The performance increased with time

[oOAwayOo]

Hi yoshall，

We implemented your project with our own dataset and had a problem with the test errors. We set
the n_encoder_steps and the n_decoder_steps T=τ=12 during the training phase to make predictions. Generally，when testing the model, there‘ll be an increase of test errors over the 12 test timesteps. However，the errors decreased and the 12th timestep got the least test error.

Looking forward to your reply and thank you very much.

[xiaohang96]

@oOAwayOo Hi oOAwayOo，
I have also spent some time studying this project. But I still wonder the process with our own dataset.
I can't thank you more if you could published the code processing the raw data.
thank you for patience.

[oOAwayOo]

@oOAwayOo Hi oOAwayOo，
I have also spent some time studying this project. But I still wonder the process with our own dataset.
I can't thank you more if you could published the code processing the raw data.
thank you for patience.

Hi xiaohang96，
The methods of processing data differ among datasets of different types. You could generate a dataset with two parts. One includes the observations of all nodes(sensors) at different time steps. Another includes the adjacency relations of the nodes.
Hope to help you.