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 2.2.07Feb7Jan12Dec21Nov1830Oct19Aug28Jun252127May20143225Apr24231721Mar1926Feb251431Jan181611327Nov2013230Oct17975426Sep1228Aug27161310928Jul25201917161312111098Jun7629May282423228542130Apr272625242319161327Mar25Jan2417214Dec1197654128Nov22212098632131Oct302926252423212019181614131211106532129Sep2827262523221915128764131Aug29282517427Jul2420171312108765429Jun282726231914231May302386523Apr2216724Mar2317161386424Feb221615new keras modelsAdd more utilsadd starting point options to the style transfer scriptnitpickmake sure densenet layer names are consistentadd center loss, mmd loss, and pairwise confusion lossimprove logging in lossesimprove loggingadd a function to load png imagesMove utils to the utils folderAdd keras-based modelsAdd a pixel wise lossAdd more logging to the predict commandsAllow architectures to provide the logits layerSave one best evaluation checkpoint by defaultAdd more logging to bob tf cache-datasetimprove logging for vat lossAdd an extra feed option to the extractorsAdd a parallel read option to dataset_from_tfrecordsimprove block extractionEPSC estimators and lossesAdd dataset_to_hdf5 commanddatasets converted to tensorflow 2.0tf20tf20Merge branch 'nose-eval-attr' into 'master'[conda] Revert BOB_NOSE_FAST hack in favour of using environment variables supported by nosetestsMerge branch 'doctest' into 'master'[sphinx] Fixed doc testUpdate meta.yamlMerge branch 'add-slow-attr' into 'master'Added @attr(slow) for slow testsIncreased latest version to 1.1.2b0 [skip ci]Increased stable version to 1.1.1v1.1.1v1.1.1[sphinx] Skipped somedoctests. The tensorflow 1.14 deprecation warnings are messing up with some doc tests and it's tricky to switch them off. Therefore, I'm skipping some doc testsAllow shuffle on epoch end in generatorMove utils to the utils folderAdd keras-based modelsAdd a pixel wise lossAdd more logging to the predict commandsAllow architectures to provide the logits layerSave one best evaluation checkpoint by default