一条冻狗

Try Baidu Cloud: [https://pan.baidu.com/s/1Wb9E6BWCJu4wZfwxm_t4TQ#list/path=%2Fmvsnet%2Ftraining_data](DTU_training). Extraction code: s2v2

> Hi， > > I faced this problem too. My env is: ubuntu=20.0.6, python=3.7, cuda=11.1, pytorch=1.7.1. My GPU is RTX 8000. > > **Command I run was:** ./scripts/dist_test_ckpt.sh 1 ./configs/stereo/kitti_models/liga.3d-and-bev.yaml...

Same problem with nvcc 10.1, nvidia-smi 10.2, pytorch 1.6.0 + cudatoolkit 10.1, mmcvfull 1.2.1, mmdet 2.6.0 and graphic cards Tesla V100s I've worked on it for few days and still...

> 3D voxel grid with coordinates (x, y, z). Thanks for your reply! It really helps a lot. So the 3D voxel grid coordinate (x, y, z) actually means (depth,...

By the way, have you tried train & eval on max_disp = 16, surprisingly, I got results very close to that train & eval on max_disp=288, is it might caused...

> Have you solved it? I also encountered the same problem sorry, it's been a long time, i can't remember.

Same question, but i got more higher score in 3D AP R40: 27.8836, 19.3681, 15.9685(test set) with default parameters.

> > Same question, but i got more higher score in 3D AP R40: 27.8836, 19.3681, 15.9685(test set) with default parameters. > > May I ask what kind of hardware...

> I also face the same problem, I tried to apply #8. It is not working for me. Can you help on how to generate 'localattention' ? Hi, actually it...