Make nuScenes dataparser compatible with ParallelDataManager #2635
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dmholtz
force-pushed
the
fix/nuscenes-parser
branch
from
a405377 to
c86e210
Compare
kerrj
reviewed
Nov 29, 2023
| fx=intrinsics[:, 0, 0].detach().clone(), | ||
| fy=intrinsics[:, 1, 1].detach().clone(), | ||
| cx=intrinsics[:, 0, 2].detach().clone(), | ||
| cy=intrinsics[:, 1, 2].detach().clone(), | ||
| height=900, | ||
| width=1600, | ||
| camera_to_worlds=poses[:, :3, :4], |
There was a problem hiding this comment.
should we also do this on the transform matrices?
There was a problem hiding this comment.
No, this is not necessary, because the data in poses is not shared across multiple parameters contrary to fx, fy, cx, cy of the tensor intrinsics.
With my fix applied, ns-train nerfacto nuscenes-data --data ... --data_dir ... runs as expected.
kerrj
approved these changes
Nov 29, 2023
dmholtz
force-pushed
the
fix/nuscenes-parser
branch
from
c86e210 to
ffdc8b5
Compare
The ParallelDataManager (see nerfstudio-project#2092) makes pytorch crash if the cameras instance's fx, fy, cx or cy tensors are loaded from a common shared tensor. This PR fixes the issue by cloning the respective tensors before passing them to the Cameras(...) constructor.
dmholtz
force-pushed
the
fix/nuscenes-parser
branch
from
ffdc8b5 to
f926c99
Compare
|
When will this PR get merged? I rebased the contribution to the latest main to have a clean history. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The ParallelDataManager (see #2092) makes pytorch crash if the cameras instance's fx, fy, cx or cy tensors are loaded from a common shared tensor.
This PR fixes the issue by cloning the respective tensors before passing them to the
Cameras(...)constructor.