gluonts.mx.model.transformer.trans_decoder module#
- class gluonts.mx.model.transformer.trans_decoder.TransformerDecoder(decoder_length: int, config: Dict, **kwargs)[source]#
Bases:
HybridBlock
- hybrid_forward(F, data: Union[NDArray, Symbol], enc_out: Union[NDArray, Symbol], mask: Optional[Union[NDArray, Symbol]] = None, is_train: bool = True) Union[NDArray, Symbol] [source]#
A transformer encoder block consists of a self-attention and a feed- forward layer with pre/post process blocks in between.