Changes since the last release: Various tweaks to the test executables Fix bug where Softmax could only be used as the activation function in a dense layer (rather than a stand alone layer) Fix a bug in the CMake installation process where some converter scripts weren't marked as executable Remove some old converters: agile2json.py, julian2json.py, keras2json-old.p
This release adds a few minor things to python code. Nothing changes any C++ code but there are some...
What's Changed Bugfixes Fix SoftmaxGrad failure with constant dy in numba backend by @ricardoV94 i...
This is a bugfix release. It should resolve some issues some people saw where the sigmoid activation...
This release adds one bug fix to v2.7. Previously the CMake build would include the system default v...
This release fixes bugs in the CMake code CMake would build the project fine, but the project would ...
This release fixes a number of bugs: Properly handle InputLayer in Keras Sequential models (thanks ...
This is a minor update from version 2.2 Improvements: Added support for time distributed dense l...
Changes since the last release: Add (some) support for ELUs (thanks @demarley) Sequence inputs now ...
This release introduces several parameterized activation functions: The old ELU function had a hard...
Main changes since the previous release: Added the ability for Graph and LightweightGraph to return...
This release adds several new features: Inputs are read into LightweightGraph lazily. In some cases...
The main improvement in version 2.1 is that now support the Keras functional API in the Graph and Li...
This is a bugfix release which only affects networks that used ELU activation functions. Since versi...
This adds a few new features and bug fixes: Add SimpleRNN layer (thanks @laurilaatu) Add Python 3.1...
This release is a major improvement when building with CMake: CMake can automatically install Eigen...
This release adds a few minor things to python code. Nothing changes any C++ code but there are some...
What's Changed Bugfixes Fix SoftmaxGrad failure with constant dy in numba backend by @ricardoV94 i...
This is a bugfix release. It should resolve some issues some people saw where the sigmoid activation...
This release adds one bug fix to v2.7. Previously the CMake build would include the system default v...
This release fixes bugs in the CMake code CMake would build the project fine, but the project would ...
This release fixes a number of bugs: Properly handle InputLayer in Keras Sequential models (thanks ...
This is a minor update from version 2.2 Improvements: Added support for time distributed dense l...
Changes since the last release: Add (some) support for ELUs (thanks @demarley) Sequence inputs now ...
This release introduces several parameterized activation functions: The old ELU function had a hard...
Main changes since the previous release: Added the ability for Graph and LightweightGraph to return...
This release adds several new features: Inputs are read into LightweightGraph lazily. In some cases...
The main improvement in version 2.1 is that now support the Keras functional API in the Graph and Li...
This is a bugfix release which only affects networks that used ELU activation functions. Since versi...
This adds a few new features and bug fixes: Add SimpleRNN layer (thanks @laurilaatu) Add Python 3.1...
This release is a major improvement when building with CMake: CMake can automatically install Eigen...
This release adds a few minor things to python code. Nothing changes any C++ code but there are some...
What's Changed Bugfixes Fix SoftmaxGrad failure with constant dy in numba backend by @ricardoV94 i...
This is a bugfix release. It should resolve some issues some people saw where the sigmoid activation...