pytcn 0.0.2

Temporal Convolution Network (TCN) based on Keras

Temporal Convolution Network (TCN)

Description

This is a implement of temporal Convolution Network (TCN) by using keras, and the version uses a dense layer as the output layer instead of fully convolution network (FCN) structure depicted in paper "An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling".

Usage

    import keras 
    from tcn import *

    # Build TCN model
    # model is a keras model
    model = tcn(input_shape=(24, 7), n_blocks=3, filters=[16, 32, 64], 
                kernel_size=[24, 24, 24], dropout_rate=[0.1, 0.1, 0.1], 
                n_outputs=6)
    # Plot the structure of model
    keras.utils.plot_model(model, to_file='model.png', show_shapes=True)

References

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling