liblaf.flame_pytorch.config

Classes:

• FlameConfig –

Functions:

• get_config –

FlameConfig pydantic-model

Bases: BaseModel

Parameters:

• flame_model_path

  (Path, default: PosixPath('model/generic_model.pkl') ) –

  flame model path

• static_landmark_embedding_path

  (Path, default: PosixPath('/home/runner/.cache/liblaf/flame-pytorch/flame_static_embedding.pkl') ) –

  Static landmark embeddings path for FLAME

• dynamic_landmark_embedding_path

  (Path, default: PosixPath('/home/runner/.cache/liblaf/flame-pytorch/flame_dynamic_embedding.npy') ) –

  Dynamic contour embedding path for FLAME

• shape_params

  (int, default: 100 ) –

  the number of shape parameters

• expression_params

  (int, default: 50 ) –

  the number of expression parameters

• pose_params

  (int, default: 6 ) –

  the number of pose parameters

• use_face_contour

  (bool, default: True ) –

  If true apply the landmark loss on also on the face contour.

• use_3d_translation

  (bool, default: True ) –

  If true apply the landmark loss on also on the face contour.

• optimize_eyeballpose

  (bool, default: True ) –

  If true optimize for the eyeball pose.

• optimize_neckpose

  (bool, default: True ) –

  If true optimize for the neck pose.

• num_worker

  (int, default: 4 ) –

  pytorch number worker.

• batch_size

  (int, default: 1 ) –

  Training batch size.

• ring_margin

  (float, default: 0.5 ) –

  ring margin.

• ring_loss_weight

  (float, default: 1.0 ) –

  weight on ring loss.

Show JSON schema:

{
  "properties": {
    "flame_model_path": {
      "format": "path",
      "title": "Flame Model Path",
      "type": "string"
    },
    "static_landmark_embedding_path": {
      "format": "path",
      "title": "Static Landmark Embedding Path",
      "type": "string"
    },
    "dynamic_landmark_embedding_path": {
      "format": "path",
      "title": "Dynamic Landmark Embedding Path",
      "type": "string"
    },
    "shape_params": {
      "default": 100,
      "title": "Shape Params",
      "type": "integer"
    },
    "expression_params": {
      "default": 50,
      "title": "Expression Params",
      "type": "integer"
    },
    "pose_params": {
      "default": 6,
      "title": "Pose Params",
      "type": "integer"
    },
    "use_face_contour": {
      "default": true,
      "title": "Use Face Contour",
      "type": "boolean"
    },
    "use_3d_translation": {
      "default": true,
      "title": "Use 3D Translation",
      "type": "boolean"
    },
    "optimize_eyeballpose": {
      "default": true,
      "title": "Optimize Eyeballpose",
      "type": "boolean"
    },
    "optimize_neckpose": {
      "default": true,
      "title": "Optimize Neckpose",
      "type": "boolean"
    },
    "num_worker": {
      "default": 4,
      "title": "Num Worker",
      "type": "integer"
    },
    "batch_size": {
      "default": 1,
      "title": "Batch Size",
      "type": "integer"
    },
    "ring_margin": {
      "default": 0.5,
      "title": "Ring Margin",
      "type": "number"
    },
    "ring_loss_weight": {
      "default": 1.0,
      "title": "Ring Loss Weight",
      "type": "number"
    }
  },
  "title": "FlameConfig",
  "type": "object"
}

Fields:

• flame_model_path (Path)
• static_landmark_embedding_path (Path)
• dynamic_landmark_embedding_path (Path)
• shape_params (int)
• expression_params (int)
• pose_params (int)
• use_face_contour (bool)
• use_3d_translation (bool)
• optimize_eyeballpose (bool)
• optimize_neckpose (bool)
• num_worker (int)
• batch_size (int)
• ring_margin (float)
• ring_loss_weight (float)

batch_size pydantic-field

batch_size: int = 1

Training batch size.

dynamic_landmark_embedding_path pydantic-field

dynamic_landmark_embedding_path: Path

Dynamic contour embedding path for FLAME

expression_params pydantic-field

expression_params: int = 50

the number of expression parameters

flame_model_path pydantic-field

flame_model_path: Path

flame model path

num_worker pydantic-field

num_worker: int = 4

pytorch number worker.

optimize_eyeballpose pydantic-field

optimize_eyeballpose: bool = True

If true optimize for the eyeball pose.

optimize_neckpose pydantic-field

optimize_neckpose: bool = True

If true optimize for the neck pose.

pose_params pydantic-field

pose_params: int = 6

the number of pose parameters

ring_loss_weight pydantic-field

ring_loss_weight: float = 1.0

weight on ring loss.

ring_margin pydantic-field

ring_margin: float = 0.5

ring margin.

shape_params pydantic-field

shape_params: int = 100

the number of shape parameters

static_landmark_embedding_path pydantic-field

static_landmark_embedding_path: Path

Static landmark embeddings path for FLAME

use_3D_translation property writable

use_3D_translation: bool

use_3d_translation pydantic-field

use_3d_translation: bool = True

If true apply the landmark loss on also on the face contour.

use_face_contour pydantic-field

use_face_contour: bool = True

If true apply the landmark loss on also on the face contour.

get_config

get_config() -> FlameConfig

Source code in src/liblaf/flame_pytorch/config.py

def get_config() -> FlameConfig:
    return FlameConfig()