{
  "architectures": [
    "Tipsv2DptForDepthEstimation"
  ],
  "backbone_config": {
    "apply_layernorm": true,
    "attention_probs_dropout_prob": 0.0,
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 16,
    "image_size": 28,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 2,
    "model_type": "tipsv2_vision_model",
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "num_register_tokens": 1,
    "out_features": [
      "stage1",
      "stage2"
    ],
    "out_indices": [
      1,
      2
    ],
    "patch_size": 14,
    "qkv_bias": true,
    "reshape_hidden_states": false,
    "stage_names": [
      "stem",
      "stage1",
      "stage2"
    ],
    "use_swiglu_ffn": false
  },
  "depth_decoder_activation": "relu",
  "dtype": "float32",
  "fusion_hidden_size": 8,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4
  },
  "max_depth": 10.0,
  "min_depth": 0.001,
  "model_type": "tipsv2_dpt",
  "neck_hidden_sizes": [
    4,
    8
  ],
  "num_depth_bins": 32,
  "readout_activation": "gelu_pytorch_tanh",
  "reassemble_factors": [
    4,
    2
  ],
  "semantic_loss_ignore_index": 255,
  "transformers_version": "5.16.0.dev0"
}