Evaluate model training Reads Detectron2 metrics.json and exports:

• training_metrics.csv: losses, lr, etc.

• validation_metrics.csv: aggregate COCO bbox and segm AP metrics

• validation_classwise.csv: per-class AP metrics (when logged by evaluator)

Evaluate model training Reads Detectron2 metrics.json and exports:

• training_metrics.csv: losses, lr, etc.

• validation_metrics.csv: aggregate COCO bbox and segm AP metrics

• validation_classwise.csv: per-class AP metrics (when logged by evaluator)

Usage

evaluate_training(
  model_id = NULL,
  model_dir = NULL,
  board = NULL,
  output_dir = "results/evaluation"
)

Arguments

model_id

Model ID (will be resolved from local board)

model_dir

Directory containing trained model (alternative to model_id)

board

Pins board (NULL = local board, only used if model_id provided)

output_dir

Output directory for results (default: 'results/evaluation')

Value

List with parsed tibbles and summary statistics