Skip to content

About

Model training pipeline

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

13 Commits

Folders and files

Repository files navigation

perception_training

Dataset consolidation, validation, export, training, and evaluation pipeline for underwater robotics perception (RoboSub), starting with the gate task.

Status: MVP. The full pipeline runs end to end on a tiny synthetic fixture. Real-data importers are not yet implemented.

Setup

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest

Tested with Python 3.11. requirements.txt has the exact versions used.

Commands

Prepare a dataset (generate fixture, import, validate, dedupe, split, export YOLO Detect):

python -m dataset_tools.prepare

Train (1-2 epoch smoke test):

python training/train.py configs/smoke_detect.yaml

Outputs go to runs/smoke/ (gitignored).

Pipeline

  1. dataset_tools/make_fixture.py: tiny fake dataset with known boxes and fake scene IDs
  2. dataset_tools/importers/: converts a source into the common manifest (data/manifest.json)
  3. dataset_tools/validators/: schema values, required fields, pixel-bounds checks
  4. dataset_tools/splits/: hash dedupe, scene-aware train/val/test split with a leakage check
  5. dataset_tools/exporters/: YOLO Detect layout and dataset.yaml
  6. training/, configs/: config-driven YOLO training with a fixed seed

Missing values are stored as null, never guessed. Records without a usable label are excluded from an export instead of getting invented labels.

Schema

Not yet implemented

  • Importers for the real synthetic generator output and reviewed SAM labels
  • YOLO Pose and Segment export
  • Visual overlays for QA
  • Evaluation (precision/recall, keypoint error, failure cases, run metadata)
  • Frozen real-world evaluation split
  • Shared-storage (OCF) artifact workflow
  • CI
  • Final schema

About

Model training pipeline

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages