config.json

{
  "architectures": [
    "DepthProForDepthEstimation"
  ],
  "dtype": "float16",
  "fov_model_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": 1024,
    "image_size": 384,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "dinov2",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "out_features": [
      "stage24"
    ],
    "out_indices": [
      24
    ],
    "patch_size": 16,
    "qkv_bias": true,
    "reshape_hidden_states": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12",
      "stage13",
      "stage14",
      "stage15",
      "stage16",
      "stage17",
      "stage18",
      "stage19",
      "stage20",
      "stage21",
      "stage22",
      "stage23",
      "stage24"
    ],
    "use_mask_token": false,
    "use_swiglu_ffn": false
  },
  "fusion_hidden_size": 256,
  "image_model_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": 1024,
    "image_size": 384,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "dinov2",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "out_features": [
      "stage24"
    ],
    "out_indices": [
      24
    ],
    "patch_size": 16,
    "qkv_bias": true,
    "reshape_hidden_states": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12",
      "stage13",
      "stage14",
      "stage15",
      "stage16",
      "stage17",
      "stage18",
      "stage19",
      "stage20",
      "stage21",
      "stage22",
      "stage23",
      "stage24"
    ],
    "use_mask_token": false,
    "use_swiglu_ffn": false
  },
  "initializer_range": 0.02,
  "intermediate_feature_dims": [
    256,
    256
  ],
  "intermediate_hook_ids": [
    11,
    5
  ],
  "merge_padding_value": 3,
  "model_type": "depth_pro",
  "num_fov_head_layers": 2,
  "patch_model_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": 1024,
    "image_size": 384,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "dinov2",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "out_features": [
      "stage24"
    ],
    "out_indices": [
      24
    ],
    "patch_size": 16,
    "qkv_bias": true,
    "reshape_hidden_states": true,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12",
      "stage13",
      "stage14",
      "stage15",
      "stage16",
      "stage17",
      "stage18",
      "stage19",
      "stage20",
      "stage21",
      "stage22",
      "stage23",
      "stage24"
    ],
    "use_mask_token": false,
    "use_swiglu_ffn": false
  },
  "patch_size": 384,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "float16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "scaled_images_feature_dims": [
    1024,
    1024,
    512
  ],
  "scaled_images_overlap_ratios": [
    0.0,
    0.5,
    0.25
  ],
  "scaled_images_ratios": [
    0.25,
    0.5,
    1
  ],
  "transformers_version": "4.57.1",
  "use_batch_norm_in_fusion_residual": false,
  "use_bias_in_fusion_residual": true,
  "use_fov_model": true
}