GTS
GTS copied to clipboard
chaoshangcs
Discrete Graph Structure Learning for Forecasting Multiple Time Series, ICLR 2021.
Hello author, I encountered the following error after executing the program 2023-08-20 13:56:10,199 - easytorch-env - INFO - Use devices 0. 2023-08-20 13:56:10,208 - easytorch-launcher - INFO - Initializing runner...
data['train_loader'] = DataLoader(data['x_train'], data['y_train'], batch_size, shuffle=True) data['val_loader'] = DataLoader(data['x_val'], data['y_val'], test_batch_size, shuffle=False) data['test_loader'] = DataLoader(data['x_test'], data['y_test'], test_batch_size, shuffle=False) Hi! Maybe there is a very small error. I think the second...
hello! I noticed that three databases are compared in the results of this article. Could you please provide the PMU data?Thanks!
Hello! I noticed that the code seems to calculate the metrics (mae, mape, rmse) for each mini-batch and then average them during the test phase. However, due to the unbalanced...
``` def encode_onehot(labels): classes = set(labels) classes_dict = {c: np.identity(len(classes))[i, :] for i, c in enumerate(classes)} labels_onehot = np.array(list(map(classes_dict.get, labels)), dtype=np.int32) return labels_onehot off_diag = np.ones([self.num_nodes, self.num_nodes]) rel_rec = np.array(encode_onehot(np.where(off_diag)[0]),...
Hello! I'm sorry to bother you.I have run the code and tried to adjust the parameters base_lr,but I found that the experimental results were quite different from the paper.The picture...
Hello, thanks for publishing your code. One thing that I have noticed is that both current config files assign the value one to the num_rnn_layers parameter, i.e., encoder and decoder...
Hi, Thank you for publishing the code. I am trying to reproduce the results for the PEMS-BAY dataset. The loss I get is larger than the one reported in the...
Metadata
Owner
Metadata
Discrete Graph Structure Learning for Forecasting Multiple Time Series, ICLR 2021.