search

nachiket92 / PGP

Code for "Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals," CoRL 2021.
https://proceedings.mlr.press/v164/deo22a.html
MIT License
216 stars 36 forks source link

Difference spotted regarding input feature dimension different in the code and paper #29

Open jingyanliao opened 1 year ago

jingyanliao commented 1 year ago

Hi,

Thank you for your contribution. When I dive deeper into the source code, I found difference between this implementation and the paper. According to the paper, lane node feature included (x, y, theta, I_stop_line, I_ped_crossing), which has the dimension of 5. At the same time, the trajectory of agents mentioned in the paper should have the dimension of 6.

image image

However, in _get_maprepresentation in nuScenes_graphs.py, the dimension of each lane node feature shows 6. Meanwhile, the representation of each surrounding agent trajectory have dimension of 5 instead of 6. What is the reason for this change?

Thank you.

zachytong commented 1 year ago

hi, i also find it and this may be that the author adds one new dim of has_successor feature to lane_node_feats tensor, corresponding to lane_node_feats = self.add_boundary_flag(e_succ, lane_node_feats) in nuScenes_graphs.py. you might compare shape change of lane_node_feats array.