{
  "architectures": [
    "ViTPoseForPoseEstimation"
  ],
  "depth": 12,
  "drop_path_rate": 0.1,
  "dropout_p": 0.0,
  "embed_dim": 384,
  "flip_test": false,
  "img_size": [
    256,
    192
  ],
  "initializer_range": 1,
  "kernel": 3,
  "keypoint_in_channels": 382,
  "keypoint_num_deconv_filters": [
    256,
    256
  ],
  "keypoint_num_deconv_kernels": [
    4,
    4
  ],
  "keypoint_num_deconv_layer": 2,
  "mlp_ratio": 4,
  "model_type": "vitpose",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_joints": 17,
  "num_output_channels": 17,
  "patch_size": 16,
  "qkv_bias": true,
  "ratio": 1,
  "target_type": "GaussianHeatMap",
  "torch_dtype": "float32",
  "transformers_version": "4.32.0.dev0",
  "udp": true,
  "use_checkpoint": false
}