close
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: igv/FSRCNN-TensorFlow
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: HelpSeeker/FSRCNN-TensorFlow
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 10 commits
  • 8 files changed
  • 2 contributors

Commits on Oct 1, 2019

  1. Increase artifact mitigation (--distort)

    The current compression artifact mitigation via --distort is far to weak to enhance low quality footage. The chance to degrade a training image is too low and the quality range too high, as to make a noticeable difference. After quite a few tests these settings seem to achieve a good balance between efficient artifact removal and the famous oil painting effect.
    HelpSeeker authored Oct 1, 2019
    Configuration menu
    Copy the full SHA
    90caa78 View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    fc56d26 View commit details
    Browse the repository at this point in the history
  3. Decrease verbosity to a minimum

    Suppresses all Future Warnings and reduces Tensorflow verbosity to basically nothing. Feels a bit hacky in main.py and suppressing warnings is usually not the brightest thing to do, but I don't have the knowledge to fix any major Tensorflow breakage anyway. On the bright side you can now easily look up information printed by the scripts, without having to weed through walls of text (especially useful, if you run several short training sessions in succession).
    HelpSeeker authored Oct 1, 2019
    Configuration menu
    Copy the full SHA
    705f904 View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2019

  1. Update documentation

    HelpSeeker authored Oct 2, 2019
    Configuration menu
    Copy the full SHA
    ef687e6 View commit details
    Browse the repository at this point in the history
  2. Support for scale=1

    igv committed Oct 2, 2019
    Configuration menu
    Copy the full SHA
    7c7c5bf View commit details
    Browse the repository at this point in the history
  3. Configuration menu
    Copy the full SHA
    0d33f0a View commit details
    Browse the repository at this point in the history

Commits on Oct 3, 2019

  1. Merge pull request haasn#1 from igv/master

    Pull recent igv commits (2019-10-02)
    HelpSeeker authored Oct 3, 2019
    Configuration menu
    Copy the full SHA
    72038df View commit details
    Browse the repository at this point in the history

Commits on Oct 4, 2019

  1. Revert "Merge pull request haasn#1 from igv/master"

    This reverts commit 72038df, reversing
    changes made to ef687e6.
    HelpSeeker committed Oct 4, 2019
    Configuration menu
    Copy the full SHA
    e30e472 View commit details
    Browse the repository at this point in the history
  2. Merge pull request #2 from igv/master

    Pull recent igv commits (2019-10-04)
    HelpSeeker authored Oct 4, 2019
    Configuration menu
    Copy the full SHA
    24ba21f View commit details
    Browse the repository at this point in the history

Commits on May 11, 2023

  1. Upload comparison images

    Found some old comparison images that I made back in the day.
    Might as well include them. They showcase what kind of source
    quality I had in mind while creating this project.
    HelpSeeker authored May 11, 2023
    Configuration menu
    Copy the full SHA
    9dc4716 View commit details
    Browse the repository at this point in the history
Loading