model:
  base_learning_rate: 2.0e-06
  target: lidm.models.diffusion.ddpm.LatentDiffusion
  params:
    linear_start: 0.0015
    linear_end: 0.0195
    num_timesteps_cond: 1
    log_every_t: 100
    timesteps: 1000
    image_size: [16, 128]
    channels: 8
    monitor: val/loss_simple_ema
    first_stage_key: image
    cond_stage_key: camera
    conditioning_key: crossattn
    cond_stage_trainable: true
    verbose: false
    unet_config:
      target: lidm.modules.diffusion.openaimodel.UNetModel
      params:
        image_size: [16, 128]
        in_channels: 8
        out_channels: 8
        model_channels: 256
        attention_resolutions: [4, 2, 1]
        num_res_blocks: 2
        channel_mult: [1, 2, 4]
        num_head_channels: 32
        use_spatial_transformer: true
        context_dim: 512
        lib_name: lidm
    first_stage_config:
      target: lidm.models.autoencoder.VQModelInterface
      params:
        embed_dim: 8
        n_embed: 16384
        lib_name: lidm
        use_mask: False  # False
        ckpt_path: models/first_stage_models/kitti/f_c2_p4_wo_logscale/model.ckpt
        ddconfig:
          double_z: false
          z_channels: 8
          in_channels: 1
          out_ch: 1
          ch: 64
          ch_mult: [1,2,2,4]
          strides: [[1,2],[2,2],[2,2]]
          num_res_blocks: 2
          attn_levels: []
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity
    cond_stage_config:
      target: lidm.modules.encoders.modules.FrozenClipMultiImageEmbedder
      params:
        model: ViT-L/14
        split_per_view: 4
        key: camera
        out_dim: 512

data:
  target: main.DataModuleFromConfig
  params:
    batch_size: 8
    num_workers: 8
    wrap: true
    dataset:
      size: [64, 1024]
      fov: [ 3,-25 ]
      depth_range: [ 1.0,56.0 ]
      depth_scale: 56  # np.log2(depth_max + 1)
      log_scale: false
      x_range: [ -50.0, 50.0 ]
      y_range: [ -50.0, 50.0 ]
      z_range: [ -3.0, 1.0 ]
      resolution: 1
      num_channels: 1
      num_cats: 10
      num_views: 1
      num_sem_cats: 19
      filtered_map_cats: [ ]
    aug:
      flip: false
      rotate: false
      keypoint_drop: false
      keypoint_drop_range:
      randaug: false
      camera_drop: 0.5
    train:
      target: lidm.data.kitti.KITTI360Train
      params:
        condition_key: camera
        split_per_view: 4
    validation:
      target: lidm.data.kitti.KITTI360Validation
      params:
        condition_key: camera
        split_per_view: 4


lightning:
  callbacks:
    image_logger:
      target: main.ImageLogger
      params:
        batch_frequency: 5000
        max_images: 8
        increase_log_steps: False

  trainer:
    benchmark: True