search

HarshayuGirase / Human-Path-Prediction

State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.
MIT License
341 stars 81 forks source link

Config of the ETH-UCY #22

Closed os1a closed 2 years ago

os1a commented 3 years ago

Hi,

Thanks for sharing the code of your great work.

Could you please share the optimal config file of the ETH-UCY. If I use a similar config file as the SDD, I am getting a lot worse results (errors are almost twice larger).

I used the same training script and pickle files provided for ETH-UCY.

Or even better, if you can share with us the pretrained model you obtain for ETH-UCY, so we can reproduce the results on this dataset.

Best, Osama

amitsunde commented 3 years ago

I have same question. Can you provide optimal config file of the ETH-UCY?

HarshayuGirase commented 3 years ago

Hi,

Unfortunately, we don’t have the exact config parameters we used. However, we were able to reproduce results and have provided notebooks to reproduce experiments for PECNET without pooling/TT (https://drive.google.com/drive/folders/1WtPEdV2aVl8ASZAk5h7fyZpa5xiRDTyv). Please see: https://github.com/HarshayuGirase/PECNet/issues/7 for more details. The main parameter to change would be data_scale. I believe the value may depend on the scene, but somewhere between 150-190 should work.

Hope this helps!

Sdabuliu commented 2 years ago

Hi,

Thanks for sharing the code of your great work.

Could you please share the optimal config file of the ETH-UCY. If I use a similar config file as the SDD, I am getting a lot worse results (errors are almost twice larger).

I used the same training script and pickle files provided for ETH-UCY.

Or even better, if you can share with us the pretrained model you obtain for ETH-UCY, so we can reproduce the results on this dataset.

Best, Osama Have you get the results reported in the paper? I have the same question,error are twice lager.