VMA
VMA copied to clipboard
hustvl
A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type
First of all, thank you for your work. You have briefly described the commands in the test phase. I have encountered a problem, I do not know which one you...
any details or script for transfering the point cloud to BEV images, like which colormap?
 Hi, in sd_driviing_line_dataset.py, if instance_class == "lane", the category of curb is 6, but the curb is six-category branch, index=[0, 1, 2, 3, 4, 5], Wouldn't this index out...
@zyc10ud Thank you for your excellent work！ I want to run demo by the following command ``` /home/wll/anaconda3/envs/vma/bin/python demo/custom_infer.py \ /home/wll/Project/VMA/demo/image_data \ projects/configs/vma_icurb.py \ ckpts/sd_line.pth \ --trajectory_sample_num 15 \ --element_type...
I am a prospective postgraduateat of a university in Wuhan , who want to conduct research based on this article. and I have diligently read your paper and project code,I...
Thank you for your excellent work. In the paper, it is mentioned that some map data needs to be manually annotated to achieve the generalization of the MapTR model. I...
