search

abduallahmohamed / Social-STGCNN

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
MIT License
483 stars 141 forks source link

Calculation of Adjacency Matrix #45

Closed RyYAO98 closed 3 years ago

RyYAO98 commented 3 years ago

Hi, thanks for your impressive work! I'm studying the implementation you released, and now there's just one issue confusing me which is related to the calculation of the adjacency matrix in utils.py. As mentioned in your paper, an element of the adjacency matrix is calculated using the observed locations of two nodes: image However, in line 45 of utils.py, it's calculated using displacement (relative position) instead of absolute position:

l2_norm = anorm(step_rel[h],step_rel[k])

Could you please explain the reason for the operation? Look forward to your reply!

abduallahmohamed commented 3 years ago

Hi,

Please refer to this: https://github.com/abduallahmohamed/Social-STGCNN/issues/15 TL:DR; the step_rel is a normalization for the trajectories. Please let me know if the previous issue isn't enough

Best

RyYAO98 commented 3 years ago

Hi,

Please refer to this: #15 TL:DR; the step_rel is a normalization for the trajectories. Please let me know if the previous issue isn't enough

Best

Thanks for your answer. It's much clear now.