nn_models.py 文件源码

def get_model(self, num_features):

        embedding_dims = 128
        nb_filter = 250
        filter_length = 8

        drop = 0.2

        model = Sequential()

        # we start off with an efficient embedding layer which maps
        # our vocab indices into embedding_dims dimensions
        model.add(Embedding(self.vocab_size,
                            embedding_dims,
                            input_length=num_features[0],
                            dropout=0.2))

        # we add a Convolution1D, which will learn nb_filter
        # word group filters of size filter_length:
        model.add(Convolution1D(nb_filter=nb_filter,
                                filter_length=filter_length,
                                border_mode='valid',
                                activation='relu',
                                subsample_length=1))

        # we use max over time pooling by defining a python function to use
        # in a Lambda layer
        def max_1d(X):
            return K.max(X, axis=1)

        model.add(Lambda(max_1d, output_shape=(nb_filter,)))

        model.add(Dropout(drop))
        model.add(Dense(1024, init='glorot_uniform'))
        model.add(BatchNormalization())
        model.add(Activation('relu'))

        model.add(Dropout(drop))
        model.add(Dense(1024, init='glorot_uniform'))
        model.add(BatchNormalization())
        model.add(Activation('relu'))

        # We project onto a single unit output layer, and squash it with a sigmoid:
        model.add(Dense(1))
        model.add(Activation('sigmoid'))

        return model