MapTR
MapTR copied to clipboard
[ICLR'23 Spotlight & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
Thanks for your great work! When I try to train maptrv2 with vovnet99 as backbone,the grad_norm is always nan. Reducing the learning rate and applying gradient clipping are both ineffective....
Thank you for great work. Could you tell me which dataset I should prepare when I use nuScenes dataset?? Now, I'd like to try to run the evaluation script with...
In MaptrV2Head, I found that reg_branch is used in two aspects. firstly, it is used to refine referece points in the transformer decoder; another term, it is used to predict...
我想用mini数据集测试下maptr的效果,想熟悉下跑通的流程,但是遇到了一些问题 运行命令是:python -m torch.distributed.launch --nproc_per_node=1 --master_port 12345 tools/test.py 在for i, data in enumerate(data_loader):报错 EOFError: Ran out of input TypeError: cannot pickle 'dict_keys' object NOTE: Redirects are currently not supported in...
add trafficlight, is that possible?
Hi, I notice there is a bev-free version maptrv2 which achieves 49.5 mAP from table3 in the paper. How can I reproduce this work? Many thanks.
Hi, Thanks for sharing such a great job! 拜读了论文,想请教一下关于路口的拓扑信息是否在输出中包含? 再次感谢!
Dear Author, I would like to express my profound gratitude for your exceptional research, which has significantly contributed to the advancement of our work. Your willingness to share the setup...
Hello, Thank you for nice work and sharing with us! As I am working through training I encountered problem.  Training does not proceed after this point. I check the...
 the 22th instance is predicted as predestrian crossing, lane divider and road boundaries with different scores. Through a score threshold is used to select the effective target. I just...