Individual skill
tao-train-mask-auto-encoder
Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating, exporting, or running inference for a TAO MAE backbone. Trigger phrases include "pretrain MAE", "self-supervised vision pretraining", "Masked Autoencoder", "Mask Auto-Encoder", "MAE fine-tune".
skills/tao-train-mask-auto-encoder/SKILL.md
Source commit 25340619336e89bcc40365c28bfe9e790430468e
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 2, 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)
- 3,901
- 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
- self Declared skill tag
- supervised Declared skill tag
- learning Declared skill tag
- education Derived category
- 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 · 7,209 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesSKILL.mdcore · 11,495 bytesconfig/skillspector-baseline.yamlasset · 834 bytesevals/evals.jsonasset · 846 bytesreferences/skill_info.yamlasset · 3,367 bytesreferences/spec_template_deploy_gen_trt_engine.yamlasset · 750 bytesreferences/spec_template_evaluate.yamlasset · 1,752 bytesreferences/spec_template_export.yamlasset · 1,842 bytesreferences/spec_template_gen_trt_engine.yamlasset · 1,913 bytesreferences/spec_template_inference.yamlasset · 1,777 bytesreferences/spec_template_train.yamlasset · 1,626 bytesreferences/tao-deploy-mask-auto-encoder.mddoc · 3,453 bytesreferences/tao-deploy-mask-auto-encoder.skill_info.yamlasset · 1,165 bytesschemas/evaluate.schema.jsonasset · 29,775 bytesschemas/export.schema.jsonasset · 30,686 bytesschemas/gen_trt_engine.schema.jsonasset · 32,596 bytesschemas/inference.schema.jsonasset · 29,776 bytesschemas/manifest.jsonasset · 7,856 bytesschemas/train.schema.jsonasset · 27,204 bytesskill-card.mddoc · 4,564 bytesskill.oms.sigasset · 8,617 bytes
Read excerpt
# MAE
> **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).
MAE (Masked Autoencoder) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations. Supports pretrain and finetune stages.
Set train.pretrained_model_path for pretrained MAE weights when fine-tuning.
For TAO Deploy TensorRT actions (`gen_trt_engine`), read `references/tao-deploy-mask-auto-encoder.md` first. Deploy spec templates live in this skill's `references/` folder with the `spec_template_deploy_*.yaml` prefix.
The parent PyTorch `mae` CLI supports `train`, `evaluate`, `inference`, and
`export`. Build TensorRT engines through the deploy workflow, not the model skill.
## Dataclass Schemas