Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: v0lta/PyTorch-Wavelet-Toolbox
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: v0lta/PyTorch-Wavelet-Toolbox
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: feature/outer-prod
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 9 commits
  • 12 files changed
  • 1 contributor

Commits on Jul 2, 2024

  1. Make _outer more general

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    2678419 View commit details
    Browse the repository at this point in the history

  2. Add general nd filter construction

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    58da7e6 View commit details
    Browse the repository at this point in the history

  3. Add general nd padding function

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    47493ee View commit details
    Browse the repository at this point in the history

  4. Apply new functions in wavelet transforms

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    6a56428 View commit details
    Browse the repository at this point in the history

  5. Change convention on 2d coeff naming. 

    We name the four coefficients of single level 2d FWT
ll, lh, hl, hh based on the filter combination they are
derived from (l - lowpass, h - highpass).
The approximation coeff is clearly denoted by ll,
the diagonal detail coeff by hh.

We generally abbreviate by the axis order, i.e.
lh corresponds to low pass on the first axis and
highpass on the second.

The naming of the horizontal and vertical detail coeffs
depend on the convention how the axes are interpreted.
PyWavelets interpret the first axis as rows and the second
as columns -> horizontal details are hl.
    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    f9a5eb9 View commit details
    Browse the repository at this point in the history

  6. Refactor

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    db86e69 View commit details
    Browse the repository at this point in the history

  7. Refactor padding removal

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    d172440 View commit details
    Browse the repository at this point in the history

  8. Fix linter remarks

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    9bea2cb View commit details
    Browse the repository at this point in the history

  9. Rewrite _create_tensor

    @felixblanke
    felixblanke committed Jul 2, 2024
    Configuration menu
    Copy the full SHA
    e151f98 View commit details
    Browse the repository at this point in the history
Loading