Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

MAL (Mask Auto-Label) training v1.0.0

Use this resource to train MAL to produce masks from minimal annotations

New

  • 363 downloads
  • 152 likes
  • 219 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install weakly-supervised-mask-labeling

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent prepares the training, evaluation and inference specs, with the pretrained ViT-MAE weights and the AutoML notes. You get segmentation masks from a few points or boxes per image.

Mostly picked by

Updated November 2, 2026

Card for the “MAL (Mask Auto-Label) training” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec_template_train.yaml: training spec
  • references/spec_template_inference.yaml: inference spec
  • schemas/manifest.json: manifest schema

Good fit for

  • You have only a few annotations per image and want full masks
  • You want segmentation guided by bounding boxes

Not for

    Tags

    • mal
    • segmentation
    • annotation
    • tao

    About

    You say

    “Prepare MAL to produce masks from my annotation boxes.”

    Card for the “MAL (Mask Auto-Label) training” skill

    Skill published by nvidia under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to train MAL to produce masks from minimal annotations
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.1 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml3.6 KB
    • references/spec_template_evaluate.yaml1.9 KB
    • references/spec_template_inference.yaml1.9 KB
    • references/spec_template_train.yaml1.6 KB
    • schemas/evaluate.schema.json21 KB
    • schemas/inference.schema.json21 KB
    • schemas/manifest.json3.8 KB
    • schemas/train.schema.json18 KB
    • skill-card.md4.8 KB
    • SKILL.md11.3 KB
    • skill.oms.sig6.6 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-mask-auto-label
    Licence
    Apache-2.0

    Notice

    « tao-train-mask-auto-label » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.