model:
  name: "facebook/dinov2-large"
  compression_dim: 512
  device: "auto" # auto-detect GPU
  sam_model: "facebook/sam2.1-hiera-large" # SAM model name
  sam_min_mask_area: 100 # Minimum mask area threshold
  sam_max_masks: 10 # Maximum number of masks to keep
  compressor_path: null # Path to trained HashCompressor weights (optional)

output:
  directory: "./outputs"

dataset:
  dataset_root: "datasets/InsDet-FULL"
  output_dir: "datasets/InsDet-FULL/Synthesized"
  num_objects_range: [3, 8]
  num_scenes: 1000
  object_scale_range: [0.1, 0.4]
  rotation_range: [-30, 30]
  overlap_threshold: 0.3
  seed: 42

benchmark:
  enabled: true
  dataset:
    source_type: "huggingface"
    path: "uoft-cs/cifar10"
    img_column: "img"
    label_column: "label"
  task:
    name: "recall_at_k"
    type: "retrieval"
    top_k: 1
  batch_size: 64
  model_table_prefix: "benchmark"