law accumulate_refusal_keeps

bendtorch-core@0.1.0.0 · src/autograd/gradient_LAWS.bend:130

import bendtorch-core@0.1.0.0/src/autograd/gradient_LAWS.bend as GradientLAWS
import Base
import bendtorch-core@0.1.0.0/src/shape/core.bend as Shape
import bendtorch-core@0.1.0.0/src/tensor/core.bend as Core
import bendtorch-core@0.1.0.0/src/autograd/gradient.bend as Gradient

130# Every refusal is a shape mismatch, decided before any write: the
131# contribution comes back unchanged, and so does the slot.
132law accumulate_refusal_keeps:
133  for +shape: Shape.Shape
134  for slot: Gradient.Slot
135  for contribution: Core.Dynamic
136  RefusalModel<slot, contribution, Gradient.accumulate(shape, slot, contribution)>

Uses (11)

Used by (0)

No other definition uses this definition.