cldm_seg_cityscapes_multi_step_D.yaml

model:
  target: cldm_seg.cldm_seg_pixel_seg_enc_multiStep.ControlLDM
  params:
    linear_start: 0.00085
    linear_end: 0.0120
    num_timesteps_cond: 1
    log_every_t: 200
    timesteps: 1000
    first_stage_key: "image"
    cond_stage_key: "txt"
    control_key: "hint"
    image_size: 64
    channels: 4
    cond_stage_trainable: false
    conditioning_key: crossattn
    monitor: val/loss_simple_ema # TODO: !change here!
    scale_factor: 0.18215
    use_ema: False # why?
    only_mid_control: False

    # vvv New! vvv
    mask_encode_mode: "id"

    class_emb_manager_config:
      target: cldm_seg.util.ClassEmbeddingManager
      params:
        text_dim: 768
        mode: "cityscapes" # Change here!
        use_time: False
        use_mapping: False

    segmenter_config:
      target: cldm_seg.seg.upernet_res_ADE.ADESegDiscriminator
      params:
        num_classes: 19 #150 # TODO: should be overwritten!
        ignore_index: 255
        segmenter_type: 'upernet101_20cls'
    # ^^^ New! ^^^

    control_stage_config:
      target: cldm_seg.cldm_seg_pixel_seg_enc_multiStep.ControlNet
      params:
        image_size: 32 # unused
        in_channels: 4
        hint_channels: 768 # change here if the condition dim is changed!
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

    unet_config:
      target: cldm_seg.cldm_seg_pixel_seg_enc_multiStep.ControlledUnetModel
      params:
        image_size: 32 # unused
        in_channels: 4
        out_channels: 4
        model_channels: 320
        attention_resolutions: [ 4, 2, 1 ]
        num_res_blocks: 2
        channel_mult: [ 1, 2, 4, 4 ]
        num_heads: 8
        use_spatial_transformer: True
        transformer_depth: 1
        context_dim: 768
        use_checkpoint: True
        legacy: False

    first_stage_config:
      target: ldm.models.autoencoder.AutoencoderKL
      params:
        embed_dim: 4
        monitor: val/rec_loss
        ddconfig:
          double_z: true
          z_channels: 4
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult:
          - 1
          - 2
          - 4
          - 4
          num_res_blocks: 2
          attn_resolutions: []
          dropout: 0.0
        lossconfig:
          target: torch.nn.Identity

    cond_stage_config:
      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder