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.

Train and run a Co-DETR detector v1.0.0

Use this resource to train, evaluate or run a Co-DETR detector for 2D object detection

New

  • 430 downloads
  • 131 likes
  • 158 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install co-detr-detector-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 checks whether the codetr command is available, falls back to the Python module otherwise, then writes the spec and runs the action. The auxiliary heads only exist during training; inference uses the primary head.

Mostly picked by

Updated November 2, 2026

Card for the “Train and run a Co-DETR detector” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md : availability, actions and spec rules
  • references/checkpoint-spec-pairing.md : pairing checkpoints and specs
  • references/spec_template_inference.yaml : inference spec template

Good fit for

  • You want a highly accurate detector and accept a high inference cost
  • You want to pre-annotate detections with Co-DETR

Not for

    Tags

    • co-detr
    • object detection
    • tao
    • training
    • detector

    About

    You say

    “Train a Co-DETR detector on my image set and evaluate it.”

    Card for the “Train and run a Co-DETR detector” 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, evaluate or run a Co-DETR detector for 2D object detection
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json1.2 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/checkpoint-spec-pairing.md2.6 KB
    • references/coco80_classmap.txt0.7 KB
    • references/skill_info.yaml1.2 KB
    • references/spec_template_inference.yaml0.8 KB
    • skill-card.md4.7 KB
    • SKILL.md19 KB
    • skill.oms.sig5.7 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « tao-train-codetr » (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.