| { | |
| "task": "body", | |
| "head": { | |
| "num_body_joints": 76, | |
| "num_identity_coeffs": 128, | |
| "num_scale_params": 57, | |
| "scale_comps_dim": 0, | |
| "scale_param_mode": "direct", | |
| "scale_parameterization": "packed", | |
| "fixed_global_scale": 1.0, | |
| "transformer_dim": 1024, | |
| "transformer_depth": 6, | |
| "transformer_heads": 8, | |
| "transformer_dim_head": 64, | |
| "transformer_mlp_dim": 1024, | |
| "transformer_context_dim": 1280, | |
| "transformer_dropout": 0.0, | |
| "transformer_emb_dropout": 0.0, | |
| "ief_iters": 1, | |
| "learnable_init": true, | |
| "use_init_to_token": true, | |
| "two_layer_heads": true, | |
| "per_layer_predictions": true, | |
| "cliff_cond_dim": 3, | |
| "camera_scale_mode": "ste_clamp" | |
| }, | |
| "backbone": { | |
| "name": "dinov3_vith16plus", | |
| "drop_path_rate": 0.1 | |
| }, | |
| "conditioning": { | |
| "camera_mode": "sam3db_perspective" | |
| }, | |
| "backbone_input_crop_w": null, | |
| "ray_pe_num_bands": null, | |
| "kp2d_translation": null, | |
| "pose_release_id": "gem-pose-body-s240000-v1", | |
| "inference": { | |
| "camera_representation": "legacy", | |
| "minimum_depth": 0.05 | |
| } | |
| } | |