Skip to content

[Work in Progress] Comparison of hypercomplex CNN with real CNN in the context of image classification. The code is part of a master's thesis.

active 2024-09-292025-04-21 (UTC)

Complete coverage26,541 / 26,541 hourly files (100%) · 2 absent upstream2023-08-152026-08-24 (UTC)
Events
207
Pushes
175
Pull requests
2
Issues
22
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 205 days from 2024-09-29 to 2025-04-21. Pushes: 175 total, peak 21 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 22 total, peak 13 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
dkwapisz19917520

Recent activity

Latest issues, pull requests and releases

  • Issue#11dkwapisz2025-02-09 13:47
    Train and reduce complexity of HyperComplex CNN model to achieve same results as CNN model. (if possible)
  • Issue#12dkwapisz2025-02-09 13:47
    Tune HyperComplex CNN model to achieve better results than CNN model.
  • Issue#9dkwapisz2025-02-09 13:47
    Train and tune CNN model using all Color Spaces.
  • Issue#10dkwapisz2025-02-09 13:47
    Start training HyperComplex CNN model using the same parameters as best CNN model.
  • Issue#8dkwapisz2025-02-09 13:47
    Implement mechanism to plot the results.
  • Issue#6dkwapisz2025-02-08 13:25
    Implement GridSearch/RandomSearch for HyperComplex CNN architecture.
  • Issue#5dkwapisz2025-02-08 13:25
    Implement GridSearch/RandomSearch for CNN architecture.
  • Issue#13dkwapisz2025-02-04 21:49
    Add logging to file and adjust printing/verboses during training.
  • Issue#7dkwapisz2025-02-04 21:49
    Implement mechanism to gather all the results with parallel run.
  • Issue#13dkwapisz2025-02-02 18:29
    Add logging to file.
  • Issue#4dkwapisz2025-02-02 18:28
    Implement parallel processing with GPU split.
  • Issue#3dkwapisz2025-02-02 13:02
    Add tests for ColorSpaceConverter.
  • Issue#2dkwapisz2025-02-02 12:39
    Align ColorSpaceConverter with HyperComplex CNN architecture.
  • Issue#10dkwapisz2025-02-02 12:13
    Start training HyperComplex CNN model using the same parameters as best CNN model.
  • Issue#9dkwapisz2025-02-02 12:12
    Train and tune CNN model using all Color Spaces.
  • Issue#8dkwapisz2025-02-02 12:12
    Implement mechanism to plot the results.
  • Issue#7dkwapisz2025-02-02 12:12
    Implement mechanism to gather all the results with parallel run.
  • Issue#6dkwapisz2025-02-02 12:12
    Implement GridSearch/RandomSearch for HyperComplex CNN architecture.
  • Issue#5dkwapisz2025-02-02 12:12
    Implement GridSearch/RandomSearch for CNN architecture.
  • Issue#4dkwapisz2025-02-02 12:11
    Implement parallel processing with GPU split.
  • Issue#3dkwapisz2025-02-02 12:11
    Add tests for ColorSpaceConverter.
  • Issue#2dkwapisz2025-02-02 12:09
    Align ColorSpaceConverter with HyperComplex CNN architecture.
  • Pull request#1dkwapisz2025-01-28 21:08
  • Pull request#1dkwapisz2025-01-28 21:08

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.