An Efficient Unitary Neural Network implementation for PyTorch
Project description
torch_eunn
This repository contains a simple PyTorch implementation of a Tunable Efficient Unitary Neural Network (EUNN) Cell. This implementation was based on the tunable EUNN presented in this paper: https://arxiv.org/abs/1612.05231.
Installation
pip install torch_eunn
Usage
from torch_eunn import EUNNLayer # feed forward layer
from torch_eunn import EUNN # Recurrent unit
Examples
- 00: Simple Tests
- 01: Copying Task
Requirements
- PyTorch >= 0.4.0:
conda install pytorch -c pytorch
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
torch_eunn-0.1.3.tar.gz
(4.8 kB
view hashes)
Built Distributions
Close
Hashes for torch_eunn-0.1.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d69dc6bc28eb00e98361ef0e5071f10d270b4ed821621ecf49e493e8d62f6a2e |
|
MD5 | 1fbbdfb927939ccdcb1760f23f9842b1 |
|
BLAKE2b-256 | b6d021937f0dfe5a2d530e50a6a7e7aff7c340afdf2162dcada13668341f98ff |
Close
Hashes for torch_eunn-0.1.3-py2-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | eeb0c4ef9f32f9486ccd5f7e96f29d9a88bff24ba1744f8c86720e85084312f8 |
|
MD5 | 874275217267dd08b13ad4b5ee14584c |
|
BLAKE2b-256 | f8e9fd3d7d7948ab2ab21abf519c964986f1f60448d0c91fc70c4258ba543ccd |