FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Training an ML-Recog metric-learning model v1.0.0
Use this resource to train a TAO embedding-based recognition model with triplet or contrastive losses
New
- 441 downloads
- 218 likes
- 221 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install metric-learning-embedding-trainingWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent writes the training and evaluation specs from typical overrides, checks the dataset requirements, then carries the run through export and inference. The skill targets fine-grained recognition, for example retail products. You get embeddings usable for similarity search.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- references/spec_template_train.yaml: training spec
- references/spec_template_evaluate.yaml: evaluation spec
- references/skill_info.yaml: skill information
Good fit for
- You identify products by comparison with a reference gallery
- You want a similarity search model rather than a fixed list of classes
Not for
Tags
- metric learning
- embeddings
- TAO
- recognition
About
You say
“Train an ml-recog model on my reference product photos and export the model.”
Skill published by nvidia under the Apache-2.0 license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to train a TAO embedding-based recognition model with triplet or contrastive losses
- Review and adjust the result
Content preview
Files
- BENCHMARK.md7.2 KB
- config/skillspector-baseline.yaml0.8 KB
- evals/evals.json0.9 KB
- LICENSE11.3 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/skill_info.yaml4.9 KB
- references/spec_template_deploy_evaluate.yaml0.2 KB
- references/spec_template_deploy_gen_trt_engine.yaml0.6 KB
- references/spec_template_deploy_inference.yaml0.3 KB
- references/spec_template_evaluate.yaml1.9 KB
- references/spec_template_export.yaml1.8 KB
- references/spec_template_gen_trt_engine.yaml2.1 KB
- references/spec_template_inference.yaml1.9 KB
- references/spec_template_train.yaml1.7 KB
- references/tao-deploy-metric-learning-recognition.md6 KB
- references/tao-deploy-metric-learning-recognition.skill_info.yaml4.1 KB
- schemas/evaluate.schema.json36.7 KB
- schemas/export.schema.json35.8 KB
- schemas/gen_trt_engine.schema.json42.2 KB
- schemas/inference.schema.json37.1 KB
- schemas/manifest.json10.7 KB
- schemas/train.schema.json33.6 KB
- skill-card.md4.2 KB
- SKILL.md11.5 KB
- skill.oms.sig9 KB
Origin and licence
Listed unmodified
- Author
- nvidia
- Source
- github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-metric-learning-recognition
- Licence
- Apache-2.0
Notice
« tao-train-metric-learning-recognition » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…