Tags give the ability to mark specific points in history as being important
- Sort by
- Name
- Oldest updated
- Last updated
-
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
-
0.1.0 - Implemented the batch normalization - Removed the hdf5 backend
-
v0.0.1b16 Introduced the VGG16
-
v0.0.1b15 New learning rate