Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Encounter error during preprocessing of DAVIS/schoolgirls scene #54

Closed
Yuhuoo opened this issue Oct 17, 2024 · 4 comments
Closed

Encounter error during preprocessing of DAVIS/schoolgirls scene #54

Yuhuoo opened this issue Oct 17, 2024 · 4 comments

Comments

@Yuhuoo
Copy link

Yuhuoo commented Oct 17, 2024

Hi, thanks for your nice work. When I preprocessed the scene of DAVIS/schoolgirls, I encountered an error. Here is the error log.

(som) ga@test-4U-GPU-Server:~/code/shape-of-motion/preproc$ python process_custom.py --img-dirs /home/ga/code/shape-of-motion/datasets/custom/images/schoolgirls/ --gpus 0 2

found 150 files in /home/ga/code/shape-of-motion/datasets/custom/unidepth_disp/schoolgirls, found /home/ga/code/shape-of-motion/datasets/custom/unidepth_intrins/schoolgirls.json, skipping
CUDA_VISIBLE_DEVICES=0 python compute_depth.py --img_dir /home/ga/code/shape-of-motion/datasets/custom/images/schoolgirls --out_raw_dir /home/ga/code/shape-of-motion/datasets/custom/depth_anything/schoolgirls --out_aligned_dir /home/ga/code/shape-of-motion/datasets/custom/aligned_depth_anything/schoolgirls --model depth-anything --metric_dir /home/ga/code/shape-of-motion/datasets/custom/unidepth_disp/schoolgirls
Raw depth-anything depth maps already computed for /home/ga/code/shape-of-motion/datasets/custom/images/schoolgirls
Aligning monodepth in /home/ga/code/shape-of-motion/datasets/custom/depth_anything/schoolgirls with metric depth in /home/ga/code/shape-of-motion/datasets/custom/unidepth_disp/schoolgirls
Founds 150 files in /home/ga/code/shape-of-motion/datasets/custom/aligned_depth_anything/schoolgirls, skipping
CUDA_VISIBLE_DEVICES=0 python recon_with_depth.py --img_dir /home/ga/code/shape-of-motion/datasets/custom/images/schoolgirls --calib /home/ga/code/shape-of-motion/datasets/custom/unidepth_intrins/schoolgirls.json --depth_dir /home/ga/code/shape-of-motion/datasets/custom/aligned_depth_anything/schoolgirls --out_path /home/ga/code/shape-of-motion/datasets/custom/droid_recon/schoolgirls
0it [00:00, ?it/s]checkpoints/droid.pth
/home/ga/software/anaconda3/envs/som/lib/python3.10/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
150it [00:03, 40.63it/s]
################################
Traceback (most recent call last):
File "/data/Gaoao/code/shape-of-motion/preproc/recon_with_depth.py", line 265, in
traj_est = droid.terminate(image_stream(args.img_dir, args.calib, args.stride))
File "/data/Gaoao/code/shape-of-motion/preproc/DROID-SLAM/droid_slam/droid.py", line 81, in terminate
self.backend(7)
File "/home/ga/software/anaconda3/envs/som/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/data/Gaoao/code/shape-of-motion/preproc/DROID-SLAM/droid_slam/droid_backend.py", line 34, in call
graph.add_proximity_factors(rad=self.backend_radius,
File "/data/Gaoao/code/shape-of-motion/preproc/DROID-SLAM/droid_slam/factor_graph.py", line 374, in add_proximity_factors
ii, jj = torch.as_tensor(es, device=self.device).unbind(dim=-1)
ValueError: not enough values to unpack (expected 2, got 0)

Can you help me?

@Yuhuoo Yuhuoo closed this as completed Oct 17, 2024
@YuyangYin
Copy link

So how to solve it? I meet the same problem.

@yingxuanyou
Copy link

I encounter the same problem, how do you solve it?

@yingxuanyou
Copy link

I encounter the same problem, how do you solve it?

I referred to this (princeton-vl/DROID-SLAM#115 (comment)) and solved the problem. Holp it can help you.

@YuyangYin
Copy link

YuyangYin commented Nov 18, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants