跳到主内容
智客 ZICQ

技能库 智客分类:运维与云 tao-analyze-gaps-visual-changenet

Tao Analyze Gaps Visual Changenet

对NVIDIA TAO VCN分类(视觉元件网)实验进行差距分析,直接通过“docker run... ship_analysis vcn_aoi.”使用被钉住的TAO数据服务容器,选择最佳决定阈值,对每个样本的弱点进行排名,并为下游扩能而释放出一个上-K最弱的薄板。 分析 VCN 分类失败时使用,选择 SDA 增强目标,或审计 PASS/NO_PASS 边界例.

1609 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

对NVIDIA TAO VCN分类(Visual Confession Net)实验进行差距分析,直接通过"docker run"来引用被绑定的TAO数据服务容器. 差距_分析 vcn_aoi. – 选择最佳决定阈值,对每个样本的弱点进行排名,并释放出一个上-K最弱的凹槽,每光线扩展后用于下游增强

何时用

分析 VCN 分类失败,选择 SDA 增强目标,或审计 PASS/NO_PASS 边界案例

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:TAO VCN Classify Gap Analysis Skill、Inputs、Setup、Pinned TAO data-services container URI (stamped from the release manifest)、Method、Step 1–4 — Run the container。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/container-setup.md、references/visual-spot-check.md、references/pitfalls.md、references/output-template.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.

TAO VCN Classify Gap Analysis SkillInputsSetupPinned TAO data-services container URI (stamped from the release manifest)MethodStep 1–4 — Run the containerStep 5 — Visual spot check (small, fixed)Reference invocationWrite the gap-analysis spec for this runContainer writes as root with --user dropped; chown back to host UID if needed.Sanity print so the script-check hook sees real numbers. Report metrics arederived from inference.csv because metrics.json is not part of the 7.2 contract.

兼容:Requires docker + nvidia-container-toolkit and a CUDA GPU. Pulls the TAO data-services container pinned in this skill.yaml` at the skill bank root. · 许可:Apache-2.0 · allowed-tools:Read Bash

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
tao-analyze-gaps-visual-changenet
description
Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.
compatibility
Requires docker + nvidia-container-toolkit and a CUDA GPU. Pulls the TAO data-services container pinned in this skill.yaml` at the skill bank root.
allowed-tools
Read Bash实验字段,支持情况取决于客户端;字段声明本身不会授予工具权限。
许可
Apache-2.0
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 4
  • references/container-setup.md
  • references/visual-spot-check.md
  • references/pitfalls.md
  • references/output-template.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「tao-analyze-gaps-visual-changenet」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-bd60b39fd33cdb37-Tao-%E5%88%86%E6%9E%90%E6%BC%8F%E6%B4%9E%E8%A7%86%E8%A7%89%E5%8F%98%E6%8D%A2%E7%BD%91.html
请存为 .cursor/skills/tao-analyze-gaps-visual-changenet/SKILL.md 或 .claude/skills/tao-analyze-gaps-visual-changenet/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/nvidia/skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/nvidia/skills' --list

npx skills add 'https://github.com/nvidia/skills' --skill 'tao-analyze-gaps-visual-changenet'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: tao-analyze-gaps-visual-changenet description: Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases. license: Apache-2.0 compatibility: Requires docker + nvidia-container-toolkit and a CUDA GPU. Pulls the TAO data-services container pinned in this skill.yaml` at the skill bank root. metadata: author: NVIDIA Corporation version: "0.1.0" allowed-tools: Read Bash tags: - data - rca - vcn - aoi --- # TAO VCN Classify Gap Analysis Skill > **Standalone install?** If this session was not initialized by the TAO skill bank plugin, run the `tao-setup` skill first (host preflight, credentials, cross-skill discovery). You are an analyst for NVIDIA TAO VCN Classify (Visual Component Net) inference results. Your job is to identify the **weakest samples per ground-truth label** by measuring signed distance from the decision threshold *in the wrong direction*, then surface them for downstream augmentation or relabeling. This skill is intentionally lightweight. VCN's classify head is a single-score binary boundary (PASS vs NO_PASS by `siamese_score`), so the analysis is computational, not investigative. The whole computation lives behind one direct `docker run` invocation against the pinned TAO data-services image (see Setup). The container's entrypoint takes ` [hydra overrides...]`; we pass `gap_analysis vcn_aoi key=value …`. Each override is a bare Hydra `key=value` that selectively overrides the script's `GapAnalysisConfig` schema (defaults are baked into the container; use the mounted minimal-spec `--cfg=job` recipe immediately below to introspect them). (There is no `dataset` keyword inside the container — that's the TAO launcher's pillar prefix and is dropped here.) You do **not** need delegated analysis, multi-phase image audits, or component-type clustering — VCN does not expose those dimensions. View only a small set of representative weak samples to qualify the gaps after the container returns. CLI surface can shift between data-services container builds. If a `gap_analysis vcn_aoi` invocation fails on argument parsing, introspect the actual schema once per image with a minimal spec on a bind-mounted host path: ```bash SPEC_DIR="$(mktemp -d)" printf '%s\n' 'min_recall: 0.99' 'top_k_per_label: 5' > "$SPEC_DIR/vcn_aoi_spec.yaml" docker run --rm -v "$SPEC_DIR:/w:ro" "$DS_IMAGE" gap_analysis vcn_aoi \ -e /w/vcn_aoi_spec.yaml --cfg=job ``` The `-e` path must resolve inside the container, so the spec must live under the directory mounted at `/w`. Reconcile any renamed keys (e.g. `inference_csv` vs `inference_results_dir`, `output_dir` vs `results_dir`) before retrying. Output parquet name is `kpi_gaps.parquet`. --- ## Inputs 1. **Experiment result directory** — contains `inference/inference.csv` from TAO VCN Classify inference. Required columns: `input_path`, `object_name`, `label`, `siamese_score`. Pass the **directory** (e.g. `inference/latest/`), not the CSV file — the container reads `inference_results_dir/inference.csv`. 2. **Training code/config directory** — contains the VCN train YAML. The container reads `dataset.classify.input_map` (lighting condition list) and `dataset.classify.image_ext` from it to expand each weak sample into one row per lighting. 3. **Dataset directory** — image root prepended to the relative `input_path` from each row (`kpi_media_path`). 4. **Schema overrides** — `min_recall`, `top_k_per_label`, and optionally a hard-pinned `threshold` are passed as Hydra overrides (defaults: `min_recall=1.0`, `top_k_per_label=50`, `threshold=-1.0` meaning sweep). **`top_k_per_label` must be a positive integer** — omitting it flips the container into "below-threshold filter" mode, which at `min_recall=1.0` returns only PASS misclassifications and zero NO_PASS rows. See Common pitfalls. --- ## Setup The threshold sweep, weakness ranking, and per-lighting expansion all run inside the pinned TAO data-services image below. Confirm Docker, the NVIDIA container toolkit, and a GPU are present and ensure the image is cached: ```bash # Pinned TAO data-services container URI (stamped from the release manifest) DS_IMAGE=nvcr.io/nvidia/tao/tao-toolkit:7.2.0-data-services # versions-key: images.tao_toolkit.data_services echo "DS_IMAGE=$DS_IMAGE" docker info > /dev/null && echo "OK: docker" nvidia-smi > /dev/null && echo "OK: GPU" docker image inspect "$DS_IMAGE" > /dev/null \ || docker pull "$DS_IMAGE" ``` A GPU is required; aborting early on a GPU-less host saves a confusing late error. Three setup rules are load-bearing and easy to get wrong: - **Path mounting** — every host path the container reads or writes (`inference.csv`, train YAML, dataset image root, output dir) must be bind-mounted, simplest with `-v $WORKSPACE:$WORKSPACE -w $WORKSPACE` so absolute paths resolve identically on both sides. - **Do not pass `--user $(id -u):$(id -g)`** — it triggers `KeyError: 'getpwuid(): uid not found: '` during the container's `transformers` import; `chown` outputs back to the host UID afterwards instead. - **`-e ` is required, not optional** — current images hard-require it and exit with `ValueError: The subtask vcn_aoi requires the following argument: -e/--experiment_spec_file` before parsing CLI overrides. See `references/container-setup.md` for the full path-mounting pattern, the `--user`/`chown` rationale and `alpine` chown command, multi-`-v` guidance, and the `-e ` requirement detail. --- ## Method The whole skill is a single `docker run` invocation followed by a small visual spot-check. The container does Steps 1–4 internally (threshold sweep, weakness scoring, top-K selection, per-lighting expansion). You handle Step 5 (visual spot-check) directly with the Read tool. ### Step 1–4 — Run the container ```bash $DOCKER gap_analysis vcn_aoi \ inference_results_dir=/inference// \ train_config=/train.yaml \ kpi_media_path= \ results_dir= \ top_k_per_label=50 ``` > **Always pass `top_k_per_label`.** This is the argument that switches the container > from the default "samples below threshold" filter into proper top-K-per-label > ranking. At `min_recall=1.0` the threshold is by construction at-or-below every > NO_PASS score, so the below-threshold filter returns ONLY misclassified PASS rows > and zero NO_PASS rows — useless as an augmentation queue. With `top_k_per_label` > set to a positive integer (either in the spec or as a Hydra override), the > container computes signed weakness against the threshold for every row and > surfaces the K weakest **per ground-truth label**, which is the per-label ranked > output downstream steps consume. Reads `inference.csv`, sweeps every unique `siamese_score` plus one value just below the minimum, keeps the candidates with NO_PASS-class recall ≥ `min_recall` (with `1e-12` tolerance), then picks the threshold with the best F1 (tie-break: precision, then threshold value). For every row, computes signed weakness from that threshold (positive = misclassified, negative = correct, magnitude = margin). Sorts by weakness descending and takes the top `top_k_per_label` per ground-truth label, then expands each weak row into one row per lighting condition using `dataset.classify.input_map` and `dataset.classify.image_ext` from the train YAML. If **no** candidate threshold meets the recall target, the container exits non-zero and writes `unreachable_kpi.txt` into `results_dir` explaining which recall the model can actually achieve. In that case, stop the analysis after the docker call, write a one-section report explaining the model fundamentally cannot reach the KPI at any operating point, and recommend retraining or relabeling — skip the visual spot-check. **TAO 7.2 artifact contract:** Container-produced required artifacts: | Artifact | Contents | |----------|----------| | `kpi_gaps.parquet` | Top-K weakest per label, expanded per lighting. Columns: `filepath`, `label`, `siamese_score`, `weakness`. | | `threshold.txt` | Chosen decision threshold (single float, plain text). | | `weak_samples_breakdown.txt` | Per-label kept-row breakdown: `` total, `<%>` of all kept rows, `N` misclassified (weakness > 0), `N` marginal (weakness ≤ 0). | You must produce the required seven-section `RCA_Report.md` after the container returns. On a reachable run, you must also produce `rca_images/` during the visual spot check. The container does not produce either agent-owned artifact. `unreachable_kpi.txt` is the failure artifact written when the recall target is unreachable. Its presence means: skip Step 5, write the abridged report, and recommend retraining. The TAO 7.2 `vcn_aoi` action does **not** emit `metrics.json`; that file is outside the 7.2 contract. Calculate report metrics from the full `inference.csv` and the chosen value in `threshold.txt` instead. Print the container's stdout summary (chosen threshold, kept-row counts, per-label breakdown) to your own stdout so the script-check hook can verify the run produced output. ### Step 5 — Visual spot check (small, fixed) Skip this step if `unreachable_kpi.txt` exists. Otherwise use the Read tool to **view** the 5 weakest PASS samples and the 5 weakest NO_PASS samples from `kpi_gaps.parquet` (deduplicated to one row per sample, using the FIRST-lighting `filepath`), classify each as exactly one of **mislabeled** / **edge case** / **data quality** / **systematic**, and copy each viewed image (resized to 128×128 if PIL is available, otherwise just copy) into `/rca_images/`. This is the only image inspection required — do not view dozens of images, run failure mode clustering, or audit goldens (VCN has no golden images). See `references/visual-spot-check.md` for the exact sample-selection sort, the per-lighting deduplication rule, the full definition of each verdict category, and the image-copy detail. --- ## Reference invocation Paste-and-edit the workspace, the four paths, and the two numeric knobs; this runs end-to-end. Capture stdout so the script-check hook sees row counts. ```bash WORKSPACE= # mounted identically inside the container EXP_DIR= # contains inference/inference.csv and train.yaml; must be inside $WORKSPACE DATASET_ROOT= # image root for inference.csv input_path entries; must be inside $WORKSPACE MIN_RECALL=1.0 # zero-miss default; lower if KPI relaxes TOP_K=50 # per-label augmentation budget OUT="$EXP_DIR/rca_results/$(date +%Y-%m-%d_%H%M%S)" SPEC="$OUT/vcn_aoi_spec.yaml" IMG=nvcr.io/nvidia/tao/tao-toolkit:7.2.0-data-services # versions-key: images.tao_toolkit.data_services mkdir -p "$OUT" # Write the gap-analysis spec for this run cat > "$SPEC" </rca_results/YYYY-MM-DD_HHMMSS/ ├── kpi_gaps.parquet # Container: top-K weakest per label, expanded per lighting ├── threshold.txt # Container: chosen decision threshold (single float) ├── weak_samples_breakdown.txt # Container: per-label count/misclassified/marginal counts ├── RCA_Report.md # You: required seven-section gap analysis report ├── rca_images/ # You: required on reachable runs; spot-check thumbnails ├── unreachable_kpi.txt # Container: ONLY when no threshold meets min_recall └── # Runtime-dependent; outside the 7.2 contract ``` At the start of the run, get the real timestamp by running `date +%Y-%m-%d_%H%M%S` in Bash. Do NOT hardcode or guess. If the user specifies a custom output path, use that instead but maintain the same internal structure. --- ## Common pitfalls The single most consequential failure mode is **forgetting `top_k_per_label` when `min_recall=1.0`**: at that recall the chosen threshold sits at or below every NO_PASS score, so without `top_k_per_label` the container falls back to a "samples below threshold" filter that returns ONLY misclassified PASS rows and zero NO_PASS rows, breaking the augmentation queue. Always include an explicit positive `top_k_per_label` (default 50) in the spec or as a Hydra override. See `references/pitfalls.md` for the complete checklist, covering: forgetting `top_k_per_label`; passing `--user`; calling with only Hydra overrides (no `-e `); spec file outside `$WORKSPACE`; spec file with unresolved `???` sentinels; image not pulled / wrong tag; path-mount mismatch; `unreachable_kpi.txt` written; `inference.csv` missing required columns; train YAML missing `dataset.classify.input_map` or `image_ext`; `kpi_media_path` not matching `input_path` prefixes; and no GPU detected from inside the container. --- ## Report Structure Write `RCA_Report.md` as a tight (1000–1800 word) computational gap analysis — depth comes from accurate numbers and a clear action list, not narrative. The full report template (7 sections: Verdict, Threshold Selection, Weakness Distribution, Top-K Weakest Samples, Visual Spot Check, Per-Label Breakdown, Recommended Actions — with the confusion-matrix and table layouts) is in `references/output-template.md`. When `unreachable_kpi.txt` exists, replace sections 3–6 with a single short section quoting that file's contents and collapse section 7 to one recommendation: retrain or relabel. --- ## Execution Order 1. Set `DS_IMAGE` to the pinned data-services URI (see Setup), then run `docker info`, `nvidia-smi`, and `docker image inspect "$DS_IMAGE"` (pulling if missing) once to confirm the environment. Abort with a clear message if any fail. 2. Run `date +%Y-%m-%d_%H%M%S` to get the timestamp; create `/rca_results//`. 3. Write `vcn_aoi_spec.yaml` into the timestamped dir with `min_recall` and `top_k_per_label` filled in. Keep it under `$WORKSPACE` so the `-e` path resolves inside the container. 4. Run `docker run … "$DS_IMAGE" gap_analysis vcn_aoi -e vcn_aoi_spec.yaml inference_results_dir=… train_config=… kpi_media_path=… output_dir=…`. The container writes `kpi_gaps.parquet`, `threshold.txt`, and `weak_samples_breakdown.txt` into `results_dir`. Print the chosen threshold and kept-row counts to stdout so the script-check hook can verify the run produced output. 5. If `unreachable_kpi.txt` exists, skip Step 6 and write the abridged report. Otherwise continue. 6. Pick 10 weak samples (5 weakest PASS + 5 weakest NO_PASS) from `kpi_gaps.parquet`, view each test image with Read, classify, and copy each into `rca_images/`. 7. Write `RCA_Report.md` last — writing it triggers the packaging hook, which copies session logs and skill config alongside.

相关技能

运维与云

Docker Essentials

用于容器管理,图像操作,调试的基本道克命令和工作流程.

运维与云

Find Skills

从开放的代理技能生态系统中发现并安装技能. 使用时:(1)用户问"我如何做X",X可能拥有现有技能,(2)用户说"为X找到技能"或"是否为X有技能",(3)用户问"你能否做X",X是专门能力,(4)用户想扩展代理能力,(5)用户想搜索工具,模板,或工作流程,(6)用户提到他们希望…

运维与云

Microsoft Foundry

构建,部署,评价,优化,微调,管理微软创始代理,模型,资源最终结束. 用法:铸造、azd ai代理、azd 提供/部署、托管代理脚手架/开发/运行/部署/拖放、即时代理创建、创建代理、更新代理、添加代理工具、援引代理、代理.yaml、评估代理、批量活化、连续活化、持续监测、代理C…

运维与云

Azure Deploy

执行已有.azure/部署计划.md和基础设施文件的ALREADY-PREPARED应用程序的Azure部署。 当用户向 CREATE 请求新应用程序时, 请不要使用此技能 。 这种技能运行了 azd上行, azd 部署, trarraform 应用, 和 az 部署命令带有内置…