TF2 implementation of a Temporal Convolutional Network with a probabilistic twist
Project description
ptcn
Tensorflow (2.x) implementation of a Temporal Convolutional Network architecture, with a probabilistic twist.
This project indulges a couple of curiosities:
- Working with convolutional sequence-to-sequence models a la An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Adding a bayesian twist to the network a la Bayesian Segnet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
This implementation has been inspired by other projects, including:
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ptcn-0.1.3.tar.gz
(3.4 kB
view hashes)
Built Distribution
ptcn-0.1.3-py3-none-any.whl
(4.2 kB
view hashes)