{
  "architectures": [
    "UperNetForSemanticSegmentation"
  ],
  "auxiliary_channels": 32,
  "auxiliary_concat_input": false,
  "auxiliary_in_channels": 40,
  "auxiliary_loss_weight": 0.4,
  "auxiliary_num_convs": 1,
  "backbone": null,
  "backbone_config": {
    "depths": [
      1,
      1,
      1,
      1
    ],
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_sizes": [
      10,
      20,
      30,
      40
    ],
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_training": true,
    "layer_norm_eps": 1e-12,
    "layer_scale_init_value": 1e-06,
    "model_type": "convnext",
    "num_channels": 3,
    "num_stages": 4,
    "out_features": [
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      2,
      3,
      4
    ],
    "patch_size": 4,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ]
  },
  "dtype": "float32",
  "hidden_size": 64,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "initializer_range": 0.02,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "loss_ignore_index": 255,
  "model_type": "upernet",
  "pool_scales": [
    1,
    2,
    3,
    6
  ],
  "transformers_version": "5.16.0.dev0",
  "use_auxiliary_head": true
}