Individual skill
tao-train-visual-changenet
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NO_PASS classification, or producing change-segmentation masks. Trigger phrases include "train Visual ChangeNet", "ChangeNet classify", "ChangeNet segment", "AOI defect detection", "PCB inspection model".
skills/tao-train-visual-changenet/SKILL.md
Source commit fce3cca4170be75e82c64920654d56ee2811b005
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3,913
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- cuda Repository topic
- developer-tools Repository topic
- llm Repository topic
- omniverse Repository topic
- pcb Declared skill tag
- aoi Declared skill tag
- defect Declared skill tag
- classification Declared skill tag
- segmentation Declared skill tag
- siamese Declared skill tag
- visual-inspection Declared skill tag
- design Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
BENCHMARK.mddoc · 7,116 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesSKILL.mdcore · 18,816 bytesconfig/skillspector-baseline.yamlasset · 1,168 byteseval.configasset · 5,729 bytesevals/evals.jsonasset · 858 bytesreferences/data-formats.mddoc · 5,625 bytesreferences/dinov3-backbones.mddoc · 1,941 bytesreferences/local-docker.mddoc · 2,104 bytesreferences/parent-model-inference.mddoc · 2,550 bytesreferences/skill_info.yamlasset · 10,425 bytesreferences/spec_template_deploy_classify_evaluate.yamlasset · 1,034 bytesreferences/spec_template_deploy_classify_gen_trt_engine.yamlasset · 430 bytesreferences/spec_template_deploy_classify_inference.yamlasset · 1,035 bytesreferences/spec_template_deploy_segment_evaluate.yamlasset · 533 bytesreferences/spec_template_deploy_segment_gen_trt_engine.yamlasset · 419 bytesreferences/spec_template_deploy_segment_inference.yamlasset · 537 bytesreferences/spec_template_evaluate.yamlasset · 4,214 bytesreferences/spec_template_export.yamlasset · 3,171 bytesreferences/spec_template_inference.yamlasset · 4,215 bytesreferences/spec_template_quantize.yamlasset · 2,850 bytesreferences/spec_template_segment.yamlasset · 2,163 bytesreferences/spec_template_segment_evaluate.yamlasset · 4,471 bytesreferences/spec_template_segment_inference.yamlasset · 4,472 bytesreferences/spec_template_segment_train.yamlasset · 4,530 bytesreferences/spec_template_train.yamlasset · 3,255 bytesreferences/tao-deploy-visual-changenet.mddoc · 6,848 bytesreferences/tao-deploy-visual-changenet.skill_info.yamlasset · 4,384 bytesreferences/troubleshooting.mddoc · 4,905 bytesreferences/tuning-parameters.mddoc · 3,959 bytesschemas/evaluate.schema.jsonasset · 80,700 bytesschemas/inference.schema.jsonasset · 80,701 bytesschemas/manifest.jsonasset · 34,450 bytesschemas/segment_evaluate.schema.jsonasset · 80,706 bytesschemas/segment_inference.schema.jsonasset · 80,707 bytesschemas/segment_train.schema.jsonasset · 81,041 bytesschemas/train.schema.jsonasset · 81,497 bytesscripts/stage_backbone.pyruns · 5,105 bytesscripts/validate_vcn_dataset.pyruns · 12,480 bytesskill-card.mddoc · 5,440 bytesskill.oms.sigasset · 13,729 bytestests/test_validate_vcn_dataset.pyruns · 4,160 bytes
Read excerpt
# Visual ChangeNet
> **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).
Visual ChangeNet is a TAO Toolkit model for visual inspection and defect detection. It supports two tasks:
- **Classify** — Binary image classification using a siamese-style architecture with a shared backbone (C-RADIO ViT) and a learnable difference module. Compares image pairs to classify defects as PASS/NO_PASS.
- **Segment** — Pixel-level change segmentation using a ViT-Large NVDINOv2 backbone. Compares before/after image pairs to produce a binary change mask.
Classify supports the public C-RADIOv2-B backbone and six frozen DINOv3
variants. Read `references/dinov3-backbones.md` before selecting DINOv3; it
contains the exact variant map, freeze requirement, Hugging Face access rules,
and local-staging overlay. For C-RADIO, use the bundled
`scripts/stage_backbone.py` and the mount in `references/local-docker.md`.