mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-02 03:42:50 +08:00
Fix some Transform3D -> Transform3d
Summary: Fix some typos in comments. Reviewed By: patricklabatut Differential Revision: D32596645 fbshipit-source-id: 09b6d8c49f4f0301b80df626c6f9a2d5b5d9b1a7
This commit is contained in:
parent
a0247ea6bd
commit
7fa333f632
@ -227,7 +227,7 @@ class CamerasBase(TensorProperties):
|
||||
eps: If eps!=None, the argument is used to clamp the
|
||||
divisor in the homogeneous normalization of the points
|
||||
transformed to the ndc space. Please see
|
||||
`transforms.Transform3D.transform_points` for details.
|
||||
`transforms.Transform3d.transform_points` for details.
|
||||
|
||||
For `CamerasBase.transform_points`, setting `eps > 0`
|
||||
stabilizes gradients since it leads to avoiding division
|
||||
@ -283,7 +283,7 @@ class CamerasBase(TensorProperties):
|
||||
eps: If eps!=None, the argument is used to clamp the
|
||||
divisor in the homogeneous normalization of the points
|
||||
transformed to the ndc space. Please see
|
||||
`transforms.Transform3D.transform_points` for details.
|
||||
`transforms.Transform3d.transform_points` for details.
|
||||
|
||||
For `CamerasBase.transform_points`, setting `eps > 0`
|
||||
stabilizes gradients since it leads to avoiding division
|
||||
@ -313,7 +313,7 @@ class CamerasBase(TensorProperties):
|
||||
eps: If eps!=None, the argument is used to clamp the
|
||||
divisor in the homogeneous normalization of the points
|
||||
transformed to the ndc space. Please see
|
||||
`transforms.Transform3D.transform_points` for details.
|
||||
`transforms.Transform3d.transform_points` for details.
|
||||
|
||||
For `CamerasBase.transform_points`, setting `eps > 0`
|
||||
stabilizes gradients since it leads to avoiding division
|
||||
|
@ -124,7 +124,7 @@ class Volumes:
|
||||
appropriate `world_coordinates` argument.
|
||||
|
||||
Internally, the mapping between `x_local` and `x_world` is represented
|
||||
as a `Transform3D` object `Volumes._local_to_world_transform`.
|
||||
as a `Transform3d` object `Volumes._local_to_world_transform`.
|
||||
Users can access the relevant transformations with the
|
||||
`Volumes.get_world_to_local_coords_transform()` and
|
||||
`Volumes.get_local_to_world_coords_transform()`
|
||||
@ -260,7 +260,7 @@ class Volumes:
|
||||
) -> Transform3d:
|
||||
"""
|
||||
Converts the `voxel_size` and `volume_translation` constructor arguments
|
||||
to the internal `Transform3D` object `local_to_world_transform`.
|
||||
to the internal `Transform3d` object `local_to_world_transform`.
|
||||
"""
|
||||
volume_size_zyx = self.get_grid_sizes().float()
|
||||
volume_size_xyz = volume_size_zyx[:, [2, 1, 0]]
|
||||
|
@ -32,7 +32,7 @@ class Transform3d:
|
||||
|
||||
BROADCASTING
|
||||
Transform3d objects supports broadcasting. Suppose that t1 and tN are
|
||||
Transform3D objects with len(t1) == 1 and len(tN) == N respectively. Then we
|
||||
Transform3d objects with len(t1) == 1 and len(tN) == N respectively. Then we
|
||||
can broadcast transforms like this:
|
||||
|
||||
.. code-block:: python
|
||||
@ -248,7 +248,7 @@ class Transform3d:
|
||||
|
||||
def inverse(self, invert_composed: bool = False):
|
||||
"""
|
||||
Returns a new Transform3D object that represents an inverse of the
|
||||
Returns a new Transform3d object that represents an inverse of the
|
||||
current transformation.
|
||||
|
||||
Args:
|
||||
@ -262,7 +262,7 @@ class Transform3d:
|
||||
independently without composing them.
|
||||
|
||||
Returns:
|
||||
A new Transform3D object containing the inverse of the original
|
||||
A new Transform3d object containing the inverse of the original
|
||||
transformation.
|
||||
"""
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user