ApplyDerivativesKind

class t3toolbox.backend.fitting.ApplyDerivativesKind

Bases: _WwPpSample, ScalarOutputKind, _DerivativesKind

Symmetric directional derivatives of the all-modes apply, orders 0..order, in direction P. sample = (ww, pp). All-modes apply has no mode axis, so weight is order-only.

name = 'apply_derivatives'

Methods

precompute(frame, s)	The reusable frame sweep at frame for sample (computed once per local model).
forward(v, s, frame, sweep)	The bare Jacobian J v (no gauge).
transpose(r, s, frame, sweep)	The bare transpose J^T r, summed over the sample stack W; raw (dU, dG).
point_forward(x_cores, s)	The point operation S(x) -- what the residual is measured against.
take(sample, data, idx)	Gather a flat W subset of (sample, data) -- the default minibatch draw's layout hook.