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

PalateKit

Menu

Request a resource

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

0 / 280

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.

Training a TAO PyTorch image classifier v1.0.0

Use this resource to train, distill and export a TAO PyTorch image classifier

New

  • 533 downloads
  • 118 likes
  • 196 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install pytorch-image-classification-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 writes the training spec from typical overrides, picks the backbone and distillation settings, then guides evaluation, quantization, TensorRT export and inference. You get a classifier ready for deployment and a checked spec.

Mostly picked by

Updated November 2, 2026

Card for the “Training a TAO PyTorch image classifier” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec_template_distill.yaml: distillation template
  • references/spec_template_export.yaml: export template
  • references/skill_info.yaml: skill information

Good fit for

  • You classify images with a ResNet or EfficientNet backbone
  • You distill a large model into a smaller one for deployment

Not for

    Tags

    • classification
    • PyTorch
    • TAO
    • distillation

    About

    You say

    “Train an EfficientNet classifier on my 12 product categories and export it to TensorRT.”

    Card for the “Training a TAO PyTorch image classifier” 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, distill and export a TAO PyTorch image classifier
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.2 KB
    • config/skillspector-baseline.yaml0.8 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml7.3 KB
    • references/spec_template_deploy_evaluate.yaml0.2 KB
    • references/spec_template_deploy_gen_trt_engine.yaml0.2 KB
    • references/spec_template_deploy_inference.yaml0.2 KB
    • references/spec_template_distill.yaml3.1 KB
    • references/spec_template_evaluate.yaml3.3 KB
    • references/spec_template_export.yaml3.4 KB
    • references/spec_template_gen_trt_engine.yaml3.5 KB
    • references/spec_template_inference.yaml3.3 KB
    • references/spec_template_quantize.yaml3.1 KB
    • references/spec_template_train.yaml3.1 KB
    • references/tao-deploy-image-classification.md5.9 KB
    • references/tao-deploy-image-classification.skill_info.yaml2.5 KB
    • schemas/distill.schema.json63.9 KB
    • schemas/evaluate.schema.json67.1 KB
    • schemas/export.schema.json68.1 KB
    • schemas/gen_trt_engine.schema.json72.1 KB
    • schemas/inference.schema.json67.1 KB
    • schemas/manifest.json29.3 KB
    • schemas/quantize.schema.json64 KB
    • schemas/train.schema.json64 KB
    • skill-card.md4.3 KB
    • SKILL.md14.1 KB
    • skill.oms.sig9.9 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « tao-train-image-classification » (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.