本文主要是介绍深度学习算法informer（时序预测）（四）（Decoder），希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
一、DecoderLayer架构如图（不改变输入形状）
二、Decoder整体
包括两部分
1. 多层DecoderLayer
2. 层归一化
代码如下
class DecoderLayer(nn.Module):def __init__(self, self_attention, cross_attention, d_model, d_ff=None,dropout=0.1, activation="relu"):super(DecoderLayer, self).__init__()d_ff = d_ff or 4*d_modelself.self_attention = self_attentionself.cross_attention = cross_attentionself.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)self.norm1 = nn.LayerNorm(d_model)self.norm2 = nn.LayerNorm(d_model)self.norm3 = nn.LayerNorm(d_model)self.dropout = nn.Dropout(dropout)self.activation = F.relu if activation == "relu" else F.geludef forward(self, x, cross, x_mask=None, cross_mask=None):x = x + self.dropout(self.self_attention(x, x, x,attn_mask=x_mask)[0])x = self.norm1(x)x = x + self.dropout(self.cross_attention(x, cross, cross,attn_mask=cross_mask)[0])y = x = self.norm2(x)y = self.dropout(self.activation(self.conv1(y.transpose(-1,1))))y = self.dropout(self.conv2(y).transpose(-1,1))return self.norm3(x+y)class Decoder(nn.Module):def __init__(self, layers, norm_layer=None):super(Decoder, self).__init__()self.layers = nn.ModuleList(layers)self.norm = norm_layerdef forward(self, x, cross, x_mask=None, cross_mask=None):for layer in self.layers:x = layer(x, cross, x_mask=x_mask, cross_mask=cross_mask)if self.norm is not None:x = self.norm(x)return x这篇关于深度学习算法informer（时序预测）（四）（Decoder）的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
