Tao train metric learning recognition vs Tao train reid
Tao train metric learning recognition is an open-source agent skill for computer vision. Tao train reid is an open-source agent skill for computer vision.
- Tao train metric learning recognition is best for train a retail product recognition model on a labeled set of known product classes.
- Tao train reid is best for train a person re-identification model on my camera dataset.
- What it is
- Tao train metric learning recognition is an open-source agent skill for computer vision.Tao train reid is an open-source agent skill for computer vision.
- Best for
- Train a retail product recognition model on a labeled set of known product classesTrain a person re-identification model on my camera dataset
- Kind
- SkillSkill
- Pricing
- Open sourceOpen source
- Platforms
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, GooseClaude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- GitHub stars
- 4K4K
- Last commit
- Nov 2026Nov 2026
- License
- Apache-2.0Apache-2.0
- Open source
- Good for
- Train a retail product recognition model on a labeled set of known product classes; Evaluate a trained embedding model against a reference gallery and query set; Run inference to match unknown product images against a reference catalogTrain a person re-identification model on my camera dataset; Evaluate a ReID checkpoint with mAP and CMC rank scores; Run inference on query and gallery images and save matches to JSON
What Tao train metric learning recognition does
Triplet-based embedding training
Trains a recognition model with triplet and contrastive losses, using configurable margins and hard-mining settings.
Retrieval evaluation
Scores the model with Precision at Rank 1 on reference and query splits to measure retrieval accuracy.
Backbone and embedding options
Offers several backbones, including ResNet and FAN variants, and a configurable embedding dimension.
AutoML routing
Sends training requests through an AutoML workflow by default, with an option to run plain training instead.
Spec and dataset setup
Lists the dataset paths and spec overrides needed for each train, evaluate and inference action.
Checkpoint handling
Resolves parent checkpoints automatically and documents an environment flag for loading trusted checkpoints.
What Tao train reid does
Docker-based training launch
Runs the TAO re-identification train action inside a GPU container with mounted data, specs and results folders.
Evaluation with retrieval metrics
Reports mAP and CMC ranks against separate test and query datasets and can write CMC and match plots.
Inference to JSON output
Runs a trained checkpoint over query and test sets and writes the results to a JSON file.
ONNX export
Exports a trained checkpoint to an ONNX file at a path set in the spec.
Checkpoint resume handling
Resumes interrupted training from a saved checkpoint and passes checkpoints between downstream actions.
Parameter and error guidance
Documents key hyperparameters, default values and fixes for common configuration errors.
Tao train metric learning recognition vs Tao train reid: questions
Is Tao train metric learning recognition or Tao train reid cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between Tao train metric learning recognition and Tao train reid?
Tao train metric learning recognition is an open-source agent skill for computer vision. Tao train reid is an open-source agent skill for computer vision.
