Python layers.GlobalMaxPooling1D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 GlobalMaxPooling1D [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 GlobalMaxPooling1D [as 别名]
def create_model(self, hyper_parameters):
        """
            构建神经网络
        :param hyper_parameters:json,  hyper parameters of network
        :return: tensor, moedl
        """
        super().create_model(hyper_parameters)
        x = self.word_embedding.output
        x = SpatialDropout1D(self.dropout_spatial)(x)
        x = AttentionSelf(self.word_embedding.embed_size)(x)
        x = GlobalMaxPooling1D()(x)
        x = Dropout(self.dropout)(x)
        # x = Flatten()(x)
        # 最后就是softmax
        dense_layer = Dense(self.label, activation=self.activate_classify)(x)
        output = [dense_layer]
        self.model = Model(self.word_embedding.input, output)
        self.model.summary(120) 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [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) 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def build_cnn(input_shape, output_dim,nb_filter):
    clf = Sequential()
    clf.add(Convolution1D(nb_filter=nb_filter,
                          filter_length=4,border_mode="valid",activation="relu",subsample_length=1,input_shape=input_shape))
    clf.add(GlobalMaxPooling1D())
    clf.add(Dense(100))
    clf.add(Dropout(0.2))
    clf.add(Activation("tanh"))
    clf.add(Dense(output_dim=output_dim, activation='softmax'))

    clf.compile(optimizer='adagrad',
                     loss='categorical_crossentropy',
                     metrics=['accuracy'])
    return clf

# just one filter 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def build_cnn_char(input_dim, output_dim,nb_filter):
    clf = Sequential()
    clf.add(Embedding(input_dim,
                      32, # character embedding size
                      input_length=maxlen,
                      dropout=0.2))
    clf.add(Convolution1D(nb_filter=nb_filter,
                          filter_length=3,border_mode="valid",activation="relu",subsample_length=1))
    clf.add(GlobalMaxPooling1D())
    clf.add(Dense(100))
    clf.add(Dropout(0.2))
    clf.add(Activation("tanh"))
    clf.add(Dense(output_dim=output_dim, activation='softmax'))

    clf.compile(optimizer='adagrad',
                     loss='categorical_crossentropy',
                     metrics=['accuracy'])
    return clf

# just one filter 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def ConvolutionLayer(input_shape, n_classes, filter_sizes=[2, 3, 4, 5], num_filters=20, word_trainable=False, vocab_sz=None,
                     embedding_matrix=None, word_embedding_dim=100, hidden_dim=20, act='relu', init='ones'):
    x = Input(shape=(input_shape,), name='input')
    z = Embedding(vocab_sz, word_embedding_dim, input_length=(input_shape,), name="embedding", 
                    weights=[embedding_matrix], trainable=word_trainable)(x)
    conv_blocks = []
    for sz in filter_sizes:
        conv = Convolution1D(filters=num_filters,
                             kernel_size=sz,
                             padding="valid",
                             activation=act,
                             strides=1,
                             kernel_initializer=init)(z)
        conv = GlobalMaxPooling1D()(conv)
        conv_blocks.append(conv)
    z = Concatenate()(conv_blocks) if len(conv_blocks) > 1 else conv_blocks[0]
    z = Dense(hidden_dim, activation="relu")(z)
    y = Dense(n_classes, activation="softmax")(z)
    return Model(inputs=x, outputs=y, name='classifier') 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_umtmum_embedding(umtmum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umtmum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'umtmum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umtmum_input)
    output = conv_umtmum(path_input)
    output = GlobalMaxPooling1D()(output)
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umtmum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umtmum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])

    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'umtmum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_umtm_embedding(umtm_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umtm = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'umtm_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umtm_input)
    output = GlobalMaxPooling1D()(conv_umtm(path_input))
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umtm_input)
        tmp_output = GlobalMaxPooling1D()(conv_umtm(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])

    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'umtm')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_umum_embedding(umum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'umum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umum_input)
    output = GlobalMaxPooling1D()(conv_umum(path_input))
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])


    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'umum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_uuum_embedding(umum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'uuum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umum_input)
    output = GlobalMaxPooling1D()(conv_umum(path_input))
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])


    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'uuum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_umtmum_embedding(umtmum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umtmum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'umtmum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umtmum_input)
    output = conv_umtmum(path_input)
    output = GlobalMaxPooling1D()(output)
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umtmum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umtmum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])
    
    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'umtmum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_umum_embedding(umum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'umum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umum_input)
    output = GlobalMaxPooling1D()(conv_umum(path_input))
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])
    
    
    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'umum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def get_uuum_embedding(umum_input, path_num, timestamps, length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2):
    conv_umum = Conv1D(filters = 128,
                       kernel_size = 4,
                       activation = 'relu',
                       kernel_regularizer = l2(0.0),
                       kernel_initializer = 'glorot_uniform',
                       padding = 'valid',
                       strides = 1,
                       name = 'uuum_conv')

    path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':0})(umum_input)
    output = GlobalMaxPooling1D()(conv_umum(path_input))
    output = Dropout(0.5)(output)

    for i in range(1, path_num):
        path_input = Lambda(slice, output_shape=(timestamps, length), arguments={'index':i})(umum_input)
        tmp_output = GlobalMaxPooling1D()(conv_umum(path_input))
        tmp_output = Dropout(0.5)(tmp_output)
        output = concatenate([output, tmp_output])
    
    
    output = Reshape((path_num, 128))(output)
    #output = path_attention(user_latent, item_latent, output, 128, 64, path_attention_layer_1, path_attention_layer_2, 'uuum')
    output = GlobalMaxPooling1D()(output)
    return output 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def ConvolutionLayer(x, input_shape, n_classes, filter_sizes=[2, 3, 4, 5], num_filters=20, word_trainable=False,
                     vocab_sz=None,
                     embedding_matrix=None, word_embedding_dim=100, hidden_dim=100, act='relu', init='ones'):
    if embedding_matrix is not None:
        z = Embedding(vocab_sz, word_embedding_dim, input_length=(input_shape,),
                      weights=[embedding_matrix], trainable=word_trainable)(x)
    else:
        z = Embedding(vocab_sz, word_embedding_dim, input_length=(input_shape,), trainable=word_trainable)(x)
    conv_blocks = []
    for sz in filter_sizes:
        conv = Convolution1D(filters=num_filters,
                             kernel_size=sz,
                             padding="valid",
                             activation=act,
                             strides=1,
                             kernel_initializer=init)(z)
        conv = GlobalMaxPooling1D()(conv)
        conv_blocks.append(conv)
    z = Concatenate()(conv_blocks) if len(conv_blocks) > 1 else conv_blocks[0]
    z = Dense(hidden_dim, activation="relu")(z)
    y = Dense(n_classes, activation="softmax")(z)
    return Model(inputs=x, outputs=y) 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import GlobalMaxPooling1D [as 别名]
def build_model(vocab_size, embedding_dim, sequence_length, embedding_matrix):

    sequence_input = Input(shape=(sequence_length,), dtype='int32')
    embedding_layer = Embedding(input_dim=vocab_size,
                                output_dim=embedding_dim,
                                weights=[embedding_matrix],
                                input_length=sequence_length,
                                trainable=False,
                                name="embedding")(sequence_input)
    x = Conv1D(128, 5, activation='relu')(embedding_layer)
    x = MaxPooling1D(5)(x)
    x = Conv1D(128, 5, activation='relu')(x)
    x = MaxPooling1D(5)(x)
    x = Conv1D(128, 5, activation='relu')(x)
    x = GlobalMaxPooling1D()(x)
    x = Dense(128, activation='relu')(x)
    preds = Dense(20, activation='softmax')(x)

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