THU-DA-6D-Pose-Group / Self6D-Diff-Renderer

The differentiable rendering code for "Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV 2020, oral)"
Apache License 2.0
104 stars 15 forks source link

too many indics #11

Open Cmnotjx opened 2 years ago

Cmnotjx commented 2 years ago

Do U have the problem that : too many indics in tensor of DIM 1???/

tan-tao11 commented 2 years ago

Hi! I met the same problem. Have U solved it?

wangg12 commented 1 year ago

Please give more details.

sunhan1997 commented 1 year ago

hello, many people meet this problem, can you solve it?

_Warning: unable to import datasets/nusc: No module named 'nuscenes' Traceback (most recent call last): File "/home/sunh/6D_ws/other_code/Self6D-Diff-Renderer-master/kaolin/kaolin/datasets/init.py", line 11, in from .nusc import NuscDetection File "/home/sunh/6D_ws/other_code/Self6D-Diff-Renderer-master/kaolin/kaolin/datasets/nusc.py", line 21, in from nuscenes.utils.geometry_utils import transform_matrix ModuleNotFoundError: No module named 'nuscenes' Warning: unable to import datasets/nusc: None 0%| | 0/13 [00:00<?, ?it/s] Traceback (most recent call last): File "tests/test_dib_render_LM_batch_depth.py", line 153, in main() File "tests/test_dib_render_LM_batch_depth.py", line 112, in main models = load_objs(obj_paths, texture_paths, height=HEIGHT, width=WIDTH) File "/home/sunh/6D_ws/other_code/Self6D-Diff-Renderer-master/tests/../core/dr_utils/dr_utils.py", line 42, in loadobjs vertices = mesh.vertices[:, :3] # x,y,z IndexError: too many indices for tensor of dimension 1