Trilinear interpolation on a 3D regular grid.
tfg.math.interpolation.trilinear.interpolate(
grid_3d, sampling_points, name='trilinear_interpolate'
)
Args |
|---|
grid_3d
|
A tensor with shape [A1, ..., An, H, W, D, C] where H, W, D are
height, width, depth of the grid and C is the number of channels.
|
sampling_points
|
A tensor with shape [A1, ..., An, M, 3] where M is the
number of sampling points. Sampling points outside the grid are projected
in the grid borders.
|
name
|
A name for this op that defaults to "trilinear_interpolate".
|
Returns |
|---|
A tensor of shape [A1, ..., An, M, C]
|
View source on GitHub