In [0]:
# Based on
# https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/6.2-understanding-recurrent-neural-networks.ipynb
In [0]:
import warnings
warnings.filterwarnings('ignore')
In [2]:
%matplotlib inline
%pylab inline
In [4]:
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.ERROR)
print(tf.__version__)
In [5]:
# let's see what compute devices we have available, hopefully a GPU
sess = tf.Session()
devices = sess.list_devices()
for d in devices:
print(d.name)
In [6]:
# a small sanity check, does tf seem to work ok?
hello = tf.constant('Hello TF!')
print(sess.run(hello))
In [7]:
from tensorflow import keras
print(keras.__version__)
In [0]:
# https://keras.io/datasets/#imdb-movie-reviews-sentiment-classification
max_features = 10000 # number of words to consider as features
maxlen = 500 # cut texts after this number of words (among top max_features most common words)
# each review is encoded as a sequence of word indexes
# indexed by overall frequency in the dataset
# output is 0 (negative) or 1 (positive)
imdb = tf.keras.datasets.imdb.load_data(num_words=max_features)
(raw_input_train, y_train), (raw_input_test, y_test) = imdb
In [0]:
# https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/sequence/pad_sequences
input_train = tf.keras.preprocessing.sequence.pad_sequences(raw_input_train, maxlen=maxlen)
input_test = tf.keras.preprocessing.sequence.pad_sequences(raw_input_test, maxlen=maxlen)
In [10]:
input_train.shape, input_test.shape, y_train.shape, y_test.shape
Out[10]:
In [11]:
embedding_dim = 32
dropout = 0.15
recurrent_dropout = 0.2
model = tf.keras.Sequential()
model.add(tf.keras.layers.Embedding(name='embedding', input_dim=max_features, output_dim=embedding_dim, input_length=maxlen))
model.add(tf.keras.layers.LSTM(name='lstm', units=32))
# binary classifier
model.add(tf.keras.layers.Dense(name='fc', units=32, activation='relu'))
model.add(tf.keras.layers.Dense(name='classifier', units=1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.summary()
In [12]:
batch_size = 1000
%time history = model.fit(input_train, y_train, epochs=10, batch_size=batch_size, validation_split=0.2)
In [13]:
train_loss, train_accuracy = model.evaluate(input_train, y_train, batch_size=batch_size)
train_accuracy
Out[13]:
In [14]:
test_loss, test_accuracy = model.evaluate(input_test, y_test, batch_size=batch_size)
test_accuracy
Out[14]:
In [15]:
# precition
model.predict(input_test[0:5])
Out[15]:
In [16]:
# ground truth
y_test[0:5]
Out[16]:
In [0]: