config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "nielsr/vitpose-base-simple",
  "architectures": [
    "VitPoseForPoseEstimation"
  ],
  "backbone": null,
  "backbone_config": {
    "model_type": "vitpose_backbone",
    "out_features": [
      "stage12"
    ],
    "out_indices": [
      12
    ]
  },
  "backbone_hidden_size": 768,
  "backbone_kwargs": null,
  "edges": [
    [15, 13],
    [13, 11],
    [16, 14],
    [14, 12],
    [11, 12],
    [5, 11],
    [6, 12],
    [5, 6],
    [5, 7],
    [6, 8],
    [7, 9],
    [8, 10],
    [1, 2],
    [0, 1],
    [0, 2],
    [1, 3],
    [2, 4],
    [3, 5],
    [4, 6]
  ],
  "id2label": {
    "0": "Nose",
    "1": "L_Eye",
    "2": "R_Eye",
    "3": "L_Ear",
    "4": "R_Ear",
    "5": "L_Shoulder",
    "6": "R_Shoulder",
    "7": "L_Elbow",
    "8": "R_Elbow",
    "9": "L_Wrist",
    "10": "R_Wrist",
    "11": "L_Hip",
    "12": "R_Hip",
    "13": "L_Knee",
    "14": "R_Knee",
    "15": "L_Ankle",
    "16": "R_Ankle"
  },
  "image_size": [
    256,
    192
  ],
  "initializer_range": 0.02,
  "label2id": {
    "Nose": 0,
    "L_Eye": 1,
    "R_Eye": 2,
    "L_Ear": 3,
    "R_Ear": 4,
    "L_Shoulder": 5,
    "R_Shoulder": 6,
    "L_Elbow": 7,
    "R_Elbow": 8,
    "L_Wrist": 9,
    "R_Wrist": 10,
    "L_Hip": 11,
    "R_Hip": 12,
    "L_Knee": 13,
    "R_Knee": 14,
    "L_Ankle": 15,
    "R_Ankle": 16
  },
  "model_type": "vitpose",
  "patch_size": [
    16,
    16
  ],
  "scale_factor": 4,
  "torch_dtype": "float32",
  "transformers_version": "4.47.0.dev0",
  "use_pretrained_backbone": false,
  "use_simple_decoder": true,
  "use_timm_backbone": false
}