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',
data='ETTh',
activation='gelu',
device=torch.device('cuda:0')):
super(Informer, self).__init__()
self.pred_len = out_len
self.attn = attn
# Encoding
self.enc_embedding = DataEmbedding(enc_in, d_model, embed, data,
dropout)
self.dec_embedding = DataEmbedding(dec_in, d_model, embed, data,
dropout)
# Attention
Attn = ProbAttention if attn == 'prob' else FullAttention
# Encoder
self.encoder = Encoder([
EncoderLayer(AttentionLayer(
Attn(False, factor, attention_dropout=dropout), d_model,
n_heads),
d_model,
d_ff,
dropout=dropout,
activation=activation) for l in range(e_layers)
], [ConvLayer(d_model) for l in range(e_layers - 1)],
norm_layer=torch.nn.LayerNorm(d_model))
# Decoder
self.decoder = Decoder([
DecoderLayer(
AttentionLayer(
FullAttention(True, factor, attention_dropout=dropout),
d_model, n_heads),
AttentionLayer(
FullAttention(False, factor, attention_dropout=dropout),
d_model, n_heads),
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 __init__(self, vocabSize, seqLength, d_model, n_hidden, d_K, d_V,
n_layers, n_heads):
super(BERT, self).__init__()
d_ffn = n_hidden * 4
self.sourceEmbedding = nn.Embedding(vocabSize, d_model)
self.posEmbedding = nn.Embedding.from_pretrained(getSinCosEncoding(
seqLength + 1, d_model),
freeze=True)
# segment info embedding
# Define sentence A and B indices associated to 1st and 2nd sentences (see paper)
# segments_ids = [0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1]
self.segmentEmbedding = nn.Embedding(2, d_model)
self.layers = nn.ModuleList([
EncoderLayer(d_model, d_ffn, d_K, d_V, n_heads)
for _ in range(n_layers)
])
def __init__(self,
enc_in,
dec_in,
c_out,
seq_len,
out_len,
d_model=120,
n_heads=8,
e_layers=3,
d_layers=2,
d_ff=512,
dropout=0.0,
embed='fixed',
data='Ali_00',
activation='gelu',
device=torch.device('cuda:0')):
super(Model, self).__init__()
self.pred_len = out_len
self.tcn = TemporalConvNet(d_model, [d_model, d_model, d_model],
kernel_size=2,
dropout=dropout)
# Encoding
self.enc_embedding = DataEmbedding(enc_in, d_model, dropout)
self.dec_embedding = DataEmbedding(dec_in, d_model, dropout)
# Attention
Attn = FullAttention
# Encoder
self.encoder = Encoder([
EncoderLayer(AttentionLayer(Attn(False, attention_dropout=dropout),
d_model, n_heads),
d_model,
d_ff,
dropout=dropout,
activation=activation) for l in range(e_layers)
], [ConvLayer(d_model) for l in range(e_layers - 1)],
tcn_layers=self.tcn,
norm_layer=torch.nn.LayerNorm(d_model))
self.hidden = d_model * 12
self.predict = nn.Linear(self.hidden, 24, bias=None)
self.d_model = d_model
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,
device=torch.device('cuda:0')):
super(InformerStack, self).__init__()
self.pred_len = out_len
self.attn = attn
self.output_attention = output_attention
# Encoding
self.enc_embedding = DataEmbedding(enc_in, d_model, embed, freq,
dropout)
self.dec_embedding = DataEmbedding(dec_in, d_model, embed, freq,
dropout)
# Attention
Attn = ProbAttention if attn == 'prob' else FullAttention
# Encoder
stacks = list(range(e_layers, 2, -1)) # you can customize here
encoders = [
Encoder([
EncoderLayer(AttentionLayer(
Attn(False,
factor,
attention_dropout=dropout,
output_attention=output_attention), d_model, n_heads),
d_model,
d_ff,
dropout=dropout,
activation=activation) for l in range(el)
], [ConvLayer(d_model) for l in range(el - 1)] if distil else None,
norm_layer=torch.nn.LayerNorm(d_model)) for el in stacks
]
self.encoder = EncoderStack(encoders)
# Decoder
self.decoder = Decoder([
DecoderLayer(
AttentionLayer(
FullAttention(True,
factor,
attention_dropout=dropout,
output_attention=False), d_model, n_heads),
AttentionLayer(
FullAttention(False,
factor,
attention_dropout=dropout,
output_attention=False), d_model, n_heads),
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 __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,
device=torch.device('cuda:0'),
decoder_case=0):
super(Informer, self).__init__()
self.pred_len = out_len
self.attn = attn
self.output_attention = output_attention
# Encoding
self.enc_embedding = DataEmbedding(enc_in, d_model, embed, freq,
dropout)
self.dec_embedding = DataEmbedding(dec_in, d_model, embed, freq,
dropout)
# Attention
Attn = ProbAttention if attn == 'prob' else FullAttention
InterpretableAttn = InterpretableProbAttention if attn == 'intprob' else InterpretableFullAttention
# Encoder
self.encoder = Encoder(
[
EncoderLayer(
# PZ
# AttentionLayer(Attn(False, factor, attention_dropout=dropout, output_attention=output_attention),
# d_model, n_heads),
InterpretableAttentionLayer(
InterpretableAttn(False,
factor,
attention_dropout=dropout,
output_attention=output_attention),
d_model, n_heads) if attn == 'intprob'
or attn == 'intfull' else AttentionLayer(
Attn(False,
factor,
attention_dropout=dropout,
output_attention=output_attention), d_model,
n_heads),
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))
# Decoder
self.decoder = Decoder(
[
DecoderLayer(
# PZ
# AttentionLayer(Attn(True, factor, attention_dropout=dropout, output_attention=False),
# d_model, n_heads),
InterpretableAttentionLayer(
InterpretableAttn(True,
factor,
attention_dropout=dropout,
output_attention=output_attention),
d_model, n_heads) if attn == 'intprob'
or attn == 'intfull' else AttentionLayer(
Attn(True,
factor,
attention_dropout=dropout,
output_attention=output_attention), d_model,
n_heads),
AttentionLayer(
FullAttention(False,
factor,
attention_dropout=dropout,
output_attention=False), d_model,
n_heads),
d_model,
self.pred_len, # pred_len
d_ff=d_ff,
dropout=dropout,
activation=activation,
case=decoder_case) 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 __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',
data='ETTh1',
freq='h',
activation='gelu',
output_attention=False,
distil=True,
device=torch.device('cuda')):
super(Informer, self).__init__()
self.pred_len = out_len
self.attn = attn
self.output_attention = output_attention
self.e_layers = e_layers
self.d_layers = d_layers
# Encoding
self.enc_embedding = DataEmbedding(enc_in, seq_len, d_model, embed,
freq, dropout, data)
self.dec_embedding = DataEmbedding(dec_in, label_len + out_len,
d_model, embed, freq, dropout, data)
# Attention
Attn = ProbAttention if attn == 'prob' else FullAttention
# Encoder
if e_layers > 0:
self.encoder = Encoder(
[
EncoderLayer(
AttentionLayer(Attn(False, factor,
attention_dropout=dropout,
output_attention=output_attention),
d_model, n_heads),
d_model,
d_ff,
dropout=dropout,
activation=activation
# stacking multiple layers
) for l in range(e_layers)
],
[
ConvLayer(
d_model
# stacking multiple layers
) for l in range(e_layers-1)
] if distil else None,
norm_layer=torch.nn.LayerNorm(d_model)
) if attn == 'prob' else \
nn.TransformerEncoder(nn.TransformerEncoderLayer(d_model, n_heads, d_ff, dropout, activation), num_layers=e_layers, norm=nn.LayerNorm(d_model))
else:
self.encoder = nn.Identity()
# Decoder
if d_layers > 0:
self.decoder = Decoder(
[
DecoderLayer(
AttentionLayer(ProbAttention(True, factor,
attention_dropout=dropout,
output_attention=False),
d_model, n_heads),
AttentionLayer(FullAttention(False, factor,
attention_dropout=dropout,
output_attention=False),
d_model, n_heads),
d_model,
d_ff,
dropout=dropout,
activation=activation,
)
for l in range(d_layers)
],
norm_layer=torch.nn.LayerNorm(d_model)
) if attn == 'prob' else \
nn.TransformerDecoder(nn.TransformerDecoderLayer(d_model, n_heads, d_ff, dropout, activation), num_layers=d_layers, norm=nn.LayerNorm(d_model))
else:
self.decoder = nn.Identity()
# 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)
