impl mtgnn
This commit is contained in:
parent
4ccb029d7e
commit
600420e8df
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: AirQuality
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 6
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 35
|
||||
steps_per_day: 24
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 35 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 6 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 6 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 6
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: BJTaxi-InFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 1024
|
||||
steps_per_day: 48
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 1024 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: BJTaxi-OutFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 1024
|
||||
steps_per_day: 48
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 1024 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: METR-LA
|
||||
device: cuda:1
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 207
|
||||
steps_per_day: 288
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 207 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: NYCBike-InFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 128
|
||||
steps_per_day: 48
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 128 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: NYCBike-OutFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 128
|
||||
steps_per_day: 48
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 128 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: PEMS-BAY
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 1
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 325
|
||||
steps_per_day: 288
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 325 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
basic:
|
||||
dataset: SolarEnergy
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: MTGNN
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
batch_size: 64
|
||||
column_wise: false
|
||||
days_per_week: 7
|
||||
horizon: 24
|
||||
input_dim: 6
|
||||
lag: 24
|
||||
normalizer: std
|
||||
num_nodes: 137
|
||||
steps_per_day: 24
|
||||
test_ratio: 0.2
|
||||
val_ratio: 0.2
|
||||
|
||||
model:
|
||||
gcn_true: True # 是否使用图卷积网络 (bool)
|
||||
buildA_true: True # 是否动态构建邻接矩阵 (bool)
|
||||
subgraph_size: 20 # 子图大小 (int)
|
||||
num_nodes: 137 # 节点数量 (int)
|
||||
node_dim: 40 # 节点嵌入维度 (int)
|
||||
dilation_exponential: 1 # 膨胀卷积指数 (int)
|
||||
conv_channels: 32 # 卷积通道数 (int)
|
||||
residual_channels: 32 # 残差通道数 (int)
|
||||
skip_channels: 64 # 跳跃连接通道数 (int)
|
||||
end_channels: 128 # 输出层通道数 (int)
|
||||
seq_len: 24 # 输入序列长度 (int)
|
||||
in_dim: 1 # 输入特征维度 (int)
|
||||
out_len: 24 # 输出序列长度 (int)
|
||||
out_dim: 1 # 输出预测维度 (int)
|
||||
layers: 3 # 模型层数 (int)
|
||||
propalpha: 0.05 # 图传播参数alpha (float)
|
||||
tanhalpha: 3 # tanh激活参数alpha (float)
|
||||
layer_norm_affline: True # 层归一化是否使用affine变换 (bool)
|
||||
gcn_depth: 2 # 图卷积深度 (int)
|
||||
dropout: 0.3 # dropout率 (float)
|
||||
predefined_A: null # 预定义邻接矩阵 (optional, None)
|
||||
static_feat: null # 静态特征 (optional, None)
|
||||
|
||||
train:
|
||||
batch_size: 64
|
||||
debug: false
|
||||
early_stop: true
|
||||
early_stop_patience: 15
|
||||
epochs: 100
|
||||
grad_norm: false
|
||||
log_step: 1000
|
||||
loss_func: mae
|
||||
lr_decay: true
|
||||
lr_decay_rate: 0.3
|
||||
lr_decay_step: 5,20,40,70
|
||||
lr_init: 0.003
|
||||
mae_thresh: None
|
||||
mape_thresh: 0.001
|
||||
max_grad_norm: 5
|
||||
output_dim: 1
|
||||
plot: false
|
||||
real_value: true
|
||||
weight_decay: 0
|
||||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: AirQuality
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 6
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: BJTaxi-InFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: BJTaxi-OutFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: METR-LA
|
||||
device: cuda:1
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: NYCBike-InFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: NYCBike-OutFlow
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -23,6 +23,7 @@ model:
|
|||
seq_len: 24
|
||||
pred_len: 24
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_model: 128
|
||||
d_ff: 2048
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: PEMS-BAY
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -24,6 +24,7 @@ model:
|
|||
pred_len: 24
|
||||
d_model: 128
|
||||
patch_len: 6
|
||||
enc_in: 1
|
||||
stride: 8
|
||||
d_ff: 2048
|
||||
dropout: 0.1
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ basic:
|
|||
dataset: SolarEnergy
|
||||
device: cuda:0
|
||||
mode: train
|
||||
model: iTransformer
|
||||
model: PatchTST
|
||||
seed: 2023
|
||||
|
||||
data:
|
||||
|
|
@ -24,6 +24,7 @@ model:
|
|||
pred_len: 24
|
||||
d_model: 128
|
||||
patch_len: 6
|
||||
enc_in: 6
|
||||
stride: 8
|
||||
d_ff: 2048
|
||||
dropout: 0.1
|
||||
|
|
|
|||
|
|
@ -3,91 +3,109 @@ from model.MTGNN.layer import *
|
|||
|
||||
|
||||
class gtnet(nn.Module):
|
||||
def __init__(self, gcn_true, buildA_true, gcn_depth, num_nodes, device, predefined_A=None, static_feat=None, dropout=0.3, subgraph_size=20, node_dim=40, dilation_exponential=1, conv_channels=32, residual_channels=32, skip_channels=64, end_channels=128, seq_length=12, in_dim=2, out_dim=12, layers=3, propalpha=0.05, tanhalpha=3, layer_norm_affline=True):
|
||||
def __init__(self, configs):
|
||||
super(gtnet, self).__init__()
|
||||
self.gcn_true = gcn_true
|
||||
self.buildA_true = buildA_true
|
||||
self.num_nodes = num_nodes
|
||||
self.dropout = dropout
|
||||
self.predefined_A = predefined_A
|
||||
self.filter_convs = nn.ModuleList()
|
||||
self.gate_convs = nn.ModuleList()
|
||||
self.residual_convs = nn.ModuleList()
|
||||
self.skip_convs = nn.ModuleList()
|
||||
self.gconv1 = nn.ModuleList()
|
||||
self.gconv2 = nn.ModuleList()
|
||||
self.norm = nn.ModuleList()
|
||||
self.start_conv = nn.Conv2d(in_channels=in_dim,
|
||||
out_channels=residual_channels,
|
||||
self.gcn_true = configs['gcn_true'] # 是否使用图卷积网络
|
||||
self.buildA_true = configs['buildA_true'] # 是否动态构建邻接矩阵
|
||||
self.num_nodes = configs['num_nodes'] # 节点数量
|
||||
self.device = configs['device'] # 设备（CPU/GPU）
|
||||
self.dropout = configs['dropout'] # dropout率
|
||||
self.predefined_A = configs.get('predefined_A', None) # 预定义邻接矩阵
|
||||
self.static_feat = configs.get('static_feat', None) # 静态特征
|
||||
self.subgraph_size = configs['subgraph_size'] # 子图大小
|
||||
self.node_dim = configs['node_dim'] # 节点嵌入维度
|
||||
self.dilation_exponential = configs['dilation_exponential'] # 膨胀卷积指数
|
||||
self.conv_channels = configs['conv_channels'] # 卷积通道数
|
||||
self.residual_channels = configs['residual_channels'] # 残差通道数
|
||||
self.skip_channels = configs['skip_channels'] # 跳跃连接通道数
|
||||
self.end_channels = configs['end_channels'] # 输出层通道数
|
||||
self.seq_length = configs['seq_len'] # 输入序列长度
|
||||
self.in_dim = configs['in_dim'] # 输入特征维度
|
||||
self.out_len = configs['out_len'] # 输出序列长度
|
||||
self.out_dim = configs['out_dim'] # 输出预测维度
|
||||
self.layers = configs['layers'] # 模型层数
|
||||
self.propalpha = configs['propalpha'] # 图传播参数alpha
|
||||
self.tanhalpha = configs['tanhalpha'] # tanh激活参数alpha
|
||||
self.layer_norm_affline = configs['layer_norm_affline'] # 层归一化是否使用affine变换
|
||||
self.gcn_depth = configs['gcn_depth'] # 图卷积深度
|
||||
self.filter_convs = nn.ModuleList() # 卷积滤波器列表
|
||||
self.gate_convs = nn.ModuleList() # 门控卷积列表
|
||||
self.residual_convs = nn.ModuleList() # 残差卷积列表
|
||||
self.skip_convs = nn.ModuleList() # 跳跃连接卷积列表
|
||||
self.gconv1 = nn.ModuleList() # 第一层图卷积列表
|
||||
self.gconv2 = nn.ModuleList() # 第二层图卷积列表
|
||||
self.norm = nn.ModuleList() # 归一化层列表
|
||||
self.start_conv = nn.Conv2d(in_channels=self.in_dim,
|
||||
out_channels=self.residual_channels,
|
||||
kernel_size=(1, 1))
|
||||
self.gc = graph_constructor(num_nodes, subgraph_size, node_dim, device, alpha=tanhalpha, static_feat=static_feat)
|
||||
self.gc = graph_constructor(self.num_nodes, self.subgraph_size, self.node_dim, self.device, alpha=self.tanhalpha, static_feat=self.static_feat)
|
||||
|
||||
self.seq_length = seq_length
|
||||
kernel_size = 7
|
||||
if dilation_exponential>1:
|
||||
self.receptive_field = int(1+(kernel_size-1)*(dilation_exponential**layers-1)/(dilation_exponential-1))
|
||||
if self.dilation_exponential>1:
|
||||
self.receptive_field = int(1+(kernel_size-1)*(self.dilation_exponential**self.layers-1)/(self.dilation_exponential-1))
|
||||
else:
|
||||
self.receptive_field = layers*(kernel_size-1) + 1
|
||||
self.receptive_field = self.layers*(kernel_size-1) + 1
|
||||
|
||||
for i in range(1):
|
||||
if dilation_exponential>1:
|
||||
rf_size_i = int(1 + i*(kernel_size-1)*(dilation_exponential**layers-1)/(dilation_exponential-1))
|
||||
if self.dilation_exponential>1:
|
||||
rf_size_i = int(1 + i*(kernel_size-1)*(self.dilation_exponential**self.layers-1)/(self.dilation_exponential-1))
|
||||
else:
|
||||
rf_size_i = i*layers*(kernel_size-1)+1
|
||||
rf_size_i = i*self.layers*(kernel_size-1)+1
|
||||
new_dilation = 1
|
||||
for j in range(1,layers+1):
|
||||
if dilation_exponential > 1:
|
||||
rf_size_j = int(rf_size_i + (kernel_size-1)*(dilation_exponential**j-1)/(dilation_exponential-1))
|
||||
for j in range(1,self.layers+1):
|
||||
if self.dilation_exponential > 1:
|
||||
rf_size_j = int(rf_size_i + (kernel_size-1)*(self.dilation_exponential**j-1)/(self.dilation_exponential-1))
|
||||
else:
|
||||
rf_size_j = rf_size_i+j*(kernel_size-1)
|
||||
|
||||
self.filter_convs.append(dilated_inception(residual_channels, conv_channels, dilation_factor=new_dilation))
|
||||
self.gate_convs.append(dilated_inception(residual_channels, conv_channels, dilation_factor=new_dilation))
|
||||
self.residual_convs.append(nn.Conv2d(in_channels=conv_channels,
|
||||
out_channels=residual_channels,
|
||||
self.filter_convs.append(dilated_inception(self.residual_channels, self.conv_channels, dilation_factor=new_dilation))
|
||||
self.gate_convs.append(dilated_inception(self.residual_channels, self.conv_channels, dilation_factor=new_dilation))
|
||||
self.residual_convs.append(nn.Conv2d(in_channels=self.conv_channels,
|
||||
out_channels=self.residual_channels,
|
||||
kernel_size=(1, 1)))
|
||||
if self.seq_length>self.receptive_field:
|
||||
self.skip_convs.append(nn.Conv2d(in_channels=conv_channels,
|
||||
out_channels=skip_channels,
|
||||
self.skip_convs.append(nn.Conv2d(in_channels=self.conv_channels,
|
||||
out_channels=self.skip_channels,
|
||||
kernel_size=(1, self.seq_length-rf_size_j+1)))
|
||||
else:
|
||||
self.skip_convs.append(nn.Conv2d(in_channels=conv_channels,
|
||||
out_channels=skip_channels,
|
||||
self.skip_convs.append(nn.Conv2d(in_channels=self.conv_channels,
|
||||
out_channels=self.skip_channels,
|
||||
kernel_size=(1, self.receptive_field-rf_size_j+1)))
|
||||
|
||||
if self.gcn_true:
|
||||
self.gconv1.append(mixprop(conv_channels, residual_channels, gcn_depth, dropout, propalpha))
|
||||
self.gconv2.append(mixprop(conv_channels, residual_channels, gcn_depth, dropout, propalpha))
|
||||
self.gconv1.append(mixprop(self.conv_channels, self.residual_channels, self.gcn_depth, self.dropout, self.propalpha))
|
||||
self.gconv2.append(mixprop(self.conv_channels, self.residual_channels, self.gcn_depth, self.dropout, self.propalpha))
|
||||
|
||||
if self.seq_length>self.receptive_field:
|
||||
self.norm.append(LayerNorm((residual_channels, num_nodes, self.seq_length - rf_size_j + 1),elementwise_affine=layer_norm_affline))
|
||||
self.norm.append(LayerNorm((self.residual_channels, self.num_nodes, self.seq_length - rf_size_j + 1),elementwise_affine=self.layer_norm_affline))
|
||||
else:
|
||||
self.norm.append(LayerNorm((residual_channels, num_nodes, self.receptive_field - rf_size_j + 1),elementwise_affine=layer_norm_affline))
|
||||
self.norm.append(LayerNorm((self.residual_channels, self.num_nodes, self.receptive_field - rf_size_j + 1),elementwise_affine=self.layer_norm_affline))
|
||||
|
||||
new_dilation *= dilation_exponential
|
||||
new_dilation *= self.dilation_exponential
|
||||
|
||||
self.layers = layers
|
||||
self.end_conv_1 = nn.Conv2d(in_channels=skip_channels,
|
||||
out_channels=end_channels,
|
||||
self.end_conv_1 = nn.Conv2d(in_channels=self.skip_channels,
|
||||
out_channels=self.end_channels,
|
||||
kernel_size=(1,1),
|
||||
bias=True)
|
||||
self.end_conv_2 = nn.Conv2d(in_channels=end_channels,
|
||||
out_channels=out_dim,
|
||||
self.end_conv_2 = nn.Conv2d(in_channels=self.end_channels,
|
||||
out_channels=self.out_len * self.out_dim,
|
||||
kernel_size=(1,1),
|
||||
bias=True)
|
||||
if self.seq_length > self.receptive_field:
|
||||
self.skip0 = nn.Conv2d(in_channels=in_dim, out_channels=skip_channels, kernel_size=(1, self.seq_length), bias=True)
|
||||
self.skipE = nn.Conv2d(in_channels=residual_channels, out_channels=skip_channels, kernel_size=(1, self.seq_length-self.receptive_field+1), bias=True)
|
||||
self.skip0 = nn.Conv2d(in_channels=self.in_dim, out_channels=self.skip_channels, kernel_size=(1, self.seq_length), bias=True)
|
||||
self.skipE = nn.Conv2d(in_channels=self.residual_channels, out_channels=self.skip_channels, kernel_size=(1, self.seq_length-self.receptive_field+1), bias=True)
|
||||
|
||||
|
||||
else:
|
||||
self.skip0 = nn.Conv2d(in_channels=in_dim, out_channels=skip_channels, kernel_size=(1, self.receptive_field), bias=True)
|
||||
self.skipE = nn.Conv2d(in_channels=residual_channels, out_channels=skip_channels, kernel_size=(1, 1), bias=True)
|
||||
self.skip0 = nn.Conv2d(in_channels=self.in_dim, out_channels=self.skip_channels, kernel_size=(1, self.receptive_field), bias=True)
|
||||
self.skipE = nn.Conv2d(in_channels=self.residual_channels, out_channels=self.skip_channels, kernel_size=(1, 1), bias=True)
|
||||
|
||||
|
||||
self.idx = torch.arange(self.num_nodes).to(device)
|
||||
self.idx = torch.arange(self.num_nodes).to(self.device)
|
||||
|
||||
|
||||
def forward(self, input, idx=None):
|
||||
input = input[..., :-2] # 去掉周期嵌入
|
||||
input = input.transpose(1, 3)
|
||||
seq_len = input.size(3)
|
||||
assert seq_len==self.seq_length, 'input sequence length not equal to preset sequence length'
|
||||
|
||||
|
|
@ -130,5 +148,8 @@ class gtnet(nn.Module):
|
|||
skip = self.skipE(x) + skip
|
||||
x = F.relu(skip)
|
||||
x = F.relu(self.end_conv_1(x))
|
||||
x = self.end_conv_2(x)
|
||||
x = self.end_conv_2(x) # [b, t*c, n, 1]
|
||||
# [b, t*c, n, 1] -> [b,t,c,n] -> [b, t, n, c]
|
||||
x = x.reshape(x.size(0), self.out_len, self.out_dim, self.num_nodes)
|
||||
x = x.permute(0, 1, 3, 2)
|
||||
return x
|
||||
|
|
@ -62,14 +62,14 @@ class Model(nn.Module):
|
|||
activation=configs['activation']
|
||||
) for l in range(configs['e_layers'])
|
||||
],
|
||||
norm_layer=nn.Sequential(Transpose(1,2), nn.BatchNorm1d(configs.d_model), Transpose(1,2))
|
||||
norm_layer=nn.Sequential(Transpose(1,2), nn.BatchNorm1d(configs['d_model']), Transpose(1,2))
|
||||
)
|
||||
|
||||
# Prediction Head
|
||||
self.head_nf = configs.d_model * \
|
||||
int((configs.seq_len - self.patch_len) / self.stride + 2)
|
||||
self.head = FlattenHead(configs.enc_in, self.head_nf, configs.pred_len,
|
||||
head_dropout=configs.dropout)
|
||||
self.head_nf = configs['d_model'] * \
|
||||
int((configs['seq_len'] - self.patch_len) / self.stride + 2)
|
||||
self.head = FlattenHead(configs['enc_in'], self.head_nf, configs['pred_len'],
|
||||
head_dropout=configs['dropout'])
|
||||
|
||||
def forecast(self, x_enc):
|
||||
# Normalization from Non-stationary Transformer
|
||||
|
|
|
|||
|
|
@ -1,5 +1,26 @@
|
|||
import torch
|
||||
import torch.nn as nn
|
||||
import math
|
||||
|
||||
class PositionalEmbedding(nn.Module):
|
||||
def __init__(self, d_model, max_len=5000):
|
||||
super(PositionalEmbedding, self).__init__()
|
||||
# Compute the positional encodings once in log space.
|
||||
pe = torch.zeros(max_len, d_model).float()
|
||||
pe.require_grad = False
|
||||
|
||||
position = torch.arange(0, max_len).float().unsqueeze(1)
|
||||
div_term = (torch.arange(0, d_model, 2).float()
|
||||
* -(math.log(10000.0) / d_model)).exp()
|
||||
|
||||
pe[:, 0::2] = torch.sin(position * div_term)
|
||||
pe[:, 1::2] = torch.cos(position * div_term)
|
||||
|
||||
pe = pe.unsqueeze(0)
|
||||
self.register_buffer('pe', pe)
|
||||
|
||||
def forward(self, x):
|
||||
return self.pe[:, :x.size(1)]
|
||||
|
||||
class PatchEmbedding(nn.Module):
|
||||
def __init__(self, d_model, patch_len, stride, padding, dropout):
|
||||
|
|
|
|||
|
|
@ -30,6 +30,7 @@ from model.ASTRA.astrav3 import ASTRA as ASTRAv3
|
|||
from model.iTransformer.iTransformer import iTransformer
|
||||
from model.HI.HI import HI
|
||||
from model.PatchTST.PatchTST import Model as PatchTST
|
||||
from model.MTGNN.MTGNN import gtnet as MTGNN
|
||||
|
||||
|
||||
|
||||
|
|
@ -99,3 +100,5 @@ def model_selector(config):
|
|||
return HI(model_config)
|
||||
case "PatchTST":
|
||||
return PatchTST(model_config)
|
||||
case "MTGNN":
|
||||
return MTGNN(model_config)
|
||||
|
|
|
|||
47
train.py
47
train.py
|
|
@ -1,10 +1,27 @@
|
|||
import yaml
|
||||
import torch
|
||||
import os
|
||||
|
||||
import utils.initializer as init
|
||||
from dataloader.loader_selector import get_dataloader
|
||||
from trainer.trainer_selector import select_trainer
|
||||
|
||||
def read_config(config_path):
|
||||
with open(config_path, "r") as file:
|
||||
config = yaml.safe_load(file)
|
||||
|
||||
# 全局配置
|
||||
device = "cuda:0" # 指定设备
|
||||
seed = 2023 # 随机种子
|
||||
epochs = 100
|
||||
|
||||
# 拷贝项
|
||||
config["basic"]["device"] = device
|
||||
config["model"]["device"] = device
|
||||
config["basic"]["seed"] = seed
|
||||
config["train"]["epochs"] = epochs
|
||||
return config
|
||||
|
||||
def run(config):
|
||||
init.init_seed(config["basic"]["seed"])
|
||||
model = init.init_model(config)
|
||||
|
|
@ -45,22 +62,26 @@ def run(config):
|
|||
|
||||
if __name__ == "__main__":
|
||||
# 指定模型
|
||||
model_list = ["PatchTST"]
|
||||
model_list = ["MTGNN"]
|
||||
# 指定数据集
|
||||
dataset_list = ["AirQuality", "SolarEnergy", "PEMS-BAY", "METR-LA", "BJTaxi-Inflow", "BJTaxi-Outflow", "NYCBike-Inflow", "NYCBike-Outflow"]
|
||||
dataset_list = ["AirQuality", "SolarEnergy", "PEMS-BAY", "METR-LA", "BJTaxi-Inflow", "BJTaxi-Outflow", "NYCBike-Inflow", "NYCBike-Outflow"]
|
||||
# dataset_list = ["AirQuality"]
|
||||
device = "cuda:0" # 指定设备
|
||||
seed = 2023 # 随机种子
|
||||
epochs = 1
|
||||
|
||||
# 我的调试开关，不做测试就填 str(False)
|
||||
os.environ["TRY"] = str(False)
|
||||
|
||||
for model in model_list:
|
||||
for dataset in dataset_list:
|
||||
config_path = f"./config/{model}/{dataset}.yaml"
|
||||
with open(config_path, "r") as file:
|
||||
config = yaml.safe_load(file)
|
||||
config["basic"]["device"] = device
|
||||
config["basic"]["seed"] = seed
|
||||
config["train"]["epochs"] = epochs
|
||||
print(f"\nRunning {model} on {dataset} with seed {seed} on {device}")
|
||||
print(f"config: {config}")
|
||||
run(config)
|
||||
# 可去这个函数里面调整统一的config项，⚠️注意调设备，epochs
|
||||
config = read_config(config_path)
|
||||
print(f"\nRunning {model} on {dataset}")
|
||||
# print(f"config: {config}")
|
||||
if os.environ.get("TRY") == "True":
|
||||
try:
|
||||
run(config)
|
||||
except Exception as e:
|
||||
pass
|
||||
else:
|
||||
run(config)
|
||||
|
||||
|
|
|
|||
|
|
@ -71,6 +71,10 @@ class Trainer:
|
|||
label = target[..., : self.args["output_dim"]]
|
||||
# 计算loss和反归一化loss
|
||||
output = self.model(data)
|
||||
# 我的调试开关
|
||||
if os.environ.get("TRY") == "True":
|
||||
print(f"[{'✅' if output.shape == label.shape else '❌'}]: output: {output.shape}, label: {label.shape}")
|
||||
assert False
|
||||
loss = self.loss(output, label)
|
||||
d_output = self.scaler.inverse_transform(output)
|
||||
d_label = self.scaler.inverse_transform(label)
|
||||
|
|
|
|||
Loading…
Reference in New Issue