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.

SegFormer training for semantic segmentation v1.0.0

Use this resource to train and deploy a SegFormer semantic segmentation model with TAO

New

  • 373 downloads
  • 234 likes
  • 212 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install segformer-semantic-segmentation-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 SegFormer training, evaluation, export and quantization specs, with the pretrained backbone rules and the required datasets. For TensorRT engines, it relies on the deploy templates provided with the skill.

Mostly picked by

Updated November 2, 2026

Card for the “SegFormer training for semantic segmentation” 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_export.yaml: export spec
  • references/skill_info.yaml: container and action information

Good fit for

  • You want to segment a scene with a lightweight model
  • You adapt a pretrained backbone to your own dataset

Not for

    Tags

    • segformer
    • semantic segmentation
    • transformer
    • tao

    About

    You say

    “Prepare the SegFormer training spec for my segmentation dataset.”

    Card for the “SegFormer training for semantic segmentation” 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 SegFormer semantic segmentation model with TAO
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7 KB
    • config/skillspector-baseline.yaml0.8 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml4.6 KB
    • references/spec_template_deploy_evaluate.yaml0.8 KB
    • references/spec_template_deploy_gen_trt_engine.yaml1.4 KB
    • references/spec_template_deploy_inference.yaml0.8 KB
    • references/spec_template_evaluate.yaml2.9 KB
    • references/spec_template_export.yaml3 KB
    • references/spec_template_inference.yaml2.9 KB
    • references/spec_template_quantize.yaml2.8 KB
    • references/spec_template_train.yaml2.8 KB
    • references/tao-deploy-segformer.md6.1 KB
    • references/tao-deploy-segformer.skill_info.yaml2.9 KB
    • schemas/evaluate.schema.json50 KB
    • schemas/export.schema.json51 KB
    • schemas/inference.schema.json50 KB
    • schemas/manifest.json18.2 KB
    • schemas/quantize.schema.json47.2 KB
    • schemas/train.schema.json47.2 KB
    • skill-card.md4.1 KB
    • SKILL.md14.7 KB
    • skill.oms.sig8.9 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « tao-train-segformer » (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.