PersFormer_3DLane

PersFormer_3DLane copied to clipboard

where is the lane vis output tensor in paper?

3

thank you for your share, but I find that the github code is not consistant with paper. such as, "Unifying anchor design in 2D and 3D. We first put curated...

zimurui

Hello，do you have your own code for car detection？

laqangela

The training code crashes

1

The training code crashes without an understandable error message: ```bash proc_id: 5 world size: 6 local_rank: 5 proc_id: 3 world size: 6 local_rank: 3 proc_id: 1 world size: 6 local_rank:...

asadnorouzi

Questions about TF

1

1. There are three coordinate systems you mention: camera_coord, vehicle_coord and ground_coord. In JSON file the "xyz" are on vehicle_coord, and the output of the model is on ground_coord, so...

nickle-fang

questions about transformations

3

0. I cannot understand the details about transformations, I think the formulation wants to get E_g2c. so, why not use 'R_gv@E' instead of 'inv(R_vg)@ E @R_vg@R_gc'? 1. which is the...

MaicsCYB

Question about benchmark

1

In OpenLane 2D Lane Detection evaluation, which value of lane width and iou threshold you took to get benchmark results? 30 & 0.5 ?

messier202

training with Apollo dataset

1

Thank you so much for your publication. I tried to training with Apollo dataset (standard group in data_splits). I got the error of no label_list. can you give me some...

BongBong87

hi boss: happened this error~

you-old

I encountered this problem when I try to train on a single Gpu, please help me,Thank you : python main_persformer.py --mod=kkk --batch_size=8 --nepochs=200 proc_id: None world size: 1 local_rank: None...

mickey-cool

Hi: I find one example of H_g2gflat: [1, 0, 0, 0] [0, 1, 0, 0] [0, 0, 0.472, 0] https://github.com/OpenPerceptionX/PersFormer_3DLane/blob/main/data/Load_Data.py#L417 but I cannot understand what's the scale(0.472) stand for Thanks!

MaicsCYB