config.json

{
  "architectures": [
    "MaskFormerForInstanceSegmentation"
  ],
  "backbone": null,
  "backbone_config": {
    "attention_probs_dropout_prob": 0.0,
    "depths": [
      2,
      2,
      18,
      2
    ],
    "drop_path_rate": 0.3,
    "embed_dim": 192,
    "encoder_stride": 32,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1536,
    "image_size": 384,
    "in_channels": 3,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-05,
    "mlp_ratio": 4.0,
    "model_type": "maskformer-swin",
    "num_channels": 3,
    "num_heads": [
      6,
      12,
      24,
      48
    ],
    "num_layers": 4,
    "out_features": [
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      1,
      2,
      3,
      4
    ],
    "patch_size": 4,
    "path_norm": true,
    "pretrain_img_size": 384,
    "qkv_bias": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "use_absolute_embeddings": false,
    "window_size": 12
  },
  "backbone_kwargs": null,
  "ce_weight": 1.0,
  "cross_entropy_weight": 1.0,
  "decoder_config": {
    "activation_dropout": 0.0,
    "activation_function": "relu",
    "attention_dropout": 0.0,
    "auxiliary_loss": false,
    "backbone": "resnet50",
    "backbone_config": null,
    "backbone_kwargs": {
      "in_chans": 3,
      "out_indices": [
        1,
        2,
        3,
        4
      ]
    },
    "bbox_cost": 5,
    "bbox_loss_coefficient": 5,
    "class_cost": 1,
    "d_model": 256,
    "decoder_attention_heads": 8,
    "decoder_ffn_dim": 2048,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 6,
    "dice_loss_coefficient": 1,
    "dilation": false,
    "dropout": 0.1,
    "encoder_attention_heads": 8,
    "encoder_ffn_dim": 2048,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 6,
    "eos_coefficient": 0.1,
    "giou_cost": 2,
    "giou_loss_coefficient": 2,
    "init_std": 0.02,
    "init_xavier_std": 1.0,
    "mask_loss_coefficient": 1,
    "max_position_embeddings": 1024,
    "model_type": "detr",
    "num_channels": 3,
    "num_hidden_layers": 6,
    "num_queries": 100,
    "position_embedding_type": "sine",
    "scale_embedding": false,
    "use_pretrained_backbone": true,
    "use_timm_backbone": true
  },
  "dice_weight": 1.0,
  "fpn_feature_size": 256,
  "id2label": {
    "0": "floor",
    "1": "door",
    "2": "blinds",
    "3": "curtain",
    "4": "windowpane"
  },
  "init_std": 0.02,
  "init_xavier_std": 1.0,
  "label2id": {
    "blinds": 2,
    "curtain": 3,
    "door": 1,
    "floor": 0,
    "windowpane": 4
  },
  "mask_feature_size": 256,
  "mask_weight": 20.0,
  "model_type": "maskformer",
  "no_object_weight": 0.1,
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "num_queries": 100,
  "output_auxiliary_logits": null,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "use_auxiliary_loss": false,
  "use_pretrained_backbone": false,
  "use_timm_backbone": false
}