model:
  image_encoder:
    backbone:
      pretrained: true
      frozen: true
      output_dim: 128
    name: feature_extractor_DPT
  segmentation_head:
    dropout_rate: 0.2
  name: map_perception_net
  num_classes: 6
  latent_dim: 128
  z_max: 50
  x_max: 25
  pixel_per_meter: 2
  num_scale_bins: 32
  loss:
    num_classes: 6
    xent_weight: 1.0
    dice_weight: 1.0
    focal_loss: false
    focal_loss_gamma: 2.0
    requires_frustrum: true
    requires_flood_mask: false
    class_weights:
    - 1.00351229
    - 4.34782609
    - 1.00110121
    - 1.03124678
    - 6.69792364
    - 7.55857899
    label_smoothing: 0.1
  scale_range:
  - 0
  - 9
  z_min: null