NNTrainer 0.4.0 Release

We are releasing NNTrainer v0.4.0

RPM Files are for Tizen, built daily at build.tizen.org (https://build.tizen.org/package/show/Tizen:Unified/nntrainer)
and available at download.tizen.org. ( http://download.tizen.org/snapshots/tizen/unified/latest/repos/standard/packages/ )
DEB files are for Ubuntu, built and download from launchpad.net (https:://launchpad.net/~nnstreamer/+archive/ubuntu/ppa )

If you have unresoved dependencies, please download them from Ubuntu universe and nnstreamer PPA

In this release:

Fixes

• Fix Batch Normalization Bugs
• Fix Embedding Layer Bugs
• Fix Grdient Access Bugs
• Add a lot of unit tests to evaluate NNTrainer implementation
  and more.

New Features

• New Layers
  • Attention Layer
  • Eanble Weight / Tensor Sharing
  • Implement Realizer to manipulate the network graph
    • Flatten Realizer, Recurrent Realizer with in/out property, Privious Input Realizer, Attach Activation Layer Realizer
  • Support Conv1D Layer
    • Support Dilation Property
  • Support multi-label/input for model
  • Support reshape Layer
  • Support Batch normalization 1 D
  • Support LSTM Cell Layer
  • Support RNNCell Layer
  • Support GRUCell Layer
  • Support Mol Attention Layer
  • Support Multi-Head Attention Layer
  • Support Gradient Clipping by Global Norm
  • Support Reduce Mean Layer
  • Support Leaky Relu Layer
  • Support Zoneout LSTM Cell Layer
  • Support Learning Rate Scheduling
  • Improve Load/Save Model
  • Support TFLite Export (Experimental)
  • Support Positional Encoding Layer
  • Support Layer Normalization
    and more
• Provides More C/C++ APIs
• New Applications
  • Transformer Applications
    and more