seppl/optical-regeneration
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 249fe1e940 wip machine_learning Joseph Hopfmüller 2025-01-27 21:05:49 +01:00
  • f38d0ca3bb model robustness testing Joseph Hopfmüller 2025-01-10 23:40:54 +01:00
  • 3af73343c1 add corrected datasets with PMD and dispersion Joseph Hopfmüller 2024-12-29 16:41:52 +01:00
  • 7a0b65f82d Merge branch 'machine_learning' of git.suuppl.dev:seppl/optical-regeneration into machine_learning Joseph Hopfmüller 2024-12-29 16:00:41 +01:00
  • 98305fdf47 update dataset configurations, add rotation module, and refine model settings for training, new hyperparameter tuning run for corrected datasets Joseph Hopfmüller 2024-12-29 16:00:36 +01:00
  • 33141bdf41 add datasets with PMD and dispersion Joseph Hopfmüller 2024-12-29 15:59:01 +01:00
  • 638b62ee03 add training data, y-pol phase shifted by 90 deg, x/y different powers Joseph Hopfmüller 2024-12-11 10:56:30 +01:00
  • 98d0b5ba8d add training data, y-pol phase shifted by 90 deg Joseph Hopfmüller 2024-12-11 10:03:29 +01:00
  • 39ae13d0af add training script for polarization estimation, refactor model definitions, randomised polarisation support in data_loader Joseph Hopfmüller 2024-12-11 09:48:38 +01:00
  • 0e29b87395 add regenerator class and update dataset configurations for model training Joseph Hopfmüller 2024-12-05 23:55:03 +01:00
  • 884d9f73c9 add default to birefsteps Joseph Hopfmüller 2024-12-05 23:50:49 +01:00
  • 08c81428ef add new training data Joseph Hopfmüller 2024-12-05 23:50:14 +01:00
  • 9299316f81 add new training_data Joseph Hopfmüller 2024-12-05 23:43:24 +01:00
  • 2fcf621a50 update submodule to latest commit Joseph Hopfmüller 2024-12-05 23:29:53 +01:00
  • 36f89f379d refactor signal generation to support single-channel mode and adjust birefringence parameters Joseph Hopfmüller 2024-12-05 23:29:48 +01:00
  • 950516197c add new training data Joseph Hopfmüller 2024-12-04 13:22:50 +01:00
  • b7eecea1ae add new training data Joseph Hopfmüller 2024-12-04 10:07:39 +01:00
  • d3626f9a44 remove newly generated training data Joseph Hopfmüller 2024-12-04 10:00:50 +01:00
  • 7f89c02d8d update submodule to latest commit Joseph Hopfmüller 2024-12-02 18:54:15 +01:00
  • a8a1c49c00 Merge branch 'machine_learning' of git.suuppl.dev:seppl/optical-regeneration into machine_learning Joseph Hopfmüller 2024-12-02 18:51:30 +01:00
  • 297e9e8d7f update submodule configuration and enhance model settings; add eye diagram functionality Joseph Hopfmüller 2024-12-02 18:50:43 +01:00
  • aa2e7a4cb4 move sliced dataset testing script Joseph Hopfmüller 2024-12-02 18:50:13 +01:00
  • 1dcefecf59 update signal generation patterns in generate_signal.py Joseph Hopfmüller 2024-12-02 18:49:38 +01:00
  • a5f2f49360 enhance data loading and processing in FiberRegenerationDataset; add timestamps and support for multiple file paths Joseph Hopfmüller 2024-12-02 18:49:14 +01:00
  • e20aa9bfb1 add eye_diagram analysis Joseph Hopfmüller 2024-12-02 18:48:43 +01:00
  • 010889af13 generate training data with finer length steps Joseph Hopfmüller 2024-12-02 18:45:10 +01:00
  • c145d58df8 update subproject reference to latest commit Joseph Hopfmüller 2024-11-29 15:53:08 +01:00
  • 487288c923 define new activation functions and parametrizations Joseph Hopfmüller 2024-11-29 15:51:25 +01:00
  • bdf6f5bfb8 clean up regen_no_hyper.py Joseph Hopfmüller 2024-11-29 15:50:34 +01:00
  • e02662ed4f new optuna studies Joseph Hopfmüller 2024-11-29 15:49:59 +01:00
  • fd7a0b9c31 using latest knowledge for hyperparameter search Joseph Hopfmüller 2024-11-29 15:49:46 +01:00
  • ff32aefd52 minor fixes and changes Joseph Hopfmüller 2024-11-29 15:49:10 +01:00
  • b156b9ceaf refactor hypertraining.py to improve model layer handling and response plotting; adjust data settings for batch processing Joseph Hopfmüller 2024-11-29 15:48:27 +01:00
  • cfa08aae4e add training.py for defining and running models without hyperparametertuning Joseph Hopfmüller 2024-11-29 15:48:18 +01:00
  • 0422c81f3b update single_core_regen settings new runs Joseph Hopfmüller 2024-11-24 01:56:01 +01:00
  • 7343ccb3a5 refactor complex loss functions for improved readability; update settings and dataset classes for consistency Joseph Hopfmüller 2024-11-24 01:55:32 +01:00
  • 9a16a5637d add optional parameter suggestion methods for Optuna trials Joseph Hopfmüller 2024-11-24 01:55:12 +01:00
  • 80e9a3379e add autosampler support Joseph Hopfmüller 2024-11-20 23:10:14 +01:00
  • 8d4d0468bd complexhalf (complex32) isn't supported by torch.linalg.qr Joseph Hopfmüller 2024-11-20 22:56:26 +01:00
  • 6358c95c42 new hyperparameter db Joseph Hopfmüller 2024-11-20 22:49:40 +01:00
  • 674033ac2e move hypertraining class into separate file; move settings dataclasses into separate file; add SemiUnitaryLayer; clean up model response plotting code; cnt hyperparameter search Joseph Hopfmüller 2024-11-20 22:49:31 +01:00
  • cdca5de473 training loop speedup Joseph Hopfmüller 2024-11-20 11:29:18 +01:00
  • 1622c38582 refactor: remove unused Optuna visualization utility Joseph Hopfmüller 2024-11-17 22:23:20 +01:00
  • 2bba760378 add: implement Optuna visualization utility with Dash Joseph Hopfmüller 2024-11-17 22:23:01 +01:00
  • 9ec548757d add: regen.py (main hyperparameter training file) feat: add utility functions for fiber dataset visualization and hyperparameter training; housekeeping: rename dataset.py -> datasets.py Joseph Hopfmüller 2024-11-17 22:22:37 +01:00
  • 05a3ee9394 refactor: clean up .gitignore, remove unused scripts Joseph Hopfmüller 2024-11-17 22:18:44 +01:00
  • 086240489a minor edits on notes Joseph Hopfmüller 2024-11-17 22:16:52 +01:00
  • 87f40fc37c add SlicedDataset class and utility scripts; refactor: remove _path_fix.py and update imports; Joseph Hopfmüller 2024-11-17 01:04:33 +01:00
  • 90aa6dbaf8 housekeeping Joseph Hopfmüller 2024-11-17 01:04:14 +01:00
  • 744c5f5166 rename dir; add torch import test script Joseph Hopfmüller 2024-11-16 00:39:19 +01:00
  • 939a511625 add installation notes for CUDA 12.4, pyenv, and PyTorch; include useful links main Joseph Hopfmüller 2024-11-16 00:03:43 +01:00
  • 2bf47dc0c0 more precise clone instructions Joseph Hopfmüller 2024-11-15 23:54:33 +01:00
  • 5871c79501 update README with cloning notes and adjust path in _path_fix.py for submodule import Joseph Hopfmüller 2024-11-15 21:21:50 +01:00
  • f7217a93bb add pypho as submodule Joseph Hopfmüller 2024-11-15 21:00:19 +01:00
  • 5e2d3dd6b7 change pypho symlink to submodule and handle new location in _path_fix.py Joseph Hopfmüller 2024-11-15 20:56:34 +01:00
  • c42da6ca58 add license EUPL-1.2 Joseph Hopfmüller 2024-11-15 18:28:45 +01:00
  • e929991b3d add datasets to LFS Joseph Hopfmüller 2024-11-15 18:27:19 +01:00
  • fa85fca978 add data to lfs Joseph Hopfmüller 2024-11-15 17:01:29 +01:00
  • 9c43ce4c85 git lfs setup cont'd 2 Joseph Hopfmüller 2024-11-15 16:54:03 +01:00
  • c76bfd20fe lfs setup cont'd Joseph Hopfmüller 2024-11-15 16:49:09 +01:00
  • f3544bc9ce setup lfs Joseph Hopfmüller 2024-11-15 16:46:49 +01:00
  • 0564969a50 signal generation working Joseph Hopfmüller 2024-11-15 16:46:09 +01:00
  • 7ac4e48c20 pam4 signal modulation Joseph Hopfmüller 2024-11-15 01:33:39 +01:00
  • e35bdf6a1a start signal gen Joseph Hopfmüller 2024-11-13 23:46:17 +01:00
  • 15d62f189d Initial commit Hopfmueller, Joseph 2024-11-13 12:00:42 +01:00