adaptive-wavelets
adaptive-wavelets copied to clipboard
Adaptive, interpretable wavelets across domains (NeurIPS 2021)
https://github.com/Yu-Group/adaptive-wavelets/blob/79d2ccbb9e54c74e5e4af3963d661b44ffac17af/awave/transform1d.py#L31C1-L31C55 In the above line is the filter the only parameter which has to be updated while backpropagating?
Current version on PyPI is from 09/06/2021 and seems to be missing some things. E.g.: ``` wt = DWT2d(wave='db5', mode='zero', J=4, init_factor=1, noise_factor=0, const_factor=0, device='cpu') ``` gives: ``` TypeError: __init__()...
Starting Training Loop... Traceback (most recent call last): File "D:\project_python\doctor_project\LYC\20241130\222.py", line 42, in wt.fit(X=X, lr=1e-2, num_epochs=10) File "C:\ProgramData\miniconda3\envs\py10\lib\site-packages\awave\transform.py", line 86, in fit trainer(train_loader, epochs=num_epochs) File "C:\ProgramData\miniconda3\envs\py10\lib\site-packages\awave\utils\train.py", line 84, in __call__...