Training Evaluation

Organization

VectorSpaceLab

training-evaluation

Routes 3DDFA training recipes, loss selection, checkpoint resume, dataset layout, and benchmark evaluation.

Overview

Publisher	VectorSpaceLab
Repository	`AREX-Skill`
Skill name	`training-evaluation`
Stars	341
Forks	26
Bundled files	5
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by VectorSpaceLab on GitHub. Read the source before you install it.

Installation

Install the Training Evaluation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/3ddfa/sub-skills/training-evaluation
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/3ddfa/sub-skills/training-evaluation

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git /tmp/AREX-Skill
mkdir -p .claude/skills
cp -r /tmp/AREX-Skill/skills/repositories/repo-skills/3ddfa/sub-skills/training-evaluation .claude/skills/training-evaluation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Training Evaluation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Training Evaluation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Training Evaluation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

training-evaluation

Use this sub-skill when you need to train 3DDFA, adapt a loss recipe, validate the training data layout, resume from a checkpoint, or interpret AFLW / AFLW2000 benchmark results.

Use this route for

train.py command setup and the bundled training/*.sh recipes.
Choosing between WPDC, VDC, and PDC.
Checking filelists, param files, and the expected cropped-image layout.
Understanding checkpoint naming and resume behavior.
Running or interpreting benchmark.py, benchmark_aflw.py, and benchmark_aflw2000.py.

Do not use this route for

Inference-only or demo flows; use the python-inference route instead.
Geometry rendering / visualization outputs; use the geometry-rendering route instead.
ONNX or C++ export; use the cpp-onnx-port route instead.

Read first

references/training-and-losses.md
references/data-layout.md
references/evaluation-benchmarks.md
references/troubleshooting.md

Skill-owned script

scripts/validate_training_args.py — safe checker for training command templates, filelists, param paths, and GPU device ids.

Operating notes

Native training is CUDA-centric: train.py calls torch.cuda.set_device(...) and wraps the model with nn.DataParallel(...).cuda().
The shipped loss modules import in a CPU-only Python environment, but their forward paths still expect CUDA tensors.
--resume restores the model state dict only; optimizer state is not bundled in the saved checkpoints.
The bundled shell recipes are templates. Adjust --root, filelists, param paths, and --devices-id to your local layout before running.
If you already have predicted params, use the benchmark helper flow described in the benchmark reference rather than re-running inference.

Cross-links

For training command validation, run the skill-owned script.
For benchmark data requirements and NME meaning, read the evaluation reference.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Training Evaluation AI skill do?

Routes 3DDFA training recipes, loss selection, checkpoint resume, dataset layout, and benchmark evaluation.

Why use Training Evaluation on TypingMind?

Because you install it once and use it with any model. Training Evaluation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Training Evaluation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/3ddfa/sub-skills/training-evaluation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Training Evaluation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Training Evaluation?

As many as you like. As long as a model supports skills, you can use Training Evaluation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Training Evaluation AI skill free?

Yes. It is published on GitHub by VectorSpaceLab under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Ui Styling

nextlevelbuilder

OrganizationPopular

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user…

Landing Report

Read-only queue dashboard for workspace-aware ship. (gstack)

Gstack Openclaw Ceo Review

garrytan

CommunityPopular

Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.

Caveman Stats

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

training-evaluation

Use this route for

Do not use this route for

Read first

Skill-owned script

Operating notes

Cross-links

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now