当前位置: 首页>>代码示例>>Python>>正文


Python recurrent.SimpleRNN方法代码示例

本文整理汇总了Python中keras.layers.recurrent.SimpleRNN方法的典型用法代码示例。如果您正苦于以下问题:Python recurrent.SimpleRNN方法的具体用法?Python recurrent.SimpleRNN怎么用?Python recurrent.SimpleRNN使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在keras.layers.recurrent的用法示例。


在下文中一共展示了recurrent.SimpleRNN方法的7个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: test_masking_layer

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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) 
开发者ID:hello-sea,项目名称:DeepLearning_Wavelet-LSTM,代码行数:21,代码来源:recurrent_test.py

示例2: create_rnn

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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 
开发者ID:cosmoharrigan,项目名称:neuroevolution,代码行数:19,代码来源:rnn.py

示例3: test_simple

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
def test_simple(self):
        _runner(recurrent.SimpleRNN) 
开发者ID:lllcho,项目名称:CAPTCHA-breaking,代码行数:4,代码来源:test_recurrent.py

示例4: rnn_test

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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) 
开发者ID:hello-sea,项目名称:DeepLearning_Wavelet-LSTM,代码行数:13,代码来源:recurrent_test.py

示例5: build

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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 
开发者ID:maxpumperla,项目名称:neuralforecast,代码行数:36,代码来源:recurrent.py

示例6: construct_model

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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 
开发者ID:kootenpv,项目名称:neural_complete,代码行数:31,代码来源:model.py

示例7: construct_model

# 需要导入模块: from keras.layers import recurrent [as 别名]
# 或者: from keras.layers.recurrent import SimpleRNN [as 别名]
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 
开发者ID:kootenpv,项目名称:neural_complete,代码行数:28,代码来源:model_all_stacked.py


注:本文中的keras.layers.recurrent.SimpleRNN方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。