Tags give the ability to mark specific points in history as being important
- Sort by
- Name
- Oldest updated
- Last updated
-
v1.2.2b0 First beta [skip-ci]
-
v1.2.0Release v1.2.0
- !81 Added @attr(slow) for slow tests: bob.nightlies#55
- !82 [sphinx] Fixed doc test
- !83 Revert BOB_NOSE_FAST hack in favour of using environment variables supported by nosetests.
- !79 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
-
v1.1.0Release v1.1.0
- !72 [predict_bio] Some fixes and new features:
- [predict_bio] fix the broken checkpoint path handling
- [predict_bio] Add an option to save data in FrameContainers
- [simplecnn] fix a bug with slim architecture
- [regressor] add a name scope for train parts
- [test] organize estimator scripts tests
- [eval] improvements to bob tf eval
- !73 Improvements to eval script:
- !74 Click 7 compatibility
- !75 Add scripts for training keras models using keras API
- Add two functions to allow dynamic weighting of samples per batch
- Add several extractors which are usefull at inference time
- Add a generic Generator class alternative to BioGenerator
- Add virtual adversarial training loss
- Fix the euclidean function so that its gradients don't become nan. Also moves the bytes_to_human function
- Add a hook to add some tensors to the summary
- Add bob tf predict command
- Fix the image augmentation function
- Add dataset_to_tfrecord and dataset_from_tfrecord
- Make bob tf cache command useful
- Add a new MLP architecture
- Fixes in inception architectures
- !77 Fixed the reuse in some operations of the inception-v1:
- !78 Fix issue with VGG16 from slim. The slim models adds the hot-encoded in the architecture function
- !76 Estimators optimize loss:
-
v1.0.4Release v1.0.4
- !70 Enable mac builds: closes #65
- !71 Enabling macbuilds: Closes #68
- !69 For some reason tensorflow 1.9 changed such index from 1 to 0: I just adjusted the test case Close #64
-
!68 Several changes: * Fixes #63 moving averages are now swapped when saving to disk * Put accuracy back to train metrics * Add
bob tf cache_dataset
* Add an option tobob tf
to enable eager execution * Add a slim version of simplecnn * Add architecture details of simplecnn and patchcnn
-
0.1.10 - Easy way to train algorithms - Fixed issues #19 #20 #21 - Added more documentation
-
0.1.9 - Documented - Fixed nosetests
-
0.1.8 - Audio support
-
0.1.7 - Fixed issues with the triplet datashuffler
-
0.1.6 - Fixed issue with prefetching + triplet training
-
0.1.5 - New session management - Documenting - New tests
-
0.1.4 New session management
-
0.1.3 GPU configurations
-
0.1.2 Created the concept of normalizer