skills.rest
NVIDIA-TAO
NVIDIA-TAOOFFICIAL
Explore all skills by this author →
GitHub

tao-train-image-classification

Train, evaluate, distill, quantize, export, and deploy TAO image classification models with PyTorch.

83|20|Updated Apr 16, 2026
Search Tags:#deployment#evaluation#PyTorch#training#image classification
One-click install
npx skills add https://github.com/NVIDIA-TAO/tao-skill-bank --skill tao-train-image-classification
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tao-train-image-classification
Source: https://github.com/NVIDIA-TAO/tao-skill-bank/tree/main/skills/models/tao-train-image-classification
Command: npx skills add https://github.com/NVIDIA-TAO/tao-skill-bank --skill tao-train-image-classification

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docker, nvidia-container-toolkit, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables the training, evaluation, distillation, quantization, export, and inference of TAO image classification models using PyTorch. It simplifies the workflow for developing and deploying AI-powered image classification solutions.

Core Features & Use Cases

  • Training and Evaluation: Supports training and evaluation using a wide range of backbones, including FAN, EfficientNet, ResNet, etc.
  • Distillation and Quantization: Facilitates the distillation of knowledge from a pre-trained model and quantization for deployment.
  • Deployment: Offers tools for deploying TAO image classification models using TensorRT for optimized inference.
  • Use Case: Imagine you are developing an image classification model for a medical imaging application. This Skill can help you train, evaluate, and deploy your model efficiently.

Quick Start

Use the tao-train-image-classification skill to train an image classifier with the following command:

tao-train-image-classification train

Frequently Asked Questions about tao-train-image-classification

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I train and evaluate an image classification model using PyTorch?▼

You can train and evaluate an image classification model using PyTorch by running the provided training command, which supports backbones like FAN, EfficientNet, and ResNet to simplify your workflow.

What is the best way to deploy TAO image classification models for optimized inference?▼

The best way to deploy TAO image classification models for optimized inference is by exporting them and using TensorRT, which streamlines the transition from PyTorch training to production deployment.

Do I need Docker and nvidia-container-toolkit to train TAO image classification models?▼

Yes, you need Docker and nvidia-container-toolkit installed, as these dependencies are strictly required to execute the environment for training, evaluating, and deploying TAO image classification models.

Can I distill and quantize a pre-trained image classification model before deployment?▼

Yes, you can distill knowledge from a pre-trained model and apply quantization techniques to optimize your PyTorch image classification model before final deployment.

What backbones are supported for PyTorch image classification training in TAO?▼

TAO image classification training supports a wide range of backbones including FAN, EfficientNet, and ResNet to develop and evaluate AI-powered models for various applications.

Related Skills

Explore More Software Engineering Skills→
NVIDIA-TAONVIDIA-TAO
83

tao-train-grounding-dino

Automate Grounding DINO training, evaluation, and ONNX export with PyTorch.

Official
Advanced
NITISH-gitbitNITISH-gitbit

tensorrt-llm

Optimize LLM inference on NVIDIA GPUs with TensorRT and FP8/INT4 quantization.

Community
Advanced
galeepgaleep

transformers

Load pre-trained Transformer models from the Hugging Face Hub for NLP, vision, audio, and multimodal tasks.

Community
Advanced
NVIDIA-TAONVIDIA-TAO
83

tao-train-visual-changenet

Train, evaluate, and deploy Visual ChangeNet models for PCB defect detection.

Official
Advanced