gluonts.mx.model.transformer.trans_decoder 模块#

class gluonts.mx.model.transformer.trans_decoder.TransformerDecoder(decoder_length: int, config: Dict, **kwargs)[源代码]#

基类：mxnet.gluon.block.HybridBlock

cache_reset()[源代码]#
hybrid_forward(F, data: Union[mxnet.ndarray.ndarray.NDArray, mxnet.symbol.symbol.Symbol], enc_out: Union[mxnet.ndarray.ndarray.NDArray, mxnet.symbol.symbol.Symbol], mask: Optional[Union[mxnet.ndarray.ndarray.NDArray, mxnet.symbol.symbol.Symbol]] = None, is_train: bool = True) → Union[mxnet.ndarray.ndarray.NDArray, mxnet.symbol.symbol.Symbol][源代码]#

Transformer 编码器块由一个自注意力层和一个前馈层组成，中间包含预处理/后处理块。