v0.12.1-p0

Improved performance for LTSM and GRU.

v0.12.0-p0

Tensor shapes and positions now explicitly track the tensor's rank.

breaking changes:

• fdeep::tensor5 has been renamed to fdeep::tensor
• fdeep::tensor5_pos has been renamed to fdeep::tensor_pos
• fdeep::shape5 has been renamed to fdeep::tensor_shape
• dropped support for shape inference in reshape layers

deprecated functions (will likely be removed from the API soon)

• float_type fdeep::tensor5::get(std::size_t, std::size_t, std::size_t, std::size_t, std::size_t) const: Please use float_type fdeep::tensor5::get(const tensor_pos&) const or float_type fdeep::tensor5::get_ignore_rank(const tensor_pos&) const instead.
• void fdeep::tensor5::set(std::size_t, std::size_t, std::size_t, std::size_t, std::size_t, float_type): Please use float_type fdeep::tensor5::set(const tensor_pos, float_type) or float_type fdeep::tensor5::set_ignore_rank(const tensor_pos&, float_type) instead.

v0.11.1-p0

• Support for batch normalization on arbitrary axes
• Improved error messages

v0.11.0-p0

Switch from keras to tf.keras.

With the release of version 2.3.0, team Keras announced the following:

This is also the last major release of multi-backend Keras. Going forward, we recommend that users consider switching their Keras code to tf.keras in TensorFlow 2.0. It implements the same Keras 2.3.0 API (so switching should be as easy as changing the Keras import statements), but it has many advantages for TensorFlow users, such as support for eager execution, distribution, TPU training, and generally far better integration between low-level TensorFlow and high-level concepts like Layer and Model. It is also better maintained.

Development will focus on tf.keras going forward. We will keep maintaining multi-backend Keras over the next 6 months, but we will only be merging bug fixes. API changes will not be ported.

So frugally-deep follows this direction.

Thanks to @keithchugg for doing the needed adjustments of the stateful implementations.

v0.10.1-p0

Improved tests and docs.

v0.10.0-p0

• Support for stateful models, supporting GRU and LSTM layers. 🎉

Huge thanks to @keithchugg for the amazing work he invested in this. 🥇

v0.9.9-p0

• Fix edge-case behavior in softmax implementation

v0.9.8-p0

Fix behavior or Upsampling1D for input tensors with different ranks.

v0.9.7-p0

• Improve handling of sequential models
• Better documentation for image conversion
• New convenience function model::predict_class_with_confidence

v0.9.6-p0

• Fix concatenation of tensors with axis < rank