Page History

...

• Added enhancements to the Gluon package, a high-level interface designed to be easy to use while keeping most of the flexibility of low level API. Gluon supports both imperative and symbolic programming, making it easy to train complex models imperatively with minimal impact on performance. Neural networks (and other machine learning models) can be defined and trained with gluon.nn and gluon.rnn packages. For Gluon tutorials, see The Straight Dope. 

• Added new loss functions - SigmoidBinaryCrossEntropyLoss, CTCLoss, HuberLoss, HingeLoss, SquaredHingeLoss, LogisticLoss, TripletLoss.

• gluon.Trainer now allows reading and setting learning rate with trainer.learning_rate property.

• Added API HybridBlock.export for exporting gluon models to MXNet format.

• Added gluon.contrib package.

  • Convolutional recurrent network cells for RNN, LSTM and GRU.
  • VariationalDropoutCell

...