{
  "architectures": [
    "MaskFormerForInstanceSegmentation"
  ],
  "backbone": null,
  "backbone_config": {
    "depths": [
      2,
      2,
      18,
      2
    ],
    "drop_path_rate": 0.3,
    "embed_dim": 128,
    "hidden_size": 1024,
    "image_size": 384,
    "in_channels": 3,
    "model_type": "swin",
    "num_heads": [
      4,
      8,
      16,
      32
    ],
    "out_features": [
      "stage4"
    ],
    "out_indices": [
      4
    ],
    "path_norm": true,
    "pretrain_img_size": 384,
    "window_size": 12
  },
  "ce_weight": 1.0,
  "cross_entropy_weight": 1.0,
  "decoder_config": {
    "max_position_embeddings": 1024,
    "model_type": "detr",
    "scale_embedding": false
  },
  "dice_weight": 12.0,
  "fpn_feature_size": 256,
  "id2label": {
    "0": "unlabeld",
    "1": "kelp"
  },
  "init_std": 0.02,
  "init_xavier_std": 1.0,
  "label2id": {
    "kelp": 1,
    "unlabeld": 0
  },
  "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": "4.38.0.dev0",
  "use_auxiliary_loss": false,
  "use_pretrained_backbone": false
}