convolutional InceptionV3 layers
for layer in base_model.layers:
    layer.trainable = False

# compile the model (should be done *after* setting layers to non-trainable)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')

# train the model on the new data for a few epochs
model.fit_generator(...)

# at this point, the top layers are well trained and we can start fine-tuning
# convolutional layers from inception V3. We will freeze the bottom N layers
# and train the remaining top layers.

# 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)

# we chose to train the top 2 inception blocks, i.e. we will freeze
# the first 172 layers and unfreeze the rest:
for layer in model.layers[:172]:
   layer.trainable = False
for layer in model.layers[172:]:
   layer.trainable = True

# we need to recompile the model for these modifications to take effect
# we use SGD with a low learning rate
from keras.optimizers import SGD
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='categorical_crossentropy')

# we train our model again (this time fine-tuning the top 2 inception blocks
# alongside the top Dense layers
model.fit_generator(...)

Build InceptionV3 over a custom input tensor

from keras.applications.inception_v3 import InceptionV3
from keras.layers import Input

# this could also be the output a different Keras model or layer
input_tensor = Input(shape=(224, 224, 3))  # this assumes K.image_dim_ordering() == 'tf'

model = InceptionV3(input_tensor=input_tensor, weights='imagenet', include_top=True)

VGG16

keras.applications.vgg16.VGG16(include_top=True, weights='imagenet', input_tensor=None)

Arguments

include_top: whether to include the 3 fully-connected layers at the top of the network.
weights: one of None (random initialization) or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Returns

A Keras model instance.

References

Very Deep Convolutional Networks for Large-Scale Image Recognition: please cite this paper if you use the VGG models in your work.

License

These weights are ported from the ones released by VGG at Oxford under the Creative Commons Attribution License.

VGG19

keras.applications.vgg19.VGG19(include_top=True, weights='imagenet', input_tensor=None)

Arguments

include_top: whether to include the 3 fully-connected layers at the top of the network.
weights: one of None (random initialization) or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Returns

A Keras model instance.

References

Very Deep Convolutional Networks for Large-Scale Image Recognition

License

These weights are ported from the ones released by VGG at Oxford under the Creative Commons Attribution License.

ResNet50

keras.applications.resnet50.ResNet50(include_top=True, weights='imagenet', input_tensor=None)

Arguments

include_top: whether to include the 3 fully-connected layers at the top of the network.
weights: one of None (random initialization) or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Returns

A Keras model instance.

References

Deep Residual Learning for Image Recognition

License

These weights are ported from the ones released by Kaiming He under the MIT license.

InceptionV3

keras.applications.inception_v3.InceptionV3(include_top=True, weights='imagenet', input_tensor=None)

Arguments

include_top: whether to include the 3 fully-connected layers at the top of the network.
weights: one of None (random initialization) or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.

Returns

A Keras model instance.

References

Rethinking the Inception Architecture for Computer Vision

License

These weights are trained by ourselves and are released under the MIT license.