Skip to content

zfyre/S-Wave

Repository files navigation

Learning Sparse Wavelet Representation

  • Using a External Model to Predict the low-pass filters and minimizing the loss function like an Autoencoder setup.
  • Download the temporary dataset using wget and unzip to the ./data directory.
  • Use the visualization.py to visualize the produced filters etc..

Image

# Initialization of Filter Prediction Model: model = FilterConv(in_channels = IN_CHANNELS, out_channels = OUT_CHANNELS) model.to(device = DEVICE) # Initialization of Autoencoder Model: data = torch.load(DATA_PATH) awt = DWT1d(filter_model = model) s # Training: awt.fit(X = data, batch_size = BATCH_SIZE, num_epochs = NUM_EPOCHS) name = f"{name_of_your_model}.pth" torch.save(awt, name)

currently implemented for 1D, using transform1d.py


OPEN FOR CONTRIBUTIONS AND MORE IDEAS!!


@article{ha2021adaptive, title={Adaptive wavelet distillation from neural networks through interpretations}, author={Ha, Wooseok and Singh, Chandan and Lanusse, Francois and Upadhyayula, Srigokul and Yu, Bin}, journal={Advances in Neural Information Processing Systems}, volume={34}, year={2021} }

About

Learning the Sparse Wavelet Representation for Specific signals using Convolution Filters

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages