Data & Analysis ✓ NVIDIA · Official parquetimage-embeddingnearest-neighbor-searchdata-miningvisual-changenetoptical-inspectiondockercuda

TAO AOI Image Mining

Embed target and source images with one encoder, then mine deduplicated nearest-neighbour AOI images for augmentation.

FollowSkills review · FSRS-2.0
Not recommended
45/ 100 5-point scale 2.3 / 5
Trust12 / 25 · 2.4/5

The documentation makes the container workflow, workspace data flow, GPU requirement, and Apache-2.0 licensing explicit, with NVIDIA provenance stated; however, Bash execution, root containers, whole-workspace mounting, automatic image pulls, and session/config copying are permitted without user confirmation, least-mount guidance, sensitive-data handling, or robust rollback, so points are deducted.

Reliability8 / 20 · 2.0/5

The three-step order, input/output contracts, pitfalls, and several validation hooks are reasonably clear; however, execution depends on Docker, NVIDIA Container Toolkit, CUDA, an external image, and versions.yaml plus reference files not supplied here. There are no committed key-path tests, and several failures still shift diagnosis to the user, so the static score is capped and reduced.

Adaptability8 / 15 · 2.7/5

The audience, AOI/VCN scenario, parquet requirements, filepath/label fields, outputs, and non-iterative boundary are fairly clear; however, the skill is narrow, requires Docker and a CUDA GPU, gives no explicit Chinese-language or mainland-China reachability guidance, and depends on an external NVIDIA registry, reducing environmental fit.

Convention7 / 15 · 2.3/5

The document is layered into Inputs, Setup, Method, Outputs, Common pitfalls, and Execution Order, and declares author, version, and license metadata; however, version 0.1.0 has no changelog, explicit maintenance owner, or update path, while referenced setup, troubleshooting, and invocation documents are absent from the supplied material and examples/FAQ coverage is incomplete.

Effectiveness6 / 15 · 2.0/5

The workflow defines a directly consumable mined.parquet and retains intermediate embeddings and a summary for downstream use and debugging; however, output quality depends on encoder choice, data quality, the external container, and GPU availability, with no verifiable representative output. The single-task benchmark is thin and reports only 20% Codex correctness, so effectiveness remains limited under static review.

Verifiability4 / 10 · 2.0/5

The files provide concrete commands, output layouts, validation hooks, an evaluation task, and a single benchmark report, offering limited auditability; however, there are no execution logs, CI test suite results, or independently reproducible artifacts, and benchmark coverage is minimal, so key claims remain only partially verifiable.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The container runs as root and mounts the entire workspace; manually confirm mount scope, data sensitivity, and overwrite risks before execution.
  • The workflow pulls and runs an external tao_toolkit.data_services image; lock and review the concrete image source and credential requirements in versions.yaml.
  • If label is missing, filter_by_label silently degrades to unfiltered mining; inspect logs and mining_summary.txt rather than relying on process success.
  • Core execution requires a CUDA GPU, Docker, and the NVIDIA container toolkit, with no mainland-China reachability or offline-image plan documented.
  • Automatic packaging of claude_session.jsonl and .claude configuration may expose session or environment data; review and sanitize before sharing results.
See the full review method →

What does this skill do, and when should you use it?

This skill runs the DEFT embed-then-mine workflow for VCN AOI iterations. It reads a target parquet and a source-pool parquet, embeds both with the same encoder, and retrieves nearest source images for each target. The workflow consists of three Docker invocations and produces a deduplicated mined-path parquet plus a mining summary. Docker, nvidia-container-toolkit, and a CUDA GPU are required.

Resolves the tao_toolkit.data_services image from versions.yaml and checks Docker, GPU availability, and the cached image; runs image_embeddings on the target parquet and source pool using one shared embedding_spec.yaml; runs tmm nearest_neighbors with mining_spec.yaml; applies topn, knn_metric, and optional label-aware filtering; writes two intermediate embedding parquets, a mined parquet containing unique filepath values, and mining_summary.txt.

  1. A VCN AOI engineer needs to expand a real-image augmentation queue from gap-analysis or routing output.
  2. A data scientist has target weak images and a candidate source pool and needs visually similar source images.
  3. A vision team wants to sweep topn or label-filtering settings across repeated mining runs.
  4. An engineering team needs to retain embeddings for diagnosing unrelated mining results or comparing encoder configurations.

What are this skill's strengths and limitations?

Pros
  • Provides a fixed, deterministic three-step workflow.
  • Supports runtime overrides for topn, distance metric, and label filtering.
  • Retains intermediate embeddings for reuse and encoder-level debugging.
  • Writes summary metrics including query count, neighbour count, and duplicates removed.
Limitations
  • Requires a CUDA GPU; CPU-only execution is not supported by the documented workflow.
  • Requires Docker, nvidia-container-toolkit, and the tao_toolkit.data_services image.
  • Different encoders across the two embedding steps make the embeddings non-comparable.
  • The supplied material does not document an independent test suite or cross-platform validation.

How do you install this skill?

Install the selected skill with the repository's documented skills CLI command:

npx skills add nvidia/skills --skill tao-mine-aoi-images --yes

The README does not document a standalone package or a specific manual-copy destination for this skill.

How do you use this skill?

Prepare a target parquet and source-pool parquet containing filepath, then create embedding_spec.yaml and mining_spec.yaml under the mounted workspace. Ask a loaded agent something like: “Run the tao-mine-aoi-images DEFT embedding and nearest-neighbour workflow on my VCN AOI target and source-pool parquets.” Before execution, resolve DS_IMAGE and check Docker and nvidia-smi. Run target embedding, source-pool embedding, and nearest-neighbour mining in that order. Both embedding runs must use identical encoder settings; SigLIP or CLIP embeddings should use the cosine metric.

FAQ

Can it run on a machine without an NVIDIA GPU?
No. The skill explicitly requires a CUDA GPU for both encoder inference and the cuML/cuDF k-NN search.
Can a CSV source pool be passed directly?
No. Convert it to parquet first while preserving the same columns; retain label as well if label-aware filtering is needed.
Why might the output contain cross-label pairs?
If filter_by_label=true but either embedding parquet lacks label, the container warns and proceeds without filtering.
Can mining parameters be changed per run?
Yes. Hydra overrides such as topn=10 can change topn, knn_metric, or filter_by_label without rewriting the mining specification.

More skills from this repository

All from NVIDIA/skills

Data & Analysis ✓ NVIDIA · Official

TAO VCN Sample Router

Routes visual-defect gap samples to eligible mining and synthetic-anomaly modules.

Dev & Engineering ✓ NVIDIA · Official

Holoscan SDK Setup Guide

Inspects a Linux host and selects the most suitable Holoscan SDK installation path.

Automation & Ops ✓ NVIDIA · Official

TAO NVIDIA GPU Host Setup

Checks and standardizes NVIDIA drivers, CUDA, and container runtime prerequisites for TAO GPU hosts.

Automation & Ops ✓ NVIDIA · Official

Holoscan NGC Container Installer

Install, validate, and launch NVIDIA Holoscan SDK through an NGC Docker container.

Automation & Ops ✓ NVIDIA · Official

cuOpt Installation Guide

Install and verify NVIDIA cuOpt for Python, C, or REST deployment.

Dev & Engineering ✓ NVIDIA · Official

Holoscan SDK Source Builder

Build Holoscan SDK from source in a Docker container and produce a local CMake-consumable installation tree.

Data & Analysis ✓ NVIDIA · Official

TAO ChangeNet Root Cause Analyzer

Uses image evidence to identify why NVIDIA TAO Visual ChangeNet classification experiments fail.

Data & Analysis ✓ NVIDIA · Official

TAO AutoML + DEFT Three-Phase Pipeline

Chains hyperparameter tuning, iterative data improvement, and final refinement for AOI and other DEFT applications.

Data & Analysis ✓ NVIDIA · Official

TAO DEFT AOI Improvement Loop

Automates evaluation, defect augmentation, mining, retraining, and deployment gating for PCB inspection models.

Data & Analysis ✓ NVIDIA · Official

TAO Visual ChangeNet Inspection

Train paired-image classifiers and change-segmentation models for PCB defect inspection.

Data & Analysis ✓ NVIDIA · Official

NV-Generate-MR

Generate synthetic body MRI volumes through NVIDIA’s rflow-mr workflow.

Data & Analysis ✓ NVIDIA · Official

cuPyNumeric Parallel Shard Loader

Builds processor-sized parallel loading paths from sharded on-disk data into distributed cuPyNumeric arrays.

Data & Analysis ✓ NVIDIA · Official

VSS Video Analytics Query

Read video-analytics incidents, metrics, alerts, and sensor data through VA-MCP.

Data & Analysis ✓ NVIDIA · Official

NV-Segment-CTMR Medical Image Segmentation

Run CT or MRI NIfTI segmentation and capture inspectable label-map evidence.

Data & Analysis ✓ NVIDIA · Official

Cosmos-Embed Video Retrieval & Fine-Tuning

Use Cosmos-Embed1 to embed, retrieve, deduplicate, and fine-tune video-text data.

Automation & Ops ✓ NVIDIA · Official

VSS Archive Video Search

Search archived video with natural language and ingest files or RTSP streams into a searchable index.

Data & Analysis ✓ NVIDIA · Official

TAO PyT Image Classification

Train, evaluate, optimize, and deploy PyTorch image classifiers with NVIDIA TAO.

Data & Analysis ✓ NVIDIA · Official

TAO Optical Inspection Training

Train and deploy Siamese-network models for manufacturing defect inspection.

Data & Analysis ✓ NVIDIA · Official

Synthetic Brain MRI Generator

Generate synthetic brain MRI volumes through NVIDIA’s documented workflow.

Data & Analysis ✓ NVIDIA · Official

TAO VCN Classification Gap Analysis

Find the weakest VCN classification samples and turn them into augmentation targets.

Related skills