PyTorch-Wavelet-Toolbox
PyTorch-Wavelet-Toolbox copied to clipboard
v0lta
Differentiable fast wavelet transforms in PyTorch with GPU support.
Hello! I was wondering if it would be possible to support a differentiable version of the `ptwt.continuous_transform.cwt` function. I see that internally, the function converts everything to numpy arrays, and...
I have a specific application where the sparse matrix representation of the DWT is really useful for a 3D signals. I'd like to propose it as an enhancement.
I have tried to pass tensor of shape B,C,D,H,W but internally it adds a dimension after B. So the tensor becomes B,1,C,D,H,W. Then it fails to conv3d. Is there anyway...
Some combinations of wavelets and number of decomposition steps cause the following `RuntimeError`: "Padding value causes wrapping around more than once". If the padding values are greater than the input...
Hi. I am trying to pull out the coefficients as a matrix. Similar to pywt. How do I do that (last line)? ``` import ptwt, pywt, torch import numpy as...
This PR bundles work to improve the documentation throughout the code base. * [X] Split the API reference into multiple pages * [ ] Add explanation of boundary handling /...
TODO: Update https://github.com/v0lta/PyTorch-Wavelet-Toolbox/blob/2b694ded2cceb6cb330de8560116685d1c306ec3/setup.cfg#L70 once the latest MyPy release, including https://github.com/python/mypy/pull/17356, is out.
Hi, thank you for providing this toolbox. Is there any future work planned toward allowing 3D stationary wavelet transform? E.g. on an array of shape (batch, channels, height, width, depth)...
Hi, thank you for providing this toolbox. Is there any future work planned toward allowing torch.compile() for ptwt?
Hi,this is elegant and convenient toolbox, but I noticed that complex data is not supported. It could be better that complex form could be implemented.
