DWSNets
Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]
File Explorer
Download Latest Version (.zip)- __init__.py
- compute_statistics.py
- generate_data_splits.py
- plot_inr_reconstruction.py
- README.md
- trainer.py
- __init__.py
- inr_dataset.py
- sine_data.py
- __init__.py
- compute_statistics.py
- generate_data_splits.py
- inr_trainer.py
- loss.py
- README.md
- trainer.py
- __init__.py
- data.py
- utils.py
- blocks.png
- sym.png
- __init__.py
- base.py
- bias_to_bias.py
- bias_to_weight.py
- layers.py
- weight_to_bias.py
- weight_to_weight.py
- __init__.py
- inr.py
- models.py
- mnist-inr-classification.ipynb
- __init__.py
- test_layers.py
- .gitignore
- .isort.cfg
- LICENCE
- README.md
- requirements.txt
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/AvivNavon/DWSNets
Downloads the entire project code from GitHub to your computer.
cd DWSNets
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)