Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 1-test_juwels
  • 104-adopt-runscript-generator-for-multiple-variables
  • 143-licensing
  • 143-licensing-2
  • Bing_issue#018_revise_convLSTM_to_Loliverhennigh_version
  • Bing_issue#156_test_CICD
  • Gong2022_temperature_forecasts
  • amirpasha_including_2tier_pystager_extraction
  • amirpasha_issue#008_data_extraction
  • amirpasha_issue#065_handling_exceptions
  • amirpasha_issue#33_fail_communication_between_master_workers
  • bing_#172_integrate_weatherbench
  • bing_#37_organize_last_mins_meeting
  • bing_clean_GMD1
  • bing_horovod_convLSTM
  • bing_issue#001_issue#003_test_juwels
  • bing_issue#005_clean_and_update_CICD_file
  • bing_issue#006_add_unitest
  • bing_issue#009_clean_up_postprocessing
  • bing_issue#010_remove_hickle_split_data
  • ambs_v1
  • ambs_gmd_nowcasting_v1.0
  • GMD1
  • modular_booster_20210203
  • new_structure_20201004_v1.0
  • old_structure_20200930
26 results
Created with Raphaël 2.2.024Aug2319171613121087230Jul292827262322212019161514131211108642130Jun2925242322211816151312111098762131May3029282726252422201918171514131211109865432130Apr2928272624232221201816151098763131Mar302926252423Bugfix in finalizing print-statements.Final bugfixes, removal of plotting of validation loss and improvements to timing. Besides, default of checked validation dataset fraction is set to 10%.Remove summary_op from val_fetches and likewise also remove summary_op from summary_writer.correction to main-loop in main_zrain_models.py.Several bugfixes due to usage of deprecated arguments in main_train_models.py.Fix for random generator on old numpy versions.Some bugfixes in handling arguments of main_train.py.Removal of some unnecessary comment lines in vanilla_convLSTM_model.pyFurther integration of new model checker-approach.First implementation of new validation loss-checker.Adopt call for convLSTM-model.Add calculator for last iteration step of warm-up phase to vanilla_convLSTM_model.pyFirst prototype for warmu-up phase of learning rate.Merge branch 'michael_issue#111_implement_parallelized_SGD' into michael_issue#119_warmup_HorovodMerge branch 'michael_issue#133_clean_up_postprocessing_code' into developRemove huge amounts of print-statements from main_visualize_postprocess.py.michael_issue#1…michael_issue#133_clean_up_postprocessing_codeMake set_model_saver_flag-method more verbose.fix normalizationMerge branch 'bing_issue#131_extract_g1_loss' into developMerge branch 'michael_issue#132_bugfix_loss_tracking' into bing_issue#131_extract_g1_lossbing_issue#131_…bing_issue#131_extract_g1_lossFinal fix to handling losses in main_train_models.py.michael_issue#1…michael_issue#132_bugfix_loss_trackingAdd print of validation loss to check if bugfix is removed.Bugfix in handling loss-terms that are tracked.update normalizationSome minor source-code style changes and removal of several print-statements.Add texture-evaluation to the default etrics of postprocessing.Removal of additional averaging keyword-argument for calc_spatial_variability.Removal of unused argument from generate_fetches in main_train_models.py.Minor fix in main_train_models.py.Add print-statement to identify checkpoint that is restored.Update of check_str_in_list-function in general_utils.py to return optionally the indices plus some style-changes in source-code.Bugfix in handling nested attributes for fetches in main_train_models.py.Generic way to dig thorugh nested objects of model which can now be handled with passing tuples to fetch_list.split best and last modelfix lon-transformMerge branch 'bing_issue#131_extract_g1_loss' into yan_issue#100_extract_prcp_dataupdateUpdate base_model.pyUpdate base_model.pyCorrection to statistical_evaluation.py