mindspore.nn.TransformerDecoder

class mindspore.nn.TransformerDecoder(decoder_layer, num_layers, norm=None)[source]

Transformer Decoder module with multi-layer stacked of TransformerDecoderLayer, including multihead self attention, cross attention and feedforward layer.

Warning

This is an experimental API that is subject to change or deletion.

Parameters

decoder_layer (Cell) – An instance of the mindspore.nn.TransformerDecoderLayer class.
num_layers (int) – The number of decoder-layers in the decoder.
norm (Cell, optional) – The layer normalization module. Default: None.

Inputs:

tgt (Tensor): The sequence to the decoder.
memory (Tensor): The sequence from the last layer of the encoder.
tgt_mask (Tensor, optional): the mask of the tgt sequence. Default: None.
memory_mask (Tensor, optional): the mask of the memory sequence. Default: None.
tgt_key_padding_mask (Tensor, optional): the mask of the tgt keys per batch. Default: None.
memory_key_padding_mask (Tensor, optional): the mask of the memory keys per batch. Default: None.

Outputs:

Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> decoder_layer = ms.nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> transformer_decoder = ms.nn.TransformerDecoder(decoder_layer, num_layers=6)
>>> memory = ms.Tensor(np.random.rand(10, 32, 512), ms.float32)
>>> tgt = ms.Tensor(np.random.rand(20, 32, 512), ms.float32)
>>> out = transformer_decoder(tgt, memory)
>>> print(out.shape)
(20, 32, 512)