Lightlines
By nvidia

tao-analyze-gaps-visual-changenet

nvidia1.6k installs

Find weak samples in your TAO image classifier.

What it does

Identifies weak NVIDIA TAO VCN Classify samples, selects a decision threshold, and produces a ranked augmentation queue.

When to use it

Use when analyzing VCN classification failures, selecting augmentation targets, or auditing PASS/NO_PASS boundary cases.

How to use it

Give it inference results, a training configuration, and dataset images; it writes a ranked augmentation queue, a gap-analysis report, and spot-check images.

What you provide

  • Your files

Uses

Good to know

  • acts without asking

Latest review

What you need · 6

Requires Docker to inspect, pull, and run the data-services container.

Requires the NVIDIA container toolkit for the GPU-enabled container workflow.


Access · 3

This skill

Claude Code session transcript

Read

Copies your agent session transcript

TAO data-services

Execute

Downloads the pinned TAO container