EfficientNet-B0 with stochastic depth and classifier dropout — forward, graph, faithfulness #

EfficientNetFullB0 and EfficientNetFullB0Eval state the sixteen-block net without its two regularisers; the *drop* / *do* artifacts render them. This file states both forwards WITH them, as the renderer (enetFwdChain) emits them, and proves the typed graphs denote them:

• stochastic depth (sd, the %dp<i> inputs) — a per-example scale dropPath on the residual BRANCH, before the skip add, at the nine blocks that carry a skip (b3 b5 b7 b8 b10 b11 b13 b14 b15, the renderer's enetDropIdxs [2, 4, 6, 7, 9, 10, 12, 13, 14], block-indexed);
• classifier dropout (cd, the %do input) — a per-element dropout between the GAP and the dense, width 1280 at every class count.

Each is Optional, as the renderer's sd / cd flags are: none renders no node, so one statement covers efficientnet_drop_fwd (sd only), efficientnet_do_fwd (cd only) and efficientnetin_dropdo_fwd (both), and their _eval twins at inference BatchNorm.

• efficientnetFwdGraphBFullDrop_faithful / efficientnetFwdGraphBFullEvalDrop_faithful — the graph denotes the forward, at every mask;
• efficientnetForwardBFullDrop_none / …_ones — with no site, or at the all-ones masks the driver passes at eval, the forward IS efficientnetForwardBFull (likewise the eval twins). The identity is exact: the keep probability is folded into the mask (Training/DropPath).

The residual-block-with-drop and the dropout head are text-guarded against the renderer in Codegen/FwdGraphTextTies at training BatchNorm (the eval graphs carry the three-block eval graph's SSA names, as EfficientNetFullB0Eval records). These artifacts are f32. The train steps' backward through the drop sites is outside this statement, as it is outside EfficientNetStepTieG.