v0.15.22-p0

• Added support for AdditiveAttention layer
• Added support for use_scale and score_mode concat in Attention layer
• Fixed softmax implementation
• Fixed compiler errors with Visual Studio 2022 (C++20)
• Avoid unnecessarily compiling the TensorFlow model when loading it for conversion

v0.15.21-p0

• Added support for CategoryEncoding layer with output_mode one_hot
• Added support for Attention layer
• Fixed zero variance in a Normalization layer
• Added support for keepdims in global pooling layers

v0.15.20-p0

• Improved the performance of the Dense layer
• Fixed variance-size assertion in the Normalization layer
• Added support for new layer types:
  • ActivityRegularization
  • CategoryEncoding
  • CenterCrop
  • Cropping3D
  • Dot
  • Minimum
  • Resizing
  • ZeroPadding3D

v0.15.19-p0

• Fixes interpretation of axis value in Normalization layer (issue 357)

v0.15.18-p0

• Improved performance (with strides==(1, 1)) of Conv2D, DepthwiseConv2D, and SeparableConv2D.
• JSON export: Reduced memory usage and output.file size.

v0.15.17-p0

• Added support for the Rescaling layer.

v0.15.16-p0

• Fixed missing inline keyword.

v0.15.15-p0

• Improved performance of SeparableConv2D and DepthwiseConv2D layers

v0.15.14-p0

• improved checks and docs
• added support for FixedDropout (noop)
• added support for tensor expansion in Multiply layer

v0.15.13-p0

• Added support for Normalization layer.