{
  "architectures": [
    "GLPNForDepthEstimation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "decoder_hidden_size": 64,
  "depths": [
    3,
    8,
    27,
    3
  ],
  "downsampling_rates": [
    1,
    4,
    8,
    16
  ],
  "drop_path_rate": 0.1,
  "head_in_index": -1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_sizes": [
    64,
    128,
    320,
    512
  ],
  "image_size": 224,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-06,
  "max_depth": 10,
  "mlp_ratios": [
    4,
    4,
    4,
    4
  ],
  "model_type": "glpn",
  "num_attention_heads": [
    1,
    2,
    5,
    8
  ],
  "num_channels": 3,
  "num_encoder_blocks": 4,
  "patch_sizes": [
    7,
    3,
    3,
    3
  ],
  "sr_ratios": [
    8,
    4,
    2,
    1
  ],
  "strides": [
    4,
    2,
    2,
    2
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.18.0.dev0"
}