Python tensorflow.python.keras.layers.LSTM Examples

The following are 5 code examples of tensorflow.python.keras.layers.LSTM(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.keras.layers , or try the search function .
Example #1
Source Project: seglearn   Author: dmbee   File: plot_segment_rep.py    License: BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def crnn_model(width=100, n_vars=6, n_classes=7, conv_kernel_size=5,
               conv_filters=3, lstm_units=3):
    input_shape = (width, n_vars)
    model = Sequential()
    model.add(Conv1D(filters=conv_filters, kernel_size=conv_kernel_size,
                     padding='valid', activation='relu', input_shape=input_shape))
    model.add(Conv1D(filters=conv_filters, kernel_size=conv_kernel_size,
                     padding='valid', activation='relu'))
    model.add(LSTM(units=lstm_units, dropout=0.1, recurrent_dropout=0.1))
    model.add(Dense(n_classes, activation="softmax"))

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

    return model


# load the data 
Example #2
Source Project: seglearn   Author: dmbee   File: plot_model_selection2.py    License: BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def crnn_model(width=100, n_vars=6, n_classes=7, conv_kernel_size=5,
               conv_filters=2, lstm_units=2):
    # create a crnn model with keras with one cnn layers, and one rnn layer
    input_shape = (width, n_vars)
    model = Sequential()
    model.add(Conv1D(filters=conv_filters, kernel_size=conv_kernel_size,
                     padding='valid', activation='relu', input_shape=input_shape))
    model.add(LSTM(units=lstm_units, dropout=0.1, recurrent_dropout=0.1))
    model.add(Dense(n_classes, activation="softmax"))

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

    return model


# load the data 
Example #3
Source Project: seglearn   Author: dmbee   File: plot_nn_training_curves.py    License: BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up
def crnn_model(width=100, n_vars=6, n_classes=7, conv_kernel_size=5,
               conv_filters=3, lstm_units=3):
    input_shape = (width, n_vars)
    model = Sequential()
    model.add(Conv1D(filters=conv_filters, kernel_size=conv_kernel_size,
                     padding='valid', activation='relu', input_shape=input_shape))
    model.add(LSTM(units=lstm_units, dropout=0.1, recurrent_dropout=0.1))
    model.add(Dense(n_classes, activation="softmax"))

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

    return model


##############################################
# Setup
##############################################

# load the data 
Example #4
Source Project: DeepCTR   Author: shenweichen   File: sequence.py    License: Apache License 2.0 6 votes vote down vote up
def build(self, input_shape):

        if len(input_shape) != 3:
            raise ValueError(
                "Unexpected inputs dimensions %d, expect to be 3 dimensions" % (len(input_shape)))
        self.fw_lstm = []
        self.bw_lstm = []
        for _ in range(self.layers):
            self.fw_lstm.append(
                LSTM(self.units, dropout=self.dropout_rate, bias_initializer='ones', return_sequences=True,
                     unroll=True))
            self.bw_lstm.append(
                LSTM(self.units, dropout=self.dropout_rate, bias_initializer='ones', return_sequences=True,
                     go_backwards=True, unroll=True))

        super(BiLSTM, self).build(
            input_shape)  # Be sure to call this somewhere! 
Example #5
Source Project: icme2019   Author: ShenDezhou   File: sequence.py    License: MIT License 5 votes vote down vote up
def build(self, input_shape):

        if len(input_shape) != 3:
            raise ValueError(
                "Unexpected inputs dimensions %d, expect to be 3 dimensions" % (len(input_shape)))
        self.fw_lstm = []
        self.bw_lstm = []
        for _ in range(self.layers):
            self.fw_lstm.append(LSTM(self.units, dropout=self.dropout, bias_initializer='ones', return_sequences=True,
                                     unroll=True))
            self.bw_lstm.append(LSTM(self.units, dropout=self.dropout, bias_initializer='ones', return_sequences=True,
                                     go_backwards=True, unroll=True))

        super(BiLSTM, self).build(
            input_shape)  # Be sure to call this somewhere!