from keras.layers import (Dense, Dropout, Embedding, GlobalAveragePooling1D,
                          Input, Bidirectional, Activation, Reshape)
from keras.layers.merge import concatenate
from keras.layers.recurrent import LSTM
from keras.models import Model, Sequential
from keras.optimizers import SGD
from keras.regularizers import l1_l2
from keras.utils import plot_model

max_features = 20000
maxlen = 30
embedding_dims = 50

visible = Input(shape=(30,), name="Input")
embedding = Embedding(max_features+1,
                      embedding_dims,
                      input_length=maxlen,
                      name="Embedding")(visible)

embedding = Dropout(rate=0.5)(embedding)

transformed = Reshape((-1,))(embedding)
representation = Dense(50, name="Representation")(transformed)
representation = Dropout(rate=0.5)(representation)
output = Dense(n_labels, activation='softmax', name="Output")(representation)
model = Model(inputs=visible, outputs=output)

sgd = SGD(lr=0.01, momentum=0.8, decay=0.0, nesterov=False)
model.compile(loss='categorical_crossentropy',
              optimizer=sgd,
              metrics=['accuracy'])

max_features = 20000
    maxlen = 30
    embedding_dims = 50

    model = Sequential()
    # we start off with an efficient embedding layer which maps
    # our vocab indices into embedding_dims dimensions
    model.add(Embedding(max_features+1,
                        embedding_dims,
                        input_length=maxlen))

    model.add(Dropout(rate=0.5))
    # we add a GlobalAveragePooling1D, which will average the embeddings
    # of all words in the document
    model.add(GlobalAveragePooling1D())
    model.add(Dropout(rate=0.5))

    # We project onto a single unit output layer, and squash it with a sigmoid:
    model.add(Dense(n_labels, activation='softmax'))

    sgd = SGD(lr=0.01, momentum=0.8, decay=0.0, nesterov=False)

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