Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/chrhenning/hypnettorch
Package for working with hypernetworks in PyTorch.
https://github.com/chrhenning/hypnettorch
deep-learning hypernet hypernets hypernetwork hypernetworks neural-network python pytorch torch
Last synced: about 1 month ago
JSON representation
Package for working with hypernetworks in PyTorch.
- Host: GitHub
- URL: https://github.com/chrhenning/hypnettorch
- Owner: chrhenning
- License: apache-2.0
- Created: 2021-10-06T16:14:06.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2023-09-07T20:28:39.000Z (over 1 year ago)
- Last Synced: 2024-11-01T20:12:28.563Z (about 2 months ago)
- Topics: deep-learning, hypernet, hypernets, hypernetwork, hypernetworks, neural-network, python, pytorch, torch
- Language: Python
- Homepage: https://hypnettorch.readthedocs.io/
- Size: 821 KB
- Stars: 117
- Watchers: 2
- Forks: 14
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# Hypernetworks for PyTorch
[This package](https://hypnettorch.readthedocs.io) contains utilities that make it easy to work with [hypernetworks](https://arxiv.org/abs/1609.09106) in [PyTorch](https://pytorch.org/).
## Installation
You can either install the latest package version via
```
python3 -m pip install hypnettorch
```
or, you directly install the current sources
```
python3 -m pip install git+https://github.com/chrhenning/hypnettorch
```
#### Installation for developers
If you actively develop the package, it is easiest to install it in `development mode`, such that all changes that are done to source files are directly visible when you use the package.
Clone the repository to a location of your choice
```
git clone https://github.com/chrhenning/hypnettorch.git
```
and move inside the cloned repo
```
cd ./hypnettorch
```
Now, you can simply **install** the package in `editable` mode, which will ensure that you can easily update the package sources (cf. [development mode](https://setuptools.readthedocs.io/en/latest/userguide/development_mode.html))
```
pip3 install --editable . --user
```
Since the package was installed in `editable` mode, you can always update the sources simply by pulling the most recent code
```
git pull
```
You can **uninstall** the package at any point by running `python3 setup.py develop -u`.
## Usage
The basic functionalities of the package are quite intuitive and easy to use, e.g.,
```python
import torch
from hypnettorch.mnets import MLP
from hypnettorch.hnets import HMLP
mnet = MLP(n_in=8, n_out=1, no_weights=True) # Create MLP with 8 inputs and 1 output.
hnet = HMLP(mnet.param_shapes) # Create hypernetwork for the above MLP.
weights = hnet.forward(cond_id=0) # Generate the weights of network `mnet`.
inputs = torch.rand(32, 8) # Random inputs.
mnet.forward(inputs, weights=weights) # Compute predictions using the generated weights.
```
There are several [tutorials](https://github.com/chrhenning/hypnettorch/tree/master/hypnettorch/tutorials). Check out the [getting started](https://github.com/chrhenning/hypnettorch/blob/master/hypnettorch/tutorials/getting_started.ipynb) tutorial when working with ``hypnettorch`` for the first time.
You may also checkout the [examples](https://hypnettorch.readthedocs.io/en/latest/examples.html). For instance, how to use hypernetworks for continual learning.
## Documentation
The documentation can be found [here](https://hypnettorch.readthedocs.io).
#### Note for developers
The documentation can be build using
```
python3 setup.py build_sphinx
```
and opened via the file [index.html](docs/html/index.html).
## Citation
When using this package in your research project, please consider citing one of our papers for which this package has been developed.
```
@inproceedings{posterior:replay:2021:henning:cervera,
title={Posterior Meta-Replay for Continual Learning},
author={Christian Henning and Maria R. Cervera and Francesco D'Angelo and Johannes von Oswald and Regina Traber and Benjamin Ehret and Seijin Kobayashi and Benjamin F. Grewe and João Sacramento},
booktitle={Conference on Neural Information Processing Systems},
year={2021},
url={https://arxiv.org/abs/2103.01133}
}
```
```
@inproceedings{ehret2020recurrenthypercl,
title={Continual Learning in Recurrent Neural Networks},
author={Benjamin Ehret and Christian Henning and Maria R. Cervera and Alexander Meulemans and Johannes von Oswald and Benjamin F. Grewe},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://arxiv.org/abs/2006.12109}
}
```
```
@inproceedings{oshg2019hypercl,
title={Continual learning with hypernetworks},
author={Johannes von Oswald and Christian Henning and Benjamin F. Grewe and Jo{\~a}o Sacramento},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://arxiv.org/abs/1906.00695}
}
```