Usage in different area about deepgtt

[boathit]

Not sure if it is caused by PyTorch version difference. Can you run it normally with the Harbin dataset?

[ehvid]

Thank you for your hastly reply, very appreciated.
Unfortunally, I have tried running the Harbin dataset, and it seems to work correctly, so no fault there.
On further inspection of my dataset, and the .h5 files resulting from the gentrain.jl, the 'S' (the tensorcore?) seems to have negative values, this cannot be correct, can it?

[boathit]

It should not be negative. This line is hard coded, perhaps you need to change the year value and also rename you file in the format "yy_mm_dd.h5" e.g. "15_10_03.h5".

[ehvid]

Think you for your reply. I have tried cleaning up my dataset, sorting the dataset according to timestamps, which solved the negative values. Furthermore, I have changed such that the names are foramtted as you mentioned, and are parsed correctly as month and day.

Unfortunaly, I still recieve the same error messages as previously. I was looking into the differences of the Harbin and Chengdu (DiDi) data sets, and it seems the trips of Chengdu are vastly longer, i.e. more gps-points; this should not make a difference though, should it?

[ehvid]

Also, should the tensor-core have specific dimensions?

[boathit]

It should not be a problem with high sampling rates because the preprocessing script will remove the redundant points, removereduantpoints.

Maybe you can compare the small batch of data returned by the DataLoader of the two cities.

[ehvid]

I ended up hardcoding the size of the regions I, O S and C to fit the size of the one created in the Harbin-set (zeros(Float32, 138, 148)).
I will admit, I am not sure if this will affect the final result of the trained model?

[Dreamkdd]

@ehvid Excuse me, do you have some results for deepGTT in the Chengdu DiDi dataset? I can share my code, and exchange experiences with you.

[ehvid]

@NKzhangzhiwen, sorry, unfortunately not. Out project has since ended with the end of the semester. Hope your problems are resolved.