# Native77 final775 Body Motion with original ViTPose and Body Pose features.
# Paths resolve relative to this file and use the repository-level weights folder.
# Download/extract yolox_humanart.onnx using docs/PRETRAINED_MODELS.md,
# "Person detector for Body Motion", or change detector.checkpoint.
# Contact/IK and rendering use the assets/soma setup in docs/INSTALL.md.
# Keep the statistics sidecar for this checkpoint. Remove stats only when using
# a GEM training checkpoint that includes its codec statistics.
pose:
  checkpoint: ../../weights/body_s240000.ckpt
  release: body
  batch_size: 4
observations:
  checkpoint: ../../weights/vitpose.pth
  release_id: vitpose77-dinov3-huge-metrosim-256x192-v1
  batch_size: 4
detector:
  checkpoint: ../../weights/yolox_humanart.onnx
  device: cpu
motion:
  checkpoint: ../../weights/motion_native77_e774_s292175.ckpt
  stats: ../../weights/motion_stats_raw.npz
  network:
    output_dim: 655
    max_len: 120
    cliffcam_dim: 3
    cam_angvel_dim: 6
    imgseq_dim: 1024
    latent_dim: 512
    num_layers: 12
    num_heads: 8
    mlp_ratio: 4.0
    pred_cam_dim: 3
    static_conf_dim: 6
    dropout: 0.1
    avgbeta: true
    obs_num_joints: 77
    sequence_static_slices:
    - - 456
      - 584
    - - 584
      - 640
  condition_spec:
    pose_release_id: gem-pose-body-s240000-v1:pose_tokens
    observation_source: vitpose77-dinov3-huge-metrosim-256x192-v1
    observation_joint_set: soma77_native_v1
  time_options:
    reference_fps: 30.0
    default_fps: 30.0
    # motion-video supplies explicit 30 Hz timestamps. For other cached inputs,
    # retain the physical-time settings and source-rate mapping of their recipe.
    fps_by_data_name: {}
camera:
  mode: background