Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 313-allow-non-monotonic-window-lead-times-in-helpers-statistics-py-ahead_names-definition
  • 414-include-crps-analysis-and-other-ens-verif-methods-or-plots
  • IntelliO3-ts
  • Kleinert_et_al_2022_Representing
  • develop protected
  • develop_IntelliO3-ts
  • enxhi_issue460_remove_TOAR-I_access
  • falco_issue271_feat_add-cdc-database-datahandler
  • felix_PaperVersion
  • felix_TF2_merge_test_sectorial_skill_scores
  • felix_issue267-create-wrf-chem-data-handler
  • felix_issue287_tech-wrf-datahandler-should-inherit-from-singlestationdatahandler
  • felix_issue303-wrf-dh-major-minor
  • felix_issue319-toar-statistics4wrf-dh
  • felix_issue400_feat-include-tf-probability
  • felix_issue411-feat_include-postprocessing-for-bnns
  • felix_issue412-create-ens-predictions-for-bnns
  • felix_issue420-datahandler-with-multiple-stats-per-variable
  • felix_issue_365-tech-set-ci-cd-artifact-expire-time
  • lukas_issue363_feat_calculate-toar-metrics-on-hourly-forecasts
  • v2.4.0 protected
  • v2.3.0 protected
  • v2.2.0 protected
  • v2.1.0 protected
  • Kleinert_etal_2022_initial_submission
  • v2.0.0 protected
  • v1.5.0 protected
  • v1.4.0 protected
  • v1.3.0 protected
  • v1.2.1 protected
  • v1.2.0 protected
  • v1.1.0 protected
  • IntelliO3-ts-v1.0_R1-submit
  • v1.0.0 protected
  • v0.12.2 protected
  • v0.12.1 protected
  • v0.12.0 protected
  • v0.11.0 protected
  • v0.10.0 protected
  • IntelliO3-ts-v1.0_initial-submit
40 results
Created with Raphaël 2.2.015Nov12119843229Oct28272625222120191815141312118765427Sep241413987632131Aug30272625242322212019181716141312119643227Jul26232221201918161587542130Jun2928232221181728May27262522212019181764329Apr282721201918161514131211109876131Mar302926fix in training_monitoring.py if validation is not availableNUMEXPR_MAX_THREADS set manually to 80 in run_mtfalco.py at the very beginning, so it does not drop to 8 (numexpr error)do_pca_reduction and n_pca_dimensions added to the hashes and sorted them to have better overviewraise ValueError in remove_nan() if intersection reaches min_length (with default=0, means it fails only if there is no intersection), option to disable pca_use_dask in run scriptmultiplied target variables occurence fixed, pca_reduction should work now (get_transposed_history fixed), start and end date are parsed as argumentsMerge branch 'release_v1.5.0' into 'master'v1.5.0v1.5.0release description is now updatedupdated version number, changelog, readme and docs and added dist fileMerge branch 'develop' into 'release_v1.5.0'Merge branch 'falco_issue323-raise-valueerror-in-remove_nan-if-data-is-nan-only' into 'develop'use dim name instead of pos to be independent of dim orderingadded use_dask with default 'False' for pca reductionupdate MyUnet modelprint statements for version testing in model classupdate UNet to TF2do_pca_reduction enabled by default and printed in main and logging.info with durationmerged latest 331-upgrade-code-to-tensorflow-v2 changesdask==2021.3.0, because afterwards support for python 3.6 was dropped.changed dask version, hopefully importable in gitlab now.calculate_pca_reduction() in data handler changed to a multiprocessing workflow using dask with every 1e3th values claculation stepspython3.8/site-packages: path changed from python3.6 in create_runscripts_HPC.shadditional netcdf4 version install removed for setup_venv_hdfml.sh and reactivated ml Jupyter/... for mlt_modules_juwels.shdeactivated additional package updates in setup_venv_*.shadded pydot to requirements.txtreadded dask and added tabulate==0.8.9 to requirements.txtdo now load model properlytest if pipeline finishes now successfullyMerge branch 'lukas_issue337_bug_ci-pipeline-fails-for-docs' into 'lukas_issue331_test_tf2_on_local_system_and_hdfml'Merge branch 'lukas_issue331_test_tf2_on_local_system_and_hdfml' into 'lukas_issue337_bug_ci-pipeline-fails-for-docs'fix issue if checkpoint has no modeltests should pass now, at least for training run modulepipreqs does not return all required packages. added requirements_tf2.txt with all dependencies. Check on other platforms for compatibilityMerge remote-tracking branch 'origin/331-upgrade-code-to-tensorflow-v2' into felix_TF2_merge_testfixes to test_inception_model.py and test_model_class.py mostly keras importings and some tower.name difference related.in 'test_abstract_model_class.py' test_compile_options_setter_as_dict() needed to be disabled until AbstractModelClass.__compare_keras_optimizers() works againtest_compile_options_setter_as_mix_attr_dict_valid_duplicates_optimizer() needed to be disabled until AbstractModelClass.__compare_keras_optimizers() works againchanged assertions to be compatible with new tf2 outputs'import keras' changed to 'import tensorflow.keras as keras' in test_abstract_model_class.pyChanged assertion comparisment containing old keras declarations. Disabled testing '_compare_keras_optimizers' since it is disabledremoved dask from requirements.txt since it does not load in GitLab. Removed __init__.py in keras_legacy, because it was unnecessary and wrong. Changed string to rawstring in PyTestRegex() calls.