{
  "_name_or_path": "openmmlab/upernet-convnext-xlarge",
  "architectures": [
    "UperNetForSemanticSegmentation"
  ],
  "auxiliary_channels": 256,
  "auxiliary_concat_input": false,
  "auxiliary_in_channels": 1024,
  "auxiliary_loss_weight": 0.4,
  "auxiliary_num_convs": 1,
  "backbone": null,
  "backbone_config": {
    "depths": [
      3,
      3,
      27,
      3
    ],
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "image_size": 224,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-12,
    "layer_scale_init_value": 1e-06,
    "model_type": "convnext",
    "num_stages": 4,
    "out_features": [
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      1,
      2,
      3,
      4
    ],
    "patch_size": 4
  },
  "backbone_kwargs": null,
  "hidden_size": 512,
  "id2label": {
    "0": "0",
    "1": "1",
    "2": "2",
    "3": "3",
    "4": "4",
    "5": "5",
    "6": "6",
    "7": "7",
    "8": "8"
  },
  "initializer_range": 0.02,
  "label2id": {
    "0": 0,
    "1": 1,
    "2": 2,
    "3": 3,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 7,
    "8": 8
  },
  "loss_ignore_index": 255,
  "model_type": "upernet",
  "pool_scales": [
    1,
    2,
    3,
    6
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.48.1",
  "use_auxiliary_head": true,
  "use_pretrained_backbone": false,
  "use_timm_backbone": false
}