/keras-tcn

Keras Temporal Convolutional Network.

Primary LanguagePython

Keras TCN

Keras Temporal Convolutional Network

Why Temporal Convolutional Network?

  • TCNs exhibit longer memory than recurrent architectures with the same capacity.
  • Constantly performs better than LSTM/GRU architectures on a vast range of tasks (Seq. MNIST, Adding Problem, Copy Memory, Word-level PTB...).
  • Parallelism, flexible receptive field size, stable gradients, low memory requirements for training, variable length inputs...

Visualization of a stack of dilated causal convolutional layers (Wavenet, 2016)

API

After installation, the model can be imported like this:

from tcn import tcn

In the following examples, we assume the input to have a shape (batch_size, timesteps, input_dim).

The model is a Keras model. The model functions (model.summary, model.fit, model.predict...) are all functional.

- Regression (Many to one) e.g. adding problem

model = tcn.dilated_tcn(output_slice_index='last',
                        num_feat=input_dim,
                        nb_filters=24,
                        kernel_size=8,
                        dilatations=[1, 2, 4, 8],
                        nb_stacks=8,
                        max_len=timesteps,
                        activation='norm_relu',
                        regression=True)

- Classification (Many to many) e.g. copy memory task

model = tcn.dilated_tcn(num_feat=input_dim,
                        num_classes=10,
                        nb_filters=10,
                        kernel_size=8,
                        dilatations=[1, 2, 4, 8],
                        nb_stacks=8,
                        max_len=timesteps,
                        activation='norm_relu')

- Classification (Many to one) e.g. sequential mnist task

model = tcn.dilated_tcn(output_slice_index='last',
                        num_feat=input_dim,
                        num_classes=10,
                        nb_filters=64,
                        kernel_size=8,
                        dilatations=[1, 2, 4, 8],
                        nb_stacks=8,
                        max_len=timesteps,
                        activation='norm_relu')

Installation

git clone git@github.com:philipperemy/keras-tcn.git
cd keras-tcn
virtualenv -p python3.6 venv
source venv/bin/activate
pip install -r requirements.txt # change to tensorflow if you dont have a gpu.
pip install . # install keras-tcn

Run

cd adding_problem/
python main.py # run adding problem task

cd copy_memory/
python main.py # run copy memory task

cd mnist_pixel/
python main.py # run sequential mnist pixel task

Tasks

Adding Problem Task

Copy Memory Task

Sequential MNIST

References