Give CriticModel a registry-built trunk and StageModel base (gitea #57) #74

Merged

lars merged 1 commits from fix/issue-57 into master 2026-08-24 09:58:02 +02:00

Conversation 0 Commits 1 Files Changed 4

+134 -44

lars commented 2026-08-24 09:51:57 +02:00

Owner

Copy Link

Copy Source

CriticModel was the one stage-shaped class left out of the trunk-registry
(gitea #33), block-conditioning-registry (gitea #34), and StageModel-base
(gitea #39) refactors: it hand-rolled a plain ResBlock stack, so a
routed/FiLM/AdaLN trunk was available to every generative stage model except
the critic competing against them under WGAN-GP.

CriticModel now subclasses StageModel (reusing its cond_enc construction, and
a stage-2 context-fusion helper factored out of Stage2OneShot onto the base)
and builds its body via build_trunk (output width 1) instead of a bespoke
ResBlock loop, so trunk.type/trunk.block_conditioning now affect the critic
too. Each stage's critic inherits its own generator's trunk config rather
than a new critic_trunk config key, mirroring the existing
critic_hidden_dim/critic_n_res_blocks "0 = inherit from generator" pattern.
Router mixing (MoE) for the critic stays out of scope. Since CriticModel is
training-only and never persisted for inference, and WGAN-GP is still
unbenchmarked, its state_dict shape has no back-compat burden.

Co-Authored-By: Claude Sonnet 5 noreply@anthropic.com

CriticModel was the one stage-shaped class left out of the trunk-registry (gitea #33), block-conditioning-registry (gitea #34), and StageModel-base (gitea #39) refactors: it hand-rolled a plain ResBlock stack, so a routed/FiLM/AdaLN trunk was available to every generative stage model except the critic competing against them under WGAN-GP. CriticModel now subclasses StageModel (reusing its cond_enc construction, and a stage-2 context-fusion helper factored out of Stage2OneShot onto the base) and builds its body via build_trunk (output width 1) instead of a bespoke ResBlock loop, so trunk.type/trunk.block_conditioning now affect the critic too. Each stage's critic inherits its own generator's trunk config rather than a new critic_trunk config key, mirroring the existing critic_hidden_dim/critic_n_res_blocks "0 = inherit from generator" pattern. Router mixing (MoE) for the critic stays out of scope. Since CriticModel is training-only and never persisted for inference, and WGAN-GP is still unbenchmarked, its state_dict shape has no back-compat burden. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

lars added 1 commit 2026-08-24 09:51:58 +02:00

Give CriticModel a registry-built trunk and StageModel base (gitea #57) ... 4b2e0ba98e

CriticModel was the one stage-shaped class left out of the trunk-registry
(gitea #33), block-conditioning-registry (gitea #34), and StageModel-base
(gitea #39) refactors: it hand-rolled a plain ResBlock stack, so a
routed/FiLM/AdaLN trunk was available to every generative stage model except
the critic competing against them under WGAN-GP.

CriticModel now subclasses StageModel (reusing its cond_enc construction, and
a stage-2 context-fusion helper factored out of Stage2OneShot onto the base)
and builds its body via build_trunk (output width 1) instead of a bespoke
ResBlock loop, so trunk.type/trunk.block_conditioning now affect the critic
too. Each stage's critic inherits its own generator's trunk config rather
than a new critic_trunk config key, mirroring the existing
critic_hidden_dim/critic_n_res_blocks "0 = inherit from generator" pattern.
Router mixing (MoE) for the critic stays out of scope. Since CriticModel is
training-only and never persisted for inference, and WGAN-GP is still
unbenchmarked, its state_dict shape has no back-compat burden.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

lars merged commit b3f28e98af into master 2026-08-24 09:58:02 +02:00

lars deleted branch fix/issue-57 2026-08-24 09:58:08 +02:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

Clear labels

architecture

bug

Silent/wrong behavior, no crash

experiment

feature

New feature matching the v0.3 redesign

investigation

modularity

Making the network genuinely pluggable

performance

phase2

validation

wontfix

Not being fixed right now

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

lars (Lars Bogner)

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: lars/giant#74