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

May I ask what the problem? #32

Open
309020726 opened this issue Dec 7, 2023 · 1 comment
Open

May I ask what the problem? #32

309020726 opened this issue Dec 7, 2023 · 1 comment

Comments

@309020726
Copy link

During the process of running "tracking_ours", the following prompt will appear:
...Endo-Depth-and-Motion-main/edam/utils/LineMesh.py:25: RuntimeWarning: invalid value encountered in divide
axis_ = axis_ / np.linalg.norm(axis_)

The first 23 frames are normal, but this warning appears from frame 24 onwards, but it can still run. Just at this point, the point cloud of the 3D visualization window suddenly becomes very small.
And there is also a warning prompt during volume reconstruction. The reconstructed result is only a plane, and no three-dimensional information can be seen.

May I ask how to solve this problem? I attempted to make the following modifications to the code:
if np.linalg.norm(axis_) != 0:
axis_ = axis_ / np.linalg.norm(axis_)
else:
axis_ = np.array([0, 0, 1])

Looking forward to your reply and assistance.

@309020726
Copy link
Author

This is rebuilding one's own dataset. Due to the incorrect results of the first step of generating depth maps in your code (not to say that your part was not done well, it's just that I don't know how to modify it to match my own dataset), I used other methods to generate depth maps, and then used the tracking and reconstruction later in your code, resulting in the above phenomenon.
The modifications I made mentioned above did not have any effect, so I am seeking your advice and help, hoping to gain some insights.
It would be even better if you could also know how to train your dataset with this code to obtain depth maps.
Thank you for your patient reading and assistance. I would greatly appreciate it.

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

1 participant