def test_cheb_polynomial1():
from lib.utils import (get_adjacency_matrix,
scaled_Laplacian, cheb_polynomial)
adj = get_adjacency_matrix('data/PEMS04/distance.csv', 307)
L = scaled_Laplacian(adj)
cheb_polys = cheb_polynomial(L, 3)
assert len(cheb_polys) == 3
for i in cheb_polys:
assert i.shape == adj.shape
ScaledSAt = bool(int(
training_config['ScaledSAt'])) # whether use spatial self attention
SE = bool(int(training_config['SE'])) # whether use spatial embedding
smooth_layer_num = int(training_config['smooth_layer_num'])
aware_temporal_context = bool(int(training_config['aware_temporal_context']))
TE = bool(int(training_config['TE']))
use_LayerNorm = True
residual_connection = True
# direction = 1 means: if i connected to j, adj[i,j]=1;
# direction = 2 means: if i connected to j, then adj[i,j]=adj[j,i]=1
if direction == 2:
adj_mx, distance_mx = get_adjacency_matrix_2direction(
adj_filename, num_of_vertices, id_filename)
if direction == 1:
adj_mx, distance_mx = get_adjacency_matrix(adj_filename, num_of_vertices,
id_filename)
folder_dir = 'MAE_%s_h%dd%dw%d_layer%d_head%d_dm%d_channel%d_dir%d_drop%.2f_%.2e' % (
model_name, num_of_hours, num_of_days, num_of_weeks, num_layers, nb_head,
d_model, encoder_input_size, direction, dropout, learning_rate)
if aware_temporal_context:
folder_dir = folder_dir + 'Tcontext'
if ScaledSAt:
folder_dir = folder_dir + 'ScaledSAt'
if SE:
folder_dir = folder_dir + 'SE' + str(smooth_layer_num)
if TE:
folder_dir = folder_dir + 'TE'
print('folder_dir:', folder_dir, flush=True)
params_path = os.path.join('../experiments', dataset_name, folder_dir)
num_for_predict = 12
num_of_weeks = 2
num_of_days = 1
num_of_hours = 2
num_of_vertices = FLAGS.num_point
num_of_features = 3
merge = False
model_name = 'Gated_STGCN_%s' % f
params_dir = 'experiment_Gated_STGCN'
prediction_path = 'Gated_STGCN_prediction_0%s' % f
wdecay = 0.000
device = torch.device(FLAGS.device)
#read laplace matrix
adj = get_adjacency_matrix(adj_filename, num_nodes)
adjs = scaled_Laplacian(adj)
supports = (torch.tensor(adjs)).type(torch.float32).to(device)
print('Model is %s' % (model_name))
timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
if params_dir != "None":
params_path = os.path.join(params_dir, model_name)
else:
params_path = 'params/%s_%s/' % (model_name, timestamp)
# check parameters file
if os.path.exists(params_path) and not FLAGS.force:
raise SystemExit("Params folder exists! Select a new params path please!")
else:
def get_backbones(config_filename, adj_filename, ctx):
config = configparser.ConfigParser()
config.read(config_filename)
K = int(config['Training']['K'])
num_of_weeks = int(config['Training']['num_of_weeks'])
num_of_days = int(config['Training']['num_of_days'])
num_of_hours = int(config['Training']['num_of_hours'])
num_of_vertices = int(config['Data']['num_of_vertices'])
adj_mx = get_adjacency_matrix(adj_filename, num_of_vertices)
L_tilde = scaled_Laplacian(adj_mx)
cheb_polynomials = [
nd.array(i, ctx=ctx) for i in cheb_polynomial(L_tilde, K)
]
backbones1 = [{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": num_of_weeks,
"cheb_polynomials": cheb_polynomials
}, {
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}]
backbones2 = [{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": num_of_days,
"cheb_polynomials": cheb_polynomials
}, {
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}]
backbones3 = [{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": num_of_hours,
"cheb_polynomials": cheb_polynomials
}, {
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}]
all_backbones = [backbones1, backbones2, backbones3]
return all_backbones
def get_backbones(config_filename, adj_filename, device):
config = configparser.ConfigParser()
config.read(config_filename)
K = int(config['Training']['K'])
num_of_weeks = int(config['Training']['num_of_weeks'])
num_of_days = int(config['Training']['num_of_days'])
num_of_hours = int(config['Training']['num_of_hours'])
num_of_vertices = int(config['Data']['num_of_vertices'])
adj_mx = get_adjacency_matrix(adj_filename, num_of_vertices) #获得邻接矩阵adj_mx
L_tilde = scaled_Laplacian(adj_mx)
cheb_polynomials = torch.tensor(cheb_polynomial(L_tilde, K),
dtype=torch.float32).to(
device) #.to(device)生成新的张量
#生成最高3阶的切比雪夫多项式
backbones1 = [
{
"K": K,
"num_of_chev_filters": 64, #切比雪夫过滤器的数量
"num_of_time_filters": 64, #时间节点过滤器的数量
"time_conv_strides": num_of_weeks, #时间卷积跨步
"cheb_polynomials": cheb_polynomials
},
{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}
]
backbones2 = [{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": num_of_days,
"cheb_polynomials": cheb_polynomials
}, {
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}]
backbones3 = [{
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": num_of_hours,
"cheb_polynomials": cheb_polynomials
}, {
"K": K,
"num_of_chev_filters": 64,
"num_of_time_filters": 64,
"time_conv_strides": 1,
"cheb_polynomials": cheb_polynomials
}]
all_backbones = [backbones1, backbones2, backbones3]
return all_backbones
def test_scaled_Laplacian():
from lib.utils import get_adjacency_matrix, scaled_Laplacian
adj = get_adjacency_matrix('data/PEMS04/distance.csv', 307)
assert scaled_Laplacian(adj).shape == adj.shape
def test_get_adjacency_matrix2():
from lib.utils import get_adjacency_matrix
filename = 'data/PEMS08/distance.csv'
num_of_vertices = 170
A = get_adjacency_matrix(filename, num_of_vertices)
assert A.shape == (num_of_vertices, num_of_vertices)
