How unbailanlinch/21days works
This repository is a Unity game project, but the sampled runtime sources describe a substantial companion subsystem: expression-recognition model development for character face rigs. Its workflow builds canonical expression data and rig projections, trains and calibrates a classifier, evaluates it, and exports a model for deployment. The graph focuses on that evidenced subsystem rather than inferring Unity gameplay connections from the tree. Edges are limited to relationships documented by source excerpts or the SOURCE INDEX; other Unity and harness capabilities are not mapped because their runtime sources were not sampled.
Main entry points: train.py Training pipeline · evaluate.py Model evaluation · datasets.py Dataset loading · run.py Rig upper-bound analysis
Components 17
Expression representation
- Canonical space
ML/expression-recognition/exprnet/canonical.py - Face rig
ML/expression-recognition/exprnet/rig.py - Labels and config
ML/expression-recognition/exprnet/common.py
Data preparation
- Dataset loading
ML/expression-recognition/exprnet/datasets.py - Feature extraction
ML/expression-recognition/exprnet/extract.py - FACS synthesis
ML/expression-recognition/exprnet/facs.py - Data augmentation
ML/expression-recognition/exprnet/augment.py - Rig coverage
ML/expression-recognition/exprnet/coverage.py
Model learning
- Classifier models
ML/expression-recognition/exprnet/models.py - Training losses
ML/expression-recognition/exprnet/losses.py - Training pipeline
ML/expression-recognition/exprnet/train.py
Validation and export
- Calibration and rejection
ML/expression-recognition/exprnet/calibrate.py - Golden-set checks
ML/expression-recognition/exprnet/golden_check.py - Model evaluation
ML/expression-recognition/exprnet/evaluate.py - Model export
ML/expression-recognition/exprnet/export.py - Rig upper-bound analysis
ML/expression-recognition/analysis/laila_upper_bound/run.py
Other components
- ML engineer
Connections 26
- ML engineer → Training pipeline: starts training
- Training pipeline → Labels and config: loads labels
ML/expression-recognition/exprnet/train.py - Training pipeline → Canonical space: loads dimensions
ML/expression-recognition/exprnet/train.py - Training pipeline → Face rig: loads rig
ML/expression-recognition/exprnet/train.py - Training pipeline → FACS synthesis: synthesizes samples
ML/expression-recognition/exprnet/train.py - Training pipeline → Dataset loading: builds training data
ML/expression-recognition/exprnet/train.py - Training pipeline → Data augmentation: augments batches
ML/expression-recognition/exprnet/train.py - Training pipeline → Classifier models: trains classifier
ML/expression-recognition/exprnet/train.py - Training pipeline → Training losses: computes loss
ML/expression-recognition/exprnet/train.py - Training pipeline → Calibration and rejection: fits thresholds
ML/expression-recognition/exprnet/train.py - Training pipeline → Model evaluation: evaluates run
ML/expression-recognition/exprnet/train.py - Dataset loading → Canonical space: aligns features
ML/expression-recognition/exprnet/datasets.py - Dataset loading → Face rig: projects features
ML/expression-recognition/exprnet/datasets.py - FACS synthesis → Canonical space: uses expression space
ML/expression-recognition/exprnet/facs.py - Rig coverage → Face rig: projects samples
ML/expression-recognition/exprnet/coverage.py - Rig coverage → Dataset loading: reads cached features
ML/expression-recognition/exprnet/coverage.py - Rig coverage → FACS synthesis: generates prototypes
ML/expression-recognition/exprnet/coverage.py - Model evaluation → Calibration and rejection: applies thresholds
ML/expression-recognition/exprnet/evaluate.py - Model evaluation → Golden-set checks: checks golden set
ML/expression-recognition/exprnet/evaluate.py - Model evaluation → Classifier models: loads classifier
ML/expression-recognition/exprnet/evaluate.py - Model evaluation → Model export: compares deployment graph
ML/expression-recognition/exprnet/evaluate.py - Model export → Classifier models: exports classifier
ML/expression-recognition/exprnet/export.py - Rig upper-bound analysis → Training pipeline: runs training
ML/expression-recognition/analysis/laila_upper_bound/run.py - Rig upper-bound analysis → Dataset loading: rebuilds splits
ML/expression-recognition/analysis/laila_upper_bound/run.py - Rig upper-bound analysis → Face rig: projects inputs
ML/expression-recognition/analysis/laila_upper_bound/run.py - Rig upper-bound analysis → Model evaluation: compares predictions
ML/expression-recognition/analysis/laila_upper_bound/run.py