整体架构如图

代码如下

lass Informer(nn.Module):def __init__(self, enc_in, dec_in, c_out, seq_len, label_len, out_len, factor=5, d_model=512, n_heads=8, e_layers=3, d_layers=2, d_ff=512, dropout=0.0, attn='prob', embed='fixed', freq='h', activation='gelu', output_attention = False, distil=True, mix=True,device=torch.device('cuda:0')):super(Informer, self).__init__()self.pred_len = out_lenself.attn = attnself.output_attention = output_attention# Encodingself.enc_embedding = DataEmbedding(enc_in, d_model, embed, freq, dropout)self.dec_embedding = DataEmbedding(dec_in, d_model, embed, freq, dropout)# AttentionAttn = ProbAttention if attn=='prob' else FullAttention# Encoderself.encoder = Encoder([EncoderLayer(AttentionLayer(Attn(False, factor, attention_dropout=dropout, output_attention=output_attention), d_model, n_heads, mix=False),d_model,d_ff,dropout=dropout,activation=activation) for l in range(e_layers)],[ConvLayer(d_model) for l in range(e_layers-1)] if distil else None,norm_layer=torch.nn.LayerNorm(d_model))# Decoderself.decoder = Decoder([DecoderLayer(AttentionLayer(Attn(True, factor, attention_dropout=dropout, output_attention=False), d_model, n_heads, mix=mix),AttentionLayer(FullAttention(False, factor, attention_dropout=dropout, output_attention=False), d_model, n_heads, mix=False),d_model,d_ff,dropout=dropout,activation=activation,)for l in range(d_layers)],norm_layer=torch.nn.LayerNorm(d_model))# self.end_conv1 = nn.Conv1d(in_channels=label_len+out_len, out_channels=out_len, kernel_size=1, bias=True)# self.end_conv2 = nn.Conv1d(in_channels=d_model, out_channels=c_out, kernel_size=1, bias=True)self.projection = nn.Linear(d_model, c_out, bias=True)def forward(self, x_enc, x_mark_enc, x_dec, x_mark_dec, enc_self_mask=None, dec_self_mask=None, dec_enc_mask=None):enc_out = self.enc_embedding(x_enc, x_mark_enc)# x_enc.shape# torch.Size([32, 96, 1])# x_mark_enc.shape# torch.Size([32, 96, 4])# enc_out.shape# torch.Size([32, 96, 512])enc_out, attns = self.encoder(enc_out, attn_mask=enc_self_mask)# enc_out.shape# torch.Size([32, 48, 512])dec_out = self.dec_embedding(x_dec, x_mark_dec)# x_dec.shape, x_mark_dec.shape# (torch.Size([32, 72, 1]), torch.Size([32, 72, 4]))# dec_out.shape# torch.Size([32, 72, 512])dec_out = self.decoder(dec_out, enc_out, x_mask=dec_self_mask, cross_mask=dec_enc_mask)# dec_out.shape# torch.Size([32, 72, 512])dec_out = self.projection(dec_out)# dec_out.shape# torch.Size([32, 72, 1])# dec_out = self.end_conv1(dec_out)# dec_out = self.end_conv2(dec_out.transpose(2,1)).transpose(1,2)if self.output_attention:return dec_out[:,-self.pred_len:,:], attnselse:return dec_out[:,-self.pred_len:,:]   # torch.Size([32, 24, 1])