search

cunjunyu / STAR

[ECCV 2020] Code for "Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction"
MIT License
358 stars 81 forks source link

Training batch size #20

Open zzw-zwzhang opened 2 years ago

zzw-zwzhang commented 2 years ago

The batch size is set to 1, and the prediction step equal to 1, which results in low training.

Have you tried strategies to speed up training?