TensorFlow Federated 0.4.0
Pre-release
Pre-release
Release 0.4.0
Major Features and Improvements
- New
tff.simulation.TransformingClientData
API and associated inifinite EMNIST dataset (see tensorflow.org/federated/api_docs/python/tff for details)
Breaking Change
- Normalized
func
tofn
across the repository (rename some parameters and functions)
Bug Fixes
- Wrapped Keras models can now be used with
tff.learning.build_federated_evaluation
- Keras models with non-trainable variables in intermediate layers (e.g. BatchNormalization) can be assigned back to Keras models with
tff.learning.ModelWeights.assign_weights_to