conda create -n dwsnets python=3.9
conda activate dwsnets
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch

git clone https://github.com/AvivNavon/DWSNets.git
cd DWSNets
pip install -e .

@InProceedings{pmlr-v202-navon23a,
  title = 	 {Equivariant Architectures for Learning in Deep Weight Spaces},
  author =       {Navon, Aviv and Shamsian, Aviv and Achituve, Idan and Fetaya, Ethan and Chechik, Gal and Maron, Haggai},
  booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
  pages = 	 {25790--25816},
  year = 	 {2023},
  editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
  volume = 	 {202},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {23--29 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v202/navon23a/navon23a.pdf},
  url = 	 {https://proceedings.mlr.press/v202/navon23a.html},
}

Contributors

Stargazers

Forkers

techthiyanes tongfanweitf aradhyamathur xzg5101 ai-hub-deep-learning-fundamental stjordanis liuyyy111 twonp168 noticeable qimaqi

state_dict = torch.load(os.path.join(path, dir_, 'checkpoints', 'model_final.pth'), map_location=device)
w0, b0 = state_dict['seq.0.weight'], state_dict['seq.0.bias']
w1, b1 = state_dict['seq.1.weight'], state_dict['seq.1.bias']
w2, b2 = state_dict['seq.2.weight'], state_dict['seq.2.bias']
x = get_mgrid(28, dim=2).to(device)
x = torch.mm(x, w0.T) + b0
x = torch.sin(x)
x = torch.mm(x, w1.T) + b1
x = torch.sin(x)
x = torch.mm(x, w2.T) + b2
x = x.reshape(28, 28).cpu().numpy()