imyyf
imyyf
https://github.com/hustvl/MapTR/blob/11307ed835dd7534ebb8927df9609f0b1b825aa6/projects/mmdet3d_plugin/maptr/assigners/maptr_assigner.py#L182 When we modify your model, we face the below error. ValueError: matrix contains invalid numeric entries We think it may be caused by cost value becomes NaN. Have you...
We find that MapTRv2 on av2 doesn't use depth supervision for LSS. From the maptrv2_av2_3d_r50_6ep.py config, we don't find loading gt_depth. So on av2 data set, MapTRv2 only uses LSS...
Will you release the MapTRv2 C+L config? We refer the MapTR C+L config and MapTRv2 C config to get a MapTRv2 C+L config. But the evaluation results are not good....
Will you release argoverse2 2d training config?
https://github.com/Mrmoore98/VectorMapNet_code/blob/4bcc8b4d6e6d61066ff0fd20484d9f5852a7a62f/configs/vectormapnet.py#L82 Hi, we find that your model using [-1.1, 0, 0.5, 1.1] as the bev_planes' presetting heights. And your former work HDMapNet using only height 0. But by our visualization,...
你好，我们在测试的时候，使用了不同的图像尺寸作为输入。但是和训练时的尺寸图像尺寸不同的时候，模型结果会差很多。请问可能的原因是什么。会不会是因为GKT的网络参数依赖于图像尺寸。
https://github.com/LeapLabTHU/DAT/issues/15 From above issue, we find that you will release a notebook. Will you release the detail of visualization? Thx.