-
Hello, amazin work!!
I would like to extarct BEV/3D lanes from RGB images.
Do you think it is possible to get the BEV lanes from the image plane?
That would be really helpful since I would like to …
-
Hi,
I saw that you are using the GlobalRotScaleTrans data augmentation, but why do you not scale the BEV ground truth map in the LoadBEVSegmentation class as well? Is it on purpose or did you just fo…
-
Thanks for your great work! In terms of the single frame prediction, i think the code difference between maptr and streammapnet should be the remove of point queries and the multipoint attention, is …
-
When use g.op define layer, in torch.onnx.export, we can use `None` para as input.
```
import torch
class TRT_SCA(torch.autograd.Function):
@staticmethod
def forward(ctx,
…
-
Hi,
Recently I try to train lanesegnet on my own dataset, but I find that the predictions are often wrong when the car turns a corner. Did you meet wrong prediction when the rotation change…
-
请问怎么实现输出结果->bev图的 可视化转换?
看到原仓库(不确定是否是原始作者的仓库 原作应该是[https://github.com/gigo-team/bev_lane_det]
但专利问题关闭了仓库,不确定是否使用了utils 中Visualizer这个类,但发现这个类本身是persformer项目的内容
所以来请问可视化方面的问题
请问有适配的代码吗?谢谢
-
生成bev map图时,x,y方向的坐标系是什么?
或者说 measurements里的GPS_x,GPS_y的坐标系是什么?
谢谢
-
Hi, Thanks for the great work!
Would you mind sharing some more details about the Positional Embedding part.
First, in polyline sequence representation, every polyline's corresponding coordinat…
-
` bev_embed, hs, init_reference, inter_references, global_bev = outputs
outputs_classes = []
outputs_coords = []
outputs_box_coords = []
for lvl in range(len…
-