界面已本地化;技能介绍与说明文档按所选语言由 AI 自动翻译,代码、命令、路径和专业术语保留原文,以原作者文档为准。
探索技能
效率与协作 · SKILL.md

rectified_ode_reflow

rectified_ode_reflow

【效率与协作】Simulate rectified-flow Euler transport and compute straightness, reflow, and convex transport diagnostics.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准

技能说明

GitHub

name: rectified_ode_reflow description: Simulate rectified-flow Euler transport and compute straightness, reflow, and convex transport diagnostics.

Rectified ODE Reflow

Use this skill when a learned rectified-flow velocity field must be integrated or audited for straightness. Do not use it to fit the velocity field.

Inputs

  • Initial samples z0.
  • Affine velocity parameters compatible with rectified_velocity_regression.
  • Euler step count.

Outputs

  • Final transported samples.
  • Path length and direct endpoint distance.
  • Straightness ratio and squared transport cost.

Workflow

  1. Integrate z <- z + dt * v(z,t) using Euler steps.
  2. Accumulate segment lengths for each sample.
  3. Compare accumulated path length with direct endpoint distance.
  4. Report one-step and multi-step diagnostics for reduced recovery.

Validation

Run python tests/test_ode.py or the Distiller validator with tests enabled.

Limitations

The script checks the ODE/reflow mechanism on numeric vectors. Full image quality metrics require a separate heavy runtime that is outside this bounded reduced recovery.

我的收藏