Classification with LSTM

    import numpy as np

    from keras.preprocessing import sequence
    from keras.models import Sequential
    from keras.layers import Dense, Dropout, Activation
    from keras.layers import Embedding
    from keras.layers import LSTM
    from keras.callbacks import EarlyStopping

    from keras.datasets import imdb

    n_words = 1000
    (X_train, y_train), (X_test, y_test) = imdb.load_data(num_words=n_words)
    print('Train seq: {}'.format(len(X_train)))
    print('Test seq: {}'.format(len(X_train)))

    print('Train example: \n{}'.format(X_train[0]))
    print('\nTest example: \n{}'.format(X_test[0]))

    # Note: the data is already preprocessed (words are mapped to vectors)

    # Pad sequences with max_len
    max_len = 200
    X_train = sequence.pad_sequences(X_train, maxlen=max_len)
    X_test = sequence.pad_sequences(X_test, maxlen=max_len)

    # Define network architecture and compile
    model = Sequential()
    model.add(Embedding(n_words, 50, input_length=max_len))
    model.add(Dropout(0.2))
    model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
    model.add(Dense(250, activation='relu'))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))

    model.compile(loss='binary_crossentropy',  optimizer='adam', metrics=['accuracy'])
    model.summary()

    callbacks = [EarlyStopping(monitor='val_acc', patience=3)]

    batch_size = 128
    n_epochs = 100

    model.fit(X_train, y_train, batch_size=batch_size, epochs=n_epochs, validation_split=0.2, callbacks=callbacks)

    print('Accuracy on test set: {}'.format(model.evaluate(X_test, y_test)[1]))

    # Accuracy on test set: 0.82884

Using TensorFlow backend.


Train seq: 25000
Test seq: 25000
Train example: 
[1, 14, 22, 16, 43, 530, 973, 2, 2, 65, 458, 2, 66, 2, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 2, 2, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2, 19, 14, 22, 4, 2, 2, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 2, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2, 2, 16, 480, 66, 2, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 2, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 2, 15, 256, 4, 2, 7, 2, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 2, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2, 56, 26, 141, 6, 194, 2, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 2, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 2, 88, 12, 16, 283, 5, 16, 2, 113, 103, 32, 15, 16, 2, 19, 178, 32]

Test example: 
[1, 591, 202, 14, 31, 6, 717, 10, 10, 2, 2, 5, 4, 360, 7, 4, 177, 2, 394, 354, 4, 123, 9, 2, 2, 2, 10, 10, 13, 92, 124, 89, 488, 2, 100, 28, 2, 14, 31, 23, 27, 2, 29, 220, 468, 8, 124, 14, 286, 170, 8, 157, 46, 5, 27, 239, 16, 179, 2, 38, 32, 25, 2, 451, 202, 14, 6, 717]
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding_1 (Embedding)      (None, 200, 50)           50000     
_________________________________________________________________
dropout_1 (Dropout)          (None, 200, 50)           0         
_________________________________________________________________
lstm_1 (LSTM)                (None, 100)               60400     
_________________________________________________________________
dense_1 (Dense)              (None, 250)               25250     
_________________________________________________________________
dropout_2 (Dropout)          (None, 250)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 251       
=================================================================
Total params: 135,901
Trainable params: 135,901
Non-trainable params: 0
_________________________________________________________________
Train on 20000 samples, validate on 5000 samples
Epoch 1/100
20000/20000 [==============================] - 49s 2ms/step - loss: 0.5634 - acc: 0.6982 - val_loss: 0.4351 - val_acc: 0.8004
Epoch 2/100
20000/20000 [==============================] - 48s 2ms/step - loss: 0.4342 - acc: 0.8023 - val_loss: 0.3923 - val_acc: 0.8278
Epoch 3/100
 4736/20000 [======>.......................] - ETA: 34s - loss: 0.4127 - acc: 0.8254


---------------------------------------------------------------------------