model:
  class_path: watch.tasks.fusion.methods.HeterogeneousModel
  init_args:
    token_width: 6
    token_dim: 64
    position_encoder:
      class_path: watch.tasks.fusion.methods.heterogeneous.MipNerfPositionalEncoder
      init_args:
        in_dims: 3
        max_freq: 3
        num_freqs: 16
    backbone:
      class_path: watch.tasks.fusion.architectures.transformer.TransformerEncoderDecoder
      init_args:
        encoder_depth: 6
        decoder_depth: 1
        dim: 160
        queries_dim: 96
        logits_dim: 64
        latent_dim_head: 256
    spatial_scale_base: 1.0
    temporal_scale_base: 1.0
    global_change_weight: 0.0
    global_class_weight: 1.0
    global_saliency_weight: 0.5
    class_loss: dicefocal
    saliency_loss: focal
    decoder: simple_conv
trainer:
  callbacks:
    # - class_path: watch.utils.lightning_ext.callbacks.AutoResumer
    # - class_path: pytorch_lightning.callbacks.ModelCheckpoint
    #   init_args:
    #     monitor: val_class_f1_macro
    #     mode: max
    #     save_top_k: 5
    #     auto_insert_metric_name: true
    - class_path: pytorch_lightning.callbacks.ModelCheckpoint
      init_args:
        monitor: val_loss
        mode: min
        save_top_k: 5
        auto_insert_metric_name: true