6.1 KiB
6.1 KiB
Here are a few examples to get you started!
Multilayer Perceptron (MLP):
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(64, input_dim=20, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(2, init='uniform'))
model.add(Activation('softmax'))
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)
model.fit(X_train, y_train, nb_epoch=20, batch_size=16)
score = model.evaluate(X_test, y_test, batch_size=16)
Alternative implementation of MLP:
model = Sequential()
model.add(Dense(64, input_dim=20, init='uniform', activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform', activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(2, init='uniform', activation='softmax'))
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)
VGG-like convnet:
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD
model = Sequential()
# input: 100x100 images with 3 channels -> (3, 100, 100) tensors.
# this applies 32 convolution filters of size 3x3 each.
model.add(Convolution2D(32, 3, 3, border_mode='full', input_shape=(3, 100, 100)))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Convolution2D(64, 3, 3, border_mode='valid'))
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
# Note: Keras does automatic shape inference.
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
model.fit(X_train, Y_train, batch_size=32, nb_epoch=1)
Sequence classification with LSTM:
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM
model = Sequential()
model.add(Embedding(max_features, 256, input_length=maxlen))
model.add(LSTM(output_dim=128, activation='sigmoid', inner_activation='hard_sigmoid'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop')
model.fit(X_train, Y_train, batch_size=16, nb_epoch=10)
score = model.evaluate(X_test, Y_test, batch_size=16)
Architecture for learning image captions with a convnet and a Gated Recurrent Unit:
(word-level embedding, caption of maximum length 16 words).
Note that getting this to work well will require using a bigger convnet, initialized with pre-trained weights.
max_caption_len = 16
vocab_size = 10000
# first, let's define an image model that
# will encode pictures into 128-dimensional vectors.
# it should be initialized with pre-trained weights.
image_model = Sequential()
image_model.add(Convolution2D(32, 3, 3, border_mode='full', input_shape=(3, 100, 100)))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(32, 3, 3))
image_model.add(Activation('relu'))
image_model.add(MaxPooling2D(pool_size=(2, 2)))
image_model.add(Convolution2D(64, 3, 3, border_mode='full'))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 3, 3))
image_model.add(Activation('relu'))
image_model.add(MaxPooling2D(pool_size=(2, 2)))
image_model.add(Flatten())
image_model.add(Dense(128))
# let's load the weights from a save file.
image_model.load_weights('weight_file.h5')
# next, let's define a RNN model that encodes sequences of words
# into sequences of 128-dimensional word vectors.
language_model = Sequential()
language_model.add(Embedding(vocab_size, 256, input_length=max_caption_len))
language_model.add(GRU(output_dim=128, return_sequences=True))
language_model.add(TimeDistributedDense(128))
# let's repeat the image vector to turn it into a sequence.
image_model.add(RepeatVector(max_caption_len))
# the output of both models will be tensors of shape (samples, max_caption_len, 128).
# let's concatenate these 2 vector sequences.
model = Merge([image_model, language_model], mode='concat', concat_axis=-1)
# let's encode this vector sequence into a single vector
model.add(GRU(256, 256, return_sequences=False))
# which will be used to compute a probability
# distribution over what the next word in the caption should be!
model.add(Dense(vocab_size))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
# "images" is a numpy float array of shape (nb_samples, nb_channels=3, width, height).
# "captions" is a numpy integer array of shape (nb_samples, max_caption_len)
# containing word index sequences representing partial captions.
# "next_words" is a numpy float array of shape (nb_samples, vocab_size)
# containing a categorical encoding (0s and 1s) of the next word in the corresponding
# partial caption.
model.fit([images, partial_captions], next_words, batch_size=16, nb_epoch=100)
In the examples folder, you will find example models for real datasets:
- CIFAR10 small images classification: Convolutional Neural Network (CNN) with realtime data augmentation
- IMDB movie review sentiment classification: LSTM over sequences of words
- Reuters newswires topic classification: Multilayer Perceptron (MLP)
- MNIST handwritten digits classification: MLP & CNN
- Character-level text generation with LSTM
...and more.