Some question about the code

[Watson52]

Hi Chen, thanks for the wonderful work. I would like to ask you some questions about the code in lav_agent.py.

1. Does the npxs means the next target point about 50m away? Show as the green point in the video?
   
   

   LAV/team_code/lav_agent.py

   Line 218 in 2d00c62

   nxps = torch.tensor([-wx,-wy]).float().to(self.device)

2. In the inference phase i.e. using LAV agent, is it redundant to load the bev_model? Since I think the bev_planner (teacher) only used to generate soft labels for UniPlanner (student) to learn in the training time.
3. One of the output of the lidar_model is named pred_heatmaps, but I think the corresponding output is the center location of other vehicles. Could you explain what a heatmapis?
   

   LAV/team_code/lav_agent.py

   Lines 220 to 224 in 2d00c62

   	features, \
   	pred_heatmaps, \
   	pred_sizemaps, \
   	pred_orimaps, \
   	pred_bev = self.lidar_model([lidar_points], [len(fused_lidar)])

   
   

   LAV/lav/models/lidar.py

   Lines 34 to 44 in 2d00c62

   	def forward(self, lidars, num_points):
   	features = self.point_pillar_net(lidars, num_points)
   	features = self.backbone(features)
   	return (features,
   	self.center_head(features),
   	self.box_head(features),
   	self.ori_head(features),
   	self.seg_head(features),
   	)

[dotchen]

1. Yes
2. Absolutely correct. You can remove it from the code but you will need to add a strict=False when loading the weights.
3. pred_heatmap is the predicted Gaussian "object centerness" map. It follows the CenterNet/CenterPoint [1,2] formulation

[1] Objects as Points, Zhou et al., 2019
[2] Center-based 3D Object Detection and Tracking, Yin et al., 2021