model:
  name: clip_dino_gnn
  num_attributes: 12
  primary_object_class: chair

encoders:
  clip:
    enabled: true
    model_name: vit_base_patch16_clip_224.openai
    pretrained: true
    output_dim: 512
    freeze_stage1: true
  dino:
    enabled: true
    model_name: vit_base_patch14_dinov2.lvd142m
    pretrained: true
    output_dim: 768
    freeze_stage1: true

fusion:
  type: concat
  output_dim: 1280
  projected_fusion:
    enabled: false
    hidden_dim: 512
  gated_fusion:
    enabled: false
    hidden_dim: 512

graph:
  variant: bipartite
  include_attribute_priors: false
  edge_weighting:
    labeled_positive: 1.0
    weak_min: 0.3
    weak_max: 0.8

attribute_nodes:
  init_type: clip_text
  prompt_template: "a {attribute} chair"
  trainable_dim: 256

gnn:
  type: gat
  layers:
    - in_dim: 1280
      out_dim: 512
      heads: 4
      dropout: 0.2
    - in_dim: 512
      out_dim: 256
      heads: 2
      dropout: 0.2
  classifier:
    in_dim: 256
    out_dim: 12

baseline_heads:
  mlp:
    enabled: true
    hidden_dims:
      - 512
      - 256
    dropout: 0.2