Bug fixes * type annotations are now correctly exposed using `py.typed` (file was missing in MANIFEST) * TransformBoundsWrapper now correctly handles `data_format` (thanks zimmerrol)
3.0.0
New Features
Foolbox 3 aka Foolbox Native has been rewritten from scratch with performance in mind. All code is running natively in PyTorch, TensorFlow and JAX, and all attacks have been rewritten with real batch support.
Foolbox 3 aka Foolbox Native has been rewritten from scratch with performance in mind. All code is running natively in PyTorch, TensorFlow and JAX, and all attacks have been rewritten with real batch support.
Warning: This is a pre-release beta version. Expect breaking changes.
2.4.0
New Features
* fixed PyTorch model gradients (fixes DeepFool with batch size > 1) * added support for TensorFlow 2.0 and newer (Graph and Eager mode) * refactored the tests * support for the latest `randomgen` version
2.3.0
New Features * new `EnsembleAveragedModel` (thanks to zimmerrol) * new `foolbox.utils.flatten` * new `foolbox.utils.atleast_kd` * new `foolbox.utils.accuracy` * `PyTorchModel` now always warns if model is in train mode, not just once * batch support for `ModelWithEstimatedGradients`
Bug fixes * fixed dtype when using Adam PGD with a PyTorch model * fixed CW attack hyperparameters