# configs/default.yaml
# Default Configuration for Geo-Layout Transformer

# 1. Data Preprocessing
data:
  patch_size: 10.0  # in microns
  patch_stride: 5.0   # in microns
  layer_mapping:
    "1/0": 0   # Example: GDS Layer 1, Datatype 0 -> Index 0 (e.g., M1)
    "2/0": 1   # Example: GDS Layer 2, Datatype 0 -> Index 1 (e.g., VIA1)
    "3/0": 2   # Example: GDS Layer 3, Datatype 0 -> Index 2 (e.g., M2)
  graph_construction:
    edge_strategy: "knn" # 'knn' or 'radius'
    knn_k: 8             # K for KNN graph construction
    radius_d: 1.0        # Radius for radius graph construction (in microns)

# 2. Model Architecture
model:
  # GNN Encoder
  gnn:
    node_input_dim: 5    # Initial node feature dim (e.g., x, y, w, h, area)
    hidden_dim: 128
    output_dim: 256      # Dimension of the patch embedding
    num_layers: 4
    gnn_type: "gat"     # 'gat', 'gcn', 'graphsage'

  # Transformer Backbone
  transformer:
    num_layers: 6
    num_heads: 8
    hidden_dim: 256      # Must match gnn.output_dim
    dropout: 0.1
    positional_encoding:
      type: "hybrid"   # 'hybrid', 'absolute', 'relative'

# 3. Training
training:
  mode: "train" # 'train', 'eval', 'pretrain'
  batch_size: 32
  learning_rate: 0.0001
  epochs: 100
  optimizer: "adamw"
  loss_function: "bce" # 'bce', 'focal_loss'
  weight_decay: 0.01
  scheduler: "cosine" # 'step', 'cosine'
  scheduler_T_0: 10
  scheduler_T_mult: 2
  early_stopping_patience: 10
  save_dir: "checkpoints"
  log_dir: "logs"
  use_amp: false  # 是否启用混合精度训练
  gradient_accumulation_steps: 1  # 梯度累积步数

# 4. Data Splits
splits:
  train_ratio: 0.8
  val_ratio: 0.1
  test_ratio: 0.1
  random_seed: 42

# 4. Self-Supervised Pre-training
pretraining:
  mask_ratio: 0.15
  epochs: 200
  learning_rate: 0.0005
  early_stopping_patience: 10