https://github.com/tnbar/tednet
TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
https://github.com/tnbar/tednet
artificial-intelligence deep-neural-networks pytorch tensor-decomposition
Last synced: 8 months ago
JSON representation
TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
- Host: GitHub
- URL: https://github.com/tnbar/tednet
- Owner: tnbar
- License: mit
- Created: 2020-12-04T09:36:43.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2022-04-06T03:00:27.000Z (about 4 years ago)
- Last Synced: 2025-09-01T11:18:02.704Z (10 months ago)
- Topics: artificial-intelligence, deep-neural-networks, pytorch, tensor-decomposition
- Language: Python
- Homepage:
- Size: 313 KB
- Stars: 97
- Watchers: 2
- Forks: 13
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-tensorial-neural-networks - TedNet - Term Tucker (BTT), Tucker-2, Tensor Train (TT) and Tensor Ring (TR) on traditional deep neural layers. | Python (Pytorch) | (Toolboxes / Deep Model Implementation)
README
[](https://github.com/tnbar/tednet/actions/workflows/python-package.yml)
[](https://tednet.readthedocs.io/en/latest/?badge=latest)
[](https://pypi.org/project/tednet/)
# TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
`tednet` is a toolkit for tensor decomposition networks. Tensor decomposition networks are neural networks whose layers are decomposed by tensor decomposition, including CANDECOMP/PARAFAC, Tucker2, Tensor Train, Tensor Ring and so on. For a convenience to do research on it, ``tednet`` provides excellent tools to deal with tensorial networks.
Now, **tednet** is easy to be installed by `pip`:
```shell script
pip install tednet
```
More information could be found in [Document](https://tednet.readthedocs.io/en/latest/index.html).
---
### Quick Start
##### Operation
There are some operations supported in `tednet`, and it is convinient to use them. First, import it:
```python
import tednet as tdt
```
Create matrix whose diagonal elements are ones:
```python
diag_matrix = tdt.eye(5, 5)
```
A way to transfer the Pytorch tensor into numpy array:
```python
diag_matrix = tdt.to_numpy(diag_matrix)
```
Similarly, the numpy array can be taken into Pytorch tensor by:
```python
diag_matrix = tdt.to_tensor(diag_matrix)
```
##### Tensor Decomposition Networks (Tensor Ring for Sample)
To use tensor ring decomposition models, simply calling the tensor ring module is enough.
```python
import tednet.tnn.tensor_ring as tr
# Define a TR-LeNet5
model = tr.TRLeNet5(10, [6, 6, 6, 6])
```
---
### Citing
If you use `tednet` in an academic work, we will appreciate you for citing our paper with:
```bibtex
@article{DBLP:journals/ijon/PanWX22,
author = {Yu Pan and
Maolin Wang and
Zenglin Xu},
title = {TedNet: {A} Pytorch toolkit for tensor decomposition networks},
journal = {Neurocomputing},
volume = {469},
pages = {234--238},
year = {2022}
}
```