Add keras-based models, add pixel-wise loss, other improvements

• d47eae91 Add dataset_to_hdf5 command
• cc8a142a EPSC estimators and losses
• 8e274774 improve block extraction
• b9583f15 Add a parallel read option to dataset_from_tfrecords
• a8bc6541 Add an extra feed option to the extractors
• 1c3fdb10 improve logging for vat loss
• 9058f1a8 Add more logging to bob tf cache-dataset
• e7445a23 Save one best evaluation checkpoint by default
• c82154ef Allow architectures to provide the logits layer
• 281e1c26 Add more logging to the predict commands
• ac7d3eda Add a pixel wise loss
• 2f7fec82 Add keras-based models
• c9311f9c Move utils to the utils folder
• 70e0b851 Allow shuffle on epoch end in generator
• 54a80323 add a function to load png images
• 036a308f improve logging
• e155ed50 improve logging in losses
• fa765388 add center loss, mmd loss, and pairwise confusion loss
• d957c74a make sure densenet layer names are consistent
• 63993d46 nitpick
• cda150df add starting point options to the style transfer script
• 7fabc04e Add more utils
• cb9744bc new keras models
• 38de7bdc Add GAN tools
• f6e1bb57 implement random rotate
• aece6e1b improve the generator and biogenerator classes
• 6e6addea nitpick
• b9cc5a9a handle nans in network predictions
• 27e73aec cast labels to required format
• 8082804e fix imports
• b9fd76bd Add model_summary to keras utils
• 4a714e00 add more option to reproducible
• 3241c38a Add keras version of models
• f481311f remove six dependency
• 36c3f4b9 Add a Gaussian blur filter

Sorry @tiago.pereira many changes again.

changed the description

ahha, I will do this after the release

added 27 commits

• c9311f9c...1fd8ec79 - 14 commits from branch master
• a11fe6b7 - EPSC estimators and losses
• e09de883 - Add dataset_to_hdf5 command
• ca1cb0f6 - improve block extraction
• 6599c915 - Add a parallel read option to dataset_from_tfrecords
• 15781756 - Add an extra feed option to the extractors
• 5f3e661d - improve logging for vat loss
• a434b01d - Add more logging to bob tf cache-dataset
• dc427f03 - Save one best evaluation checkpoint by default
• 84f783f1 - Allow architectures to provide the logits layer
• aa3eb646 - Add more logging to the predict commands
• 25a765d7 - Add a pixel wise loss
• d0849f10 - Add keras-based models
• 6021c7b4 - Move utils to the utils folder

Compare with previous version

added 30 commits

• b979b3d9 - Add dataset_to_hdf5 command
• cb4ffc23 - concept of readers and transforms
• c0b426f3 - cgm stuff
• 14577c16 - Adanet stuff
• 72897bea - untested architectures
• 014d092c - EPSC estimators and losses
• 3d303b08 - improve block extraction
• fbf82737 - Add a parallel read option to dataset_from_tfrecords
• 454b95f1 - Add an extra feed option to the extractors
• 3a526566 - improve logging for vat loss
• 7b1ab946 - Add more logging to bob tf cache-dataset
• 20160c06 - Save one best evaluation checkpoint by default
• 258e732d - Allow architectures to provide the logits layer
• f31081bd - Add more logging to the predict commands
• 9d9ce081 - Add a pixel wise loss
• fefec7b0 - Add keras-based models
• 29f82fe3 - Move utils to the utils folder
• 41351548 - Allow shuffle on epoch end in generator
• 5306c167 - After everything started working again with cuda 10
• 3edbd3d5 - implement random rotate
• 0adfd12f - improve the generator and biogenerator classes
• 005de8e8 - nitpick
• dd6c0b06 - handle nans in network predictions
• c4710dab - cast labels to required format
• 2ee3a4fb - fix imports
• 31cfd198 - Add model_summary to keras utils
• 06758809 - add more option to reproducible
• b501df46 - Add keras version of models
• b775bf1c - remove six dependency
• dfd6cf19 - Add a Gaussian blur filter

Compare with previous version

added 35 commits

• 4dd88c12 - Add dataset_to_hdf5 command
• cc8a142a - EPSC estimators and losses
• 857275d3 - improve block extraction
• 5328bd78 - Add a parallel read option to dataset_from_tfrecords
• ce97d05e - Add an extra feed option to the extractors
• 6c827bcc - improve logging for vat loss
• 0d0e4c63 - Add more logging to bob tf cache-dataset
• 68d6ca2f - Save one best evaluation checkpoint by default
• d46cb5c1 - Allow architectures to provide the logits layer
• 1a2392d8 - Add more logging to the predict commands
• 9d279cac - Add a pixel wise loss
• 22eabcd1 - Add keras-based models
• 6aabd230 - Move utils to the utils folder
• 70e0b851 - Allow shuffle on epoch end in generator
• 54a80323 - add a function to load png images
• 036a308f - improve logging
• e155ed50 - improve logging in losses
• fa765388 - add center loss, mmd loss, and pairwise confusion loss
• d957c74a - make sure densenet layer names are consistent
• 63993d46 - nitpick
• cda150df - add starting point options to the style transfer script
• 7fabc04e - Add more utils
• cb9744bc - new keras models
• 38de7bdc - Add GAN tools
• f6e1bb57 - implement random rotate
• aece6e1b - improve the generator and biogenerator classes
• 6e6addea - nitpick
• b9cc5a9a - handle nans in network predictions
• 27e73aec - cast labels to required format
• 8082804e - fix imports
• b9fd76bd - Add model_summary to keras utils
• 4a714e00 - add more option to reproducible
• 3241c38a - Add keras version of models
• f481311f - remove six dependency
• 36c3f4b9 - Add a Gaussian blur filter

Compare with previous version

assigned to @amohammadi and unassigned @tiago.pereira

changed the description

mentioned in issue #75 (closed)

added 2 commits

• 89e4b78b - remove extra models and improve comments
• 0c5f373a - disable slow tests for deprecated stuff

Compare with previous version

added 3 commits

• a67951e4 - disable more slow tests
• e154fba1 - Fix the biogenerator when the multiple samples is False
• 59eb6356 - update .gitignore

Compare with previous version

added 1 commit

• 25d35e2a - Fix sphinx warnings

Compare with previous version

enabled an automatic merge when the pipeline for 25d35e2a succeeds

merged

mentioned in commit 365e6379

mentioned in issue bob#259 (closed)