Python layers.Conv1D方法代码示例

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def create_model(time_window_size, metric):
        model = Sequential()

        model.add(Conv1D(filters=256, kernel_size=5, padding='same', activation='relu',
                         input_shape=(time_window_size, 1)))
        model.add(MaxPooling1D(pool_size=4))

        model.add(LSTM(64))

        model.add(Dense(units=time_window_size, activation='linear'))

        model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])

        # model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
        # model.compile(optimizer="sgd", loss="mse", metrics=[metric])

        print(model.summary())
        return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def CausalCNN(n_filters, lr, decay, loss, 
               seq_len, input_features, 
               strides_len, kernel_size,
               dilation_rates):

    inputs = Input(shape=(seq_len, input_features), name='input_layer')   
    x=inputs
    for dilation_rate in dilation_rates:
        x = Conv1D(filters=n_filters,
               kernel_size=kernel_size, 
               padding='causal',
               dilation_rate=dilation_rate,
               activation='linear')(x) 
        x = BatchNormalization()(x)
        x = Activation('relu')(x)

    #x = Dense(7, activation='relu', name='dense_layer')(x)
    outputs = Dense(3, activation='sigmoid', name='output_layer')(x)
    causalcnn = Model(inputs, outputs=[outputs])

    return causalcnn 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def create_model():
    inputs = Input(shape=(length,), dtype='int32', name='inputs')
    embedding_1 = Embedding(len(vocab), EMBED_DIM, input_length=length, mask_zero=True)(inputs)
    bilstm = Bidirectional(LSTM(EMBED_DIM // 2, return_sequences=True))(embedding_1)
    bilstm_dropout = Dropout(DROPOUT_RATE)(bilstm)
    embedding_2 = Embedding(len(vocab), EMBED_DIM, input_length=length)(inputs)
    con = Conv1D(filters=FILTERS, kernel_size=2 * HALF_WIN_SIZE + 1, padding='same')(embedding_2)
    con_d = Dropout(DROPOUT_RATE)(con)
    dense_con = TimeDistributed(Dense(DENSE_DIM))(con_d)
    rnn_cnn = concatenate([bilstm_dropout, dense_con], axis=2)
    dense = TimeDistributed(Dense(len(chunk_tags)))(rnn_cnn)
    crf = CRF(len(chunk_tags), sparse_target=True)
    crf_output = crf(dense)
    model = Model(input=[inputs], output=[crf_output])
    model.compile(loss=crf.loss_function, optimizer=Adam(), metrics=[crf.accuracy])
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def ann_model(input_shape):

    inp = Input(shape=input_shape, name='mfcc_in')
    model = inp

    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Flatten()(model)

    model = Dense(56)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)
    model = Dropout(0.2)(model)
    model = Dense(28)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)

    model = Dense(1)(model)
    model = Activation('sigmoid')(model)

    model = Model(inp, model)
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def DiscriminatorConv(V, E, filter_sizes, num_filters, dropout):
    '''
    Another Discriminator model, currently unused because keras don't support
    masking for Conv1D and it does huge influence on training.
    # Arguments:
        V: int, Vocabrary size
        E: int, Embedding size
        filter_sizes: list of int, list of each Conv1D filter sizes
        num_filters: list of int, list of each Conv1D num of filters
        dropout: float
    # Returns:
        discriminator: keras model
            input: word ids, shape = (B, T)
            output: probability of true data or not, shape = (B, 1)
    '''
    input = Input(shape=(None,), dtype='int32', name='Input')   # (B, T)
    out = Embedding(V, E, name='Embedding')(input)  # (B, T, E)
    out = VariousConv1D(out, filter_sizes, num_filters)
    out = Highway(out, num_layers=1)
    out = Dropout(dropout, name='Dropout')(out)
    out = Dense(1, activation='sigmoid', name='FC')(out)

    discriminator = Model(input, out)
    return discriminator 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def VariousConv1D(x, filter_sizes, num_filters, name_prefix=''):
    '''
    Layer wrapper function for various filter sizes Conv1Ds
    # Arguments:
        x: tensor, shape = (B, T, E)
        filter_sizes: list of int, list of each Conv1D filter sizes
        num_filters: list of int, list of each Conv1D num of filters
        name_prefix: str, layer name prefix
    # Returns:
        out: tensor, shape = (B, sum(num_filters))
    '''
    conv_outputs = []
    for filter_size, n_filter in zip(filter_sizes, num_filters):
        conv_name = '{}VariousConv1D/Conv1D/filter_size_{}'.format(name_prefix, filter_size)
        pooling_name = '{}VariousConv1D/MaxPooling/filter_size_{}'.format(name_prefix, filter_size)
        conv_out = Conv1D(n_filter, filter_size, name=conv_name)(x)   # (B, time_steps, n_filter)
        conv_out = GlobalMaxPooling1D(name=pooling_name)(conv_out) # (B, n_filter)
        conv_outputs.append(conv_out)
    concatenate_name = '{}VariousConv1D/Concatenate'.format(name_prefix)
    out = Concatenate(name=concatenate_name)(conv_outputs)
    return out 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def construct_model(classe_nums):
    model = Sequential()

    model.add(
        Conv1D(filters=256, kernel_size=3, strides=1, activation='relu', input_shape=(99, 40), name='block1_conv1'))
    model.add(MaxPool1D(pool_size=2, name='block1_pool1'))
    model.add(BatchNormalization(momentum=0.9, epsilon=1e-5, axis=1))

    model.add(Conv1D(filters=256, kernel_size=3, strides=1, activation='relu', name='block1_conv2'))
    model.add(MaxPool1D(pool_size=2, name='block1_pool2'))

    model.add(Flatten(name='block1_flat1'))
    model.add(Dropout(0.5, name='block1_drop1'))

    model.add(Dense(512, activation='relu', name='block2_dense2'))
    model.add(MaxoutDense(512, nb_feature=4, name="block2_maxout2"))
    model.add(Dropout(0.5, name='block2_drop2'))

    model.add(Dense(512, activation='relu', name='block2_dense3', kernel_regularizer=l2(1e-4)))
    model.add(MaxoutDense(512, nb_feature=4, name="block2_maxout3"))
    model.add(Dense(classe_nums, activation='softmax', name="predict"))

    # plot_model(model, to_file='model_struct.png', show_shapes=True, show_layer_names=False)

    model.summary() 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def shortcut_pool(inputs, output, filters=256, pool_type='max', shortcut=True):
    """
        ResNet(shortcut连接|skip连接|residual连接), 
        这里是用shortcut连接. 恒等映射, block+f(block)
        再加上 downsampling实现
        参考: https://github.com/zonetrooper32/VDCNN/blob/keras_version/vdcnn.py
    :param inputs: tensor
    :param output: tensor
    :param filters: int
    :param pool_type: str, 'max'、'k-max' or 'conv' or other
    :param shortcut: boolean
    :return: tensor
    """
    if shortcut:
        conv_2 = Conv1D(filters=filters, kernel_size=1, strides=2, padding='SAME')(inputs)
        conv_2 = BatchNormalization()(conv_2)
        output = downsampling(output, pool_type=pool_type)
        out = Add()([output, conv_2])
    else:
        out = ReLU(inputs)
        out = downsampling(out, pool_type=pool_type)
    if pool_type is not None: # filters翻倍
        out = Conv1D(filters=filters*2, kernel_size=1, strides=1, padding='SAME')(out)
        out = BatchNormalization()(out)
    return out 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def downsampling(inputs, pool_type='max'):
    """
        In addition, downsampling with stride 2 essentially doubles the effective coverage 
        (i.e., coverage in the original document) of the convolution kernel; 
        therefore, after going through downsampling L times, 
        associations among words within a distance in the order of 2L can be represented. 
        Thus, deep pyramid CNN is computationally efficient for representing long-range associations 
        and so more global information. 
        参考: https://github.com/zonetrooper32/VDCNN/blob/keras_version/vdcnn.py
    :param inputs: tensor,
    :param pool_type: str, select 'max', 'k-max' or 'conv'
    :return: tensor,
    """
    if pool_type == 'max':
        output = MaxPooling1D(pool_size=3, strides=2, padding='SAME')(inputs)
    elif pool_type == 'k-max':
        output = k_max_pooling(top_k=int(K.int_shape(inputs)[1]/2))(inputs)
    elif pool_type == 'conv':
        output = Conv1D(kernel_size=3, strides=2, padding='SAME')(inputs)
    else:
        output = MaxPooling1D(pool_size=3, strides=2, padding='SAME')(inputs)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def model_lstm(input_shape):
    
    inp = Input(shape=input_shape)
    model = inp
    
    if input_shape[0] > 2: model = Conv1D(filters=24, kernel_size=(3), activation='relu')(model)
#    if input_shape[0] > 0: model = TimeDistributed(Conv1D(filters=24, kernel_size=3, activation='relu'))(model)
    model = LSTM(16)(model)
    model = Activation('relu')(model)
    model = Dropout(0.2)(model)
    model = Dense(16)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)

    model = Dense(1)(model)
    model = Activation('sigmoid')(model)
    
    model = Model(inp, model)
    return model

# %% 
    
# Conv-1D architecture. Just one sample as input 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def cnn(maxlen, embed_size, recurrent_units, dropout_rate, recurrent_dropout_rate, dense_size, nb_classes):
    #inp = Input(shape=(maxlen, ))
    input_layer = Input(shape=(maxlen, embed_size), )
    #x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)
    x = Dropout(dropout_rate)(input_layer) 
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    x = MaxPooling1D(pool_size=2)(x)
    x = GRU(recurrent_units)(x)
    x = Dropout(dropout_rate)(x)
    x = Dense(dense_size, activation="relu")(x)
    x = Dense(nb_classes, activation="sigmoid")(x)
    model = Model(inputs=input_layer, outputs=x)
    model.summary()  
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def cnn2_best(maxlen, embed_size, recurrent_units, dropout_rate, recurrent_dropout_rate, dense_size, nb_classes):
    #inp = Input(shape=(maxlen, ))
    input_layer = Input(shape=(maxlen, embed_size), )
    #x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)
    x = Dropout(dropout_rate)(input_layer) 
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = GRU(recurrent_units, return_sequences=False, dropout=dropout_rate,
                           recurrent_dropout=dropout_rate)(x)
    #x = Dropout(dropout_rate)(x)
    x = Dense(dense_size, activation="relu")(x)
    x = Dense(nb_classes, activation="sigmoid")(x)
    model = Model(inputs=input_layer, outputs=x)
    model.summary()  
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def cnn2(maxlen, embed_size, recurrent_units, dropout_rate, recurrent_dropout_rate, dense_size, nb_classes):
    #inp = Input(shape=(maxlen, ))
    input_layer = Input(shape=(maxlen, embed_size), )
    #x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)
    x = Dropout(dropout_rate)(input_layer) 
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = Conv1D(filters=recurrent_units, kernel_size=2, padding='same', activation='relu')(x)
    #x = MaxPooling1D(pool_size=2)(x)
    x = GRU(recurrent_units, return_sequences=False, dropout=dropout_rate,
                           recurrent_dropout=dropout_rate)(x)
    #x = Dropout(dropout_rate)(x)
    x = Dense(dense_size, activation="relu")(x)
    x = Dense(nb_classes, activation="sigmoid")(x)
    model = Model(inputs=input_layer, outputs=x)
    model.summary()  
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def conv(maxlen, embed_size, recurrent_units, dropout_rate, recurrent_dropout_rate, dense_size, nb_classes):
    filter_kernels = [7, 7, 5, 5, 3, 3]
    #inp = Input(shape=(maxlen, ))
    input_layer = Input(shape=(maxlen, embed_size), )
    #x = Embedding(max_features, embed_size, weights=[embedding_matrix], trainable=False)(inp)
    conv = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[0], border_mode='valid', activation='relu')(input_layer)
    conv = MaxPooling1D(pool_length=3)(conv)
    conv1 = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[1], border_mode='valid', activation='relu')(conv)
    conv1 = MaxPooling1D(pool_length=3)(conv1)
    conv2 = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[2], border_mode='valid', activation='relu')(conv1)
    conv3 = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[3], border_mode='valid', activation='relu')(conv2)
    conv4 = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[4], border_mode='valid', activation='relu')(conv3)
    conv5 = Conv1D(nb_filter=recurrent_units, filter_length=filter_kernels[5], border_mode='valid', activation='relu')(conv4)
    conv5 = MaxPooling1D(pool_length=3)(conv5)
    conv5 = Flatten()(conv5)
    z = Dropout(0.5)(Dense(dense_size, activation='relu')(conv5))
    #x = GlobalMaxPool1D()(x)
    x = Dense(nb_classes, activation="sigmoid")(z)
    model = Model(inputs=input_layer, outputs=x)
    model.summary()  
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model


# LSTM + conv 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import Conv1D [as 别名]
def build_model_text_cnn(self):
        #########    text-cnn    #########
        # bert embedding
        bert_inputs, bert_output = KerasBertEmbedding().bert_encode()
        # text cnn
        bert_output_emmbed = SpatialDropout1D(rate=self.keep_prob)(bert_output)
        concat_out = []
        for index, filter_size in enumerate(self.filters):
            x = Conv1D(name='TextCNN_Conv1D_{}'.format(index), filters=int(self.embedding_dim/2), kernel_size=self.filters[index], padding='valid', kernel_initializer='normal', activation='relu')(bert_output_emmbed)
            x = GlobalMaxPooling1D(name='TextCNN_MaxPool1D_{}'.format(index))(x)
            concat_out.append(x)
        x = Concatenate(axis=1)(concat_out)
        x = Dropout(self.keep_prob)(x)

        # 最后就是softmax
        dense_layer = Dense(self.label, activation=self.activation)(x)
        output_layers = [dense_layer]
        self.model = Model(bert_inputs, output_layers)