A recurrent neural network (RNN) is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior.
keras.layers.recurrent.SimpleRNN(units, activation='tanh', use_bias=True,
kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal',
bias_initializer='zeros',
kernel_regularizer=None,
recurrent_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None, recurrent_constraint=None,
bias_constraint=None, dropout=0.0, recurrent_dropout=0.0)
a(x) = x).kernel weights matrix,
used for the linear transformation of the inputs.
(see initializers).recurrent_kernel
weights matrix,
used for the linear transformation of the recurrent state.
(see initializers).kernel weights matrix
(see regularizer).recurrent_kernel weights matrix
(see regularizer).kernel weights matrix
(see constraints).recurrent_kernel weights matrix
(see constraints).Contrary to feed-forward neural networks, the RNN is characterized by the ability of encoding longer past information, thus very suitable for sequential models. The BPTT extends the ordinary BP algorithm to suit the recurrent neural architecture.
Reference: Backpropagation through Time
In [1]:
%matplotlib inline
In [3]:
import numpy as np
import pandas as pd
#import theano
#import theano.tensor as T
import keras
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
# -- Keras Import
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.preprocessing import image
from keras.datasets import imdb
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.preprocessing import sequence
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM, GRU, SimpleRNN
from keras.layers import Activation, TimeDistributed, RepeatVector
from keras.callbacks import EarlyStopping, ModelCheckpoint
This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets.
IMDB provided a set of 25,000 highly polar movie reviews for training, and 25,000 for testing.
There is additional unlabeled data for use as well. Raw text and already processed bag of words formats are provided.
In [4]:
max_features = 20000
maxlen = 100 # cut texts after this number of words (among top max_features most common words)
batch_size = 32
print("Loading data...")
(X_train, y_train), (X_test, y_test) = imdb.load_data(num_words=max_features)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
print('Example:')
print(X_train[:1])
print("Pad sequences (samples x time)")
X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
In [7]:
print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
model.add(SimpleRNN(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adam')
print("Train...")
model.fit(X_train, y_train, batch_size=batch_size, epochs=1,
validation_data=(X_test, y_test))
Out[7]:
A LSTM network is an artificial neural network that contains LSTM blocks instead of, or in addition to, regular network units. A LSTM block may be described as a "smart" network unit that can remember a value for an arbitrary length of time.
Unlike traditional RNNs, an Long short-term memory network is well-suited to learn from experience to classify, process and predict time series when there are very long time lags of unknown size between important events.
keras.layers.recurrent.LSTM(units, activation='tanh', recurrent_activation='hard_sigmoid', use_bias=True,
kernel_initializer='glorot_uniform', recurrent_initializer='orthogonal',
bias_initializer='zeros', unit_forget_bias=True, kernel_regularizer=None,
recurrent_regularizer=None, bias_regularizer=None, activity_regularizer=None,
kernel_constraint=None, recurrent_constraint=None, bias_constraint=None,
dropout=0.0, recurrent_dropout=0.0)
a(x) = x).kernel weights matrix,
used for the linear transformation of the inputs.recurrent_kernel
weights matrix,
used for the linear transformation of the recurrent state.bias_initializer="zeros".
This is recommended in Jozefowicz et al.kernel weights matrix.recurrent_kernel weights matrix.kernel weights matrix.recurrent_kernel weights matrix.Gated recurrent units are a gating mechanism in recurrent neural networks.
Much similar to the LSTMs, they have fewer parameters than LSTM, as they lack an output gate.
keras.layers.recurrent.GRU(units, activation='tanh', recurrent_activation='hard_sigmoid', use_bias=True,
kernel_initializer='glorot_uniform', recurrent_initializer='orthogonal',
bias_initializer='zeros', kernel_regularizer=None, recurrent_regularizer=None,
bias_regularizer=None, activity_regularizer=None, kernel_constraint=None,
recurrent_constraint=None, bias_constraint=None,
dropout=0.0, recurrent_dropout=0.0)
In [ ]:
print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
# !!! Play with those! try and get better results!
#model.add(SimpleRNN(128))
#model.add(GRU(128))
#model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adam')
print("Train...")
model.fit(X_train, y_train, batch_size=batch_size,
epochs=4, validation_data=(X_test, y_test))
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size)
print('Test score:', score)
print('Test accuracy:', acc)
Generate movies with 3 to 7 moving squares inside.
The squares are of shape $1 \times 1$ or $2 \times 2$ pixels, which move linearly over time.
For convenience we first create movies with bigger width and height (80x80)
and at the end we select a $40 \times 40$ window.
In [1]:
# Artificial Data Generation
def generate_movies(n_samples=1200, n_frames=15):
row = 80
col = 80
noisy_movies = np.zeros((n_samples, n_frames, row, col, 1), dtype=np.float)
shifted_movies = np.zeros((n_samples, n_frames, row, col, 1),
dtype=np.float)
for i in range(n_samples):
# Add 3 to 7 moving squares
n = np.random.randint(3, 8)
for j in range(n):
# Initial position
xstart = np.random.randint(20, 60)
ystart = np.random.randint(20, 60)
# Direction of motion
directionx = np.random.randint(0, 3) - 1
directiony = np.random.randint(0, 3) - 1
# Size of the square
w = np.random.randint(2, 4)
for t in range(n_frames):
x_shift = xstart + directionx * t
y_shift = ystart + directiony * t
noisy_movies[i, t, x_shift - w: x_shift + w,
y_shift - w: y_shift + w, 0] += 1
# Make it more robust by adding noise.
# The idea is that if during inference,
# the value of the pixel is not exactly one,
# we need to train the network to be robust and still
# consider it as a pixel belonging to a square.
if np.random.randint(0, 2):
noise_f = (-1)**np.random.randint(0, 2)
noisy_movies[i, t,
x_shift - w - 1: x_shift + w + 1,
y_shift - w - 1: y_shift + w + 1,
0] += noise_f * 0.1
# Shift the ground truth by 1
x_shift = xstart + directionx * (t + 1)
y_shift = ystart + directiony * (t + 1)
shifted_movies[i, t, x_shift - w: x_shift + w,
y_shift - w: y_shift + w, 0] += 1
# Cut to a 40x40 window
noisy_movies = noisy_movies[::, ::, 20:60, 20:60, ::]
shifted_movies = shifted_movies[::, ::, 20:60, 20:60, ::]
noisy_movies[noisy_movies >= 1] = 1
shifted_movies[shifted_movies >= 1] = 1
return noisy_movies, shifted_movies
In [2]:
from keras.models import Sequential
from keras.layers.convolutional import Conv3D
from keras.layers.convolutional_recurrent import ConvLSTM2D
from keras.layers.normalization import BatchNormalization
import numpy as np
from matplotlib import pyplot as plt
%matplotlib inline
We create a layer which take as input movies of shape (n_frames, width, height, channels) and returns a movie
of identical shape.
In [3]:
seq = Sequential()
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
input_shape=(None, 40, 40, 1),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(Conv3D(filters=1, kernel_size=(3, 3, 3),
activation='sigmoid',
padding='same', data_format='channels_last'))
seq.compile(loss='binary_crossentropy', optimizer='adadelta')
In [4]:
# Train the network
noisy_movies, shifted_movies = generate_movies(n_samples=1200)
seq.fit(noisy_movies[:1000], shifted_movies[:1000], batch_size=10,
epochs=20, validation_split=0.05)
In [5]:
# Testing the network on one movie
# feed it with the first 7 positions and then
# predict the new positions
which = 1004
track = noisy_movies[which][:7, ::, ::, ::]
for j in range(16):
new_pos = seq.predict(track[np.newaxis, ::, ::, ::, ::])
new = new_pos[::, -1, ::, ::, ::]
track = np.concatenate((track, new), axis=0)
In [6]:
# And then compare the predictions
# to the ground truth
track2 = noisy_movies[which][::, ::, ::, ::]
for i in range(15):
fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(121)
if i >= 7:
ax.text(1, 3, 'Predictions !', fontsize=20, color='w')
else:
ax.text(1, 3, 'Inital trajectory', fontsize=20)
toplot = track[i, ::, ::, 0]
plt.imshow(toplot)
ax = fig.add_subplot(122)
plt.text(1, 3, 'Ground truth', fontsize=20)
toplot = track2[i, ::, ::, 0]
if i >= 2:
toplot = shifted_movies[which][i - 1, ::, ::, 0]
plt.imshow(toplot)
plt.savefig('imgs/convlstm/%i_animate.png' % (i + 1))
In [ ]: