Skip to content

fix: fix the dimension comments of t_sorted and t_indices #221

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.

Sign up for GitHub

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

Merged
liruilong940607 merged 1 commit into from
May 16, 2023
Merged

fix: fix the dimension comments of t_sorted and t_indices #221

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions nerfacc/cuda/csrc/nerfacc.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,8 @@ std::tuple<RaySegmentsSpec, RaySegmentsSpec, torch::Tensor> traverse_grids(
const torch::Tensor binaries, // [n_grids, resx, resy, resz]
const torch::Tensor aabbs, // [n_grids, 6]
// intersections
const torch::Tensor t_sorted, // [n_rays, n_grids]
const torch::Tensor t_indices, // [n_rays, n_grids]
const torch::Tensor t_sorted, // [n_rays, n_grids * 2]
const torch::Tensor t_indices, // [n_rays, n_grids * 2]
const torch::Tensor hits, // [n_rays, n_grids]
// options
const torch::Tensor near_planes,
Expand Down
12 changes: 6 additions & 6 deletions nerfacc/grid.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,8 +107,8 @@ def traverse_grids(
over_allocate: Optional[bool] = False,
rays_mask: Optional[Tensor] = None, # [n_rays]
# pre-compute intersections
t_sorted: Optional[Tensor] = None, # [n_rays, n_grids]
t_indices: Optional[Tensor] = None, # [n_rays, n_grids]
t_sorted: Optional[Tensor] = None, # [n_rays, n_grids * 2]
t_indices: Optional[Tensor] = None, # [n_rays, n_grids * 2]
hits: Optional[Tensor] = None, # [n_rays, n_grids]
) -> Tuple[RayIntervals, RaySamples, Tensor]:
"""Ray Traversal within Multiple Grids.
Expand All @@ -129,8 +129,8 @@ def traverse_grids(
traverse_steps_limit: Optional. Maximum number of samples per ray.
over_allocate: Optional. Whether to over-allocate the memory for the outputs.
rays_mask: Optional. (n_rays,) Skip some rays if given.
t_sorted: Optional. (n_rays, n_grids) Pre-computed sorted t values for each ray-grid pair. Default to None.
t_indices: Optional. (n_rays, n_grids) Pre-computed sorted t indices for each ray-grid pair. Default to None.
t_sorted: Optional. (n_rays, n_grids * 2) Pre-computed sorted t values for each ray-grid pair. Default to None.
t_indices: Optional. (n_rays, n_grids * 2) Pre-computed sorted t indices for each ray-grid pair. Default to None.
hits: Optional. (n_rays, n_grids) Pre-computed hit flags for each ray-grid pair. Default to None.

Returns:
Expand Down Expand Up @@ -171,8 +171,8 @@ def traverse_grids(
binaries.contiguous(), # [m, resx, resy, resz]
aabbs.contiguous(), # [m, 6]
# intersections
t_sorted.contiguous(), # [n_rays, m]
t_indices.contiguous(), # [n_rays, m]
t_sorted.contiguous(), # [n_rays, m * 2]
t_indices.contiguous(), # [n_rays, m * 2]
hits.contiguous(), # [n_rays, m]
# options
near_planes.contiguous(), # [n_rays]
Expand Down