tunakasif/torch-frft

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

Implementation of "Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains" by Tancik et al.

Differentiable short-time Fourier transform (DSTFT): Gradient-based parameters tuning for adaptive time-frequency representation. DSTFT is a neural network layer whose weights are its parameters (e.g. window and hop lengths).

TensorLy-Torch: Deep Tensor Learning with TensorLy and PyTorch

[JMLR] Differentiable fast wavelet transforms in PyTorch with GPU support.

Learning in infinite dimension with neural operators.

Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.

Add Dendrites to your PyTorch Project

Neural network quantization for research and prototyping