Python keras.layers.recurrent.SimpleRNN() Examples

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def create_rnn():
    """Create a recurrent neural network to compute a control policy.

    Reference:
    Koutnik, Jan, Jurgen Schmidhuber, and Faustino Gomez. "Evolving deep
    unsupervised convolutional networks for vision-based reinforcement
    learning." Proceedings of the 2014 conference on Genetic and
    evolutionary computation. ACM, 2014.
    """
    model = Sequential()

    model.add(SimpleRNN(output_dim=3, stateful=True, batch_input_shape=(1, 1, 3)))
    model.add(Dense(input_dim=3, output_dim=3))

    model.compile(loss='mse', optimizer='rmsprop')

    return model 

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def test_masking_layer():
    ''' This test based on a previously failing issue here:
    https://github.com/keras-team/keras/issues/1567
    '''
    inputs = np.random.random((6, 3, 4))
    targets = np.abs(np.random.random((6, 3, 5)))
    targets /= targets.sum(axis=-1, keepdims=True)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=False))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1)

    model = Sequential()
    model.add(Masking(input_shape=(3, 4)))
    model.add(recurrent.SimpleRNN(units=5, return_sequences=True, unroll=True))
    model.compile(loss='categorical_crossentropy', optimizer='adam')
    model.fit(inputs, targets, epochs=1, batch_size=100, verbose=1) 

def construct_model(maxlen, input_dimension, output_dimension, lstm_vector_output_dim):
    """
    Склеены три слова
    """
    input = Input(shape=(maxlen, input_dimension), name='input')


    # lstm_encode = LSTM(lstm_vector_output_dim)(input)
    lstm_encode = SimpleRNN(lstm_vector_output_dim, activation='relu')(input)


    encoded_copied = RepeatVector(n=maxlen)(lstm_encode)


    # lstm_decode = LSTM(output_dim=output_dimension, return_sequences=True, activation='softmax')(encoded_copied)
    lstm_decode = SimpleRNN(output_dim=output_dimension, return_sequences=True, activation='softmax')(encoded_copied)


    encoder = Model(input, lstm_decode)


    adam = Adam()
    encoder.compile(loss='categorical_crossentropy', optimizer=adam)


    return encoder 

def test_simple(self):
        _runner(recurrent.SimpleRNN) 

def construct_model(maxlen, input_dimension, output_dimension, lstm_vector_output_dim):
    """
        Склеены три слова
    """
    input = Input(shape=(maxlen, input_dimension), name='input')


    # lstm_encode = LSTM(lstm_vector_output_dim)(input)
    lstm_encode = SimpleRNN(lstm_vector_output_dim, activation='sigmoid')(input)


    encoded_copied = RepeatVector(n=maxlen)(lstm_encode)


    # lstm_decode = LSTM(output_dim=output_dimension, return_sequences=True, activation='softmax')(encoded_copied)
    lstm_decode = SimpleRNN(output_dim=output_dimension, return_sequences=True, activation='softmax')(encoded_copied)


    decoded = TimeDistributed(Dense(output_dimension, activation='softmax'))(lstm_decode)


    encoder_decoder = Model(input, decoded)


    adam = Adam()
    encoder_decoder.compile(loss='categorical_crossentropy', optimizer=adam)


    return encoder_decoder 

def build(self, input_shape):
        self.input_spec = [InputSpec(shape=input_shape)]
        if self.stateful:
            self.reset_states()
        else:
            # initial states: all-zero tensor of shape (output_dim)
            self.states = [None]
        input_dim = input_shape[2]
        self.input_dim = input_dim

        self.W = self.init((input_dim, self.output_dim),
                           name='{}_W'.format(self.name))
        # Only change in build compared to SimpleRNN:
        # U is of shape (inner_input_dim, output_dim) now.
        self.U = self.inner_init((self.inner_input_dim, self.output_dim),
                                 name='{}_U'.format(self.name))
        self.b = K.zeros((self.output_dim,), name='{}_b'.format(self.name))

        self.regularizers = []
        if self.W_regularizer:
            self.W_regularizer.set_param(self.W)
            self.regularizers.append(self.W_regularizer)
        if self.U_regularizer:
            self.U_regularizer.set_param(self.U)
            self.regularizers.append(self.U_regularizer)
        if self.b_regularizer:
            self.b_regularizer.set_param(self.b)
            self.regularizers.append(self.b_regularizer)

        self.trainable_weights = [self.W, self.U, self.b]

        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f) 

def rnn_test(f):
    """
    All the recurrent layers share the same interface,
    so we can run through them with a single function.
    """
    f = keras_test(f)
    return pytest.mark.parametrize('layer_class', [
        recurrent.SimpleRNN,
        recurrent.GRU,
        recurrent.LSTM
    ])(f)