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.

Deformable DETR training for 2D detection v1.0.0

Use this resource to train and deploy a 2D Deformable DETR detector with TAO

New

  • 479 downloads
  • 195 likes
  • 209 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install deformable-detr-object-training

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 evaluation, export and quantization specs, including handling of pretrained backbone or full-model weights. You get configuration files for 2D object detection.

Mostly picked by

Updated November 2, 2026

Card for the “Deformable DETR training for 2D detection” 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_export.yaml: export spec
  • references/spec_template_quantize.yaml: quantization spec
  • references/skill_info.yaml: container and action information

Good fit for

  • You want an object detector lighter than DINO
  • You must quantize a Deformable DETR for TensorRT deployment

Not for

    Tags

    • deformable detr
    • detection
    • tao
    • transformer

    About

    You say

    “Prepare the quantization spec for my trained Deformable DETR.”

    Card for the “Deformable DETR training for 2D detection” 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 and deploy a 2D Deformable DETR detector with TAO
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.1 KB
    • config/skillspector-baseline.yaml0.8 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml4.8 KB
    • references/spec_template_deploy_evaluate.yaml0.4 KB
    • references/spec_template_deploy_gen_trt_engine.yaml0.7 KB
    • references/spec_template_deploy_inference.yaml0.5 KB
    • references/spec_template_evaluate.yaml3 KB
    • references/spec_template_export.yaml3.1 KB
    • references/spec_template_gen_trt_engine.yaml3.2 KB
    • references/spec_template_inference.yaml3.1 KB
    • references/spec_template_quantize.yaml2.8 KB
    • references/spec_template_train.yaml2.8 KB
    • references/tao-deploy-deformable-detr.md5.6 KB
    • references/tao-deploy-deformable-detr.skill_info.yaml2.4 KB
    • schemas/evaluate.schema.json51.1 KB
    • schemas/export.schema.json51.7 KB
    • schemas/gen_trt_engine.schema.json56.3 KB
    • schemas/inference.schema.json52 KB
    • schemas/manifest.json15.7 KB
    • schemas/quantize.schema.json47.7 KB
    • schemas/train.schema.json47.7 KB
    • skill-card.md4.5 KB
    • SKILL.md15.3 KB
    • skill.oms.sig9.4 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-deformable-detr
    Licence
    Apache-2.0

    Notice

    « tao-train-deformable-detr » (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.