UniformManifoldGeometryOps#
- class t3toolbox.backend.geometry.UniformManifoldGeometryOps#
Bases:
t3toolbox.backend.common.ValueHashedFieldsThe uniform manifold geometry at a fixed rank – the raw-supercore twin of
t3toolbox.uniform_manifold.UNIFORM_MANIFOLD.The uniform layer’s optimizer state is a bare
(tucker_supercore, tt_supercore)pair, so the rank structure the operations need – the modeshape, the plain-UT3masks, and the variationvar_masks– lives here instead, loop-invariant and value-hashed (docs/uniform_backend_jit_recipe.md: hold the masks as state, trace only the supercores). Build it from the point you are about to optimize withfrom_point().The uniform layer requires a minimal-rank start (
uniform_minimal()): from a non-minimal frame the retraction truncates to the realizable rank, which no longer matches the fixed masks held here.- shape: t3toolbox.backend.common.typ.Tuple[int, ...]#
- masks: t3toolbox.backend.common.typ.Tuple#
- var_masks: t3toolbox.backend.common.typ.Tuple#
- groups: t3toolbox.backend.common.typ.Tuple[t3toolbox.backend.common.typ.Tuple[int, ...], ...] = ()#
- property n_stack: int#
|C|, the frame stack rank (0 for a single tensor). The tucker edge mask is(d,) + C + (n,), so the stack is everything between.- Return type:
int
Methods#
|
The geometry at |
|
This geometry restricted to tied Tucker factors ( |
|
The orthonormal frame at |
|
The point's frame stack |
|
The bare supercore pair |
|
The per-frame SF-T3 companion when tied, |
|
The gauge projection |
|
The manifold retraction (the tied embedding + grouped SVD when shared); bare pair out. |
|
The MASKED coordinate |
|
|
|
The attachment point as a gauged tangent |