Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • amir
  • gan
  • integrate_structures
  • lstm
  • master default protected
  • newlstm
  • oldmaster
  • predict
  • speed-up
  • tf20
  • towards_tf2
  • updates
  • v3.0.0
  • v2.0.0
  • v1.2.2b0
  • v1.2.1
  • v1.2.0
  • v1.1.1
  • v1.1.0
  • v1.0.4
  • v1.0.3
  • v1.0.2
  • v1.0.1
  • v1.0.0
  • 0.1.10
  • 0.1.9
  • 0.1.8
  • 0.1.7
  • 0.1.6
  • 0.1.5
  • 0.1.4
  • 0.1.3
32 results
Created with Raphaël 2.2.09Dec7654128Nov22212098632131Oct302926252423212019181614131211106532129Sep2827262523221915128764131Aug29282517427Jul2420171312108765429Jun282726231914231May302386523Apr2216724Mar2317161386424Feb2216156Jan4321Dec196130Nov2928242118171614111098543231Oct30282726252321181716141312111097626Sep252321129875230Aug2928252416121110Created mechanism that allows as to train only parts of the graphMerge branch 'reproducible' into 'master'chmod -R -x+X .Merge branch 'reproducible' into 'master'remove the models after the testsMerge branch 'reproducible' into 'master'Merge branch 'train_and_evaluate' into 'master'Use tf.train.get_or_create_global_step (introduced in 1.2) instead of the contrib oneUse tf.train.get_or_create_global_step (introduced in 1.2) instead of the contrib oneMerge branch 'early-stop' into 'master'Mention at which step did the best value happenfix earlystopping. Implement testsAccuracy/totalremove verbosityAdd an early stopping hookMerge branch 'predict' into 'master'added lstm, simple cnn, and simple mlp networksAdd a script to call tf.estimator.train_and_evaluateUse bob.extension to load the config filesimprove super callimprove logging of predict_bioMerge branch 'predict' into 'master'make tensorflow logging to warningrename test methodmake reproducibility a functionHandle number of parallel jobs correctlyMerge branch 'predict' into 'master'Merge branch 'master' into 'predict'Merge branch 'organizing-transfer-learning' into 'master'Renamed the keyword argumente is_training_mode to mode and use the tf.estimator.Modekeys to switch between training/validation/prediction modeslog_device_placement=TrueExist if all files already existcorrect syntaxcode clean-upfilter existing filesAdd base_archremove repeat. Use dataset.repeat insteadmake sure the biofiles are keptKeep regenerating labels and keysupdate train generic script