Skip to main content

vame.model.create_training

Variational Animal Motion Embedding 1.0-alpha Toolbox © K. Luxem & P. Bauer, Department of Cellular Neuroscience Leibniz Institute for Neurobiology, Magdeburg, Germany

https://github.com/LINCellularNeuroscience/VAME Licensed under GNU General Public License v3.0

plot_check_parameter​

def plot_check_parameter(cfg: dict, iqr_val: float, num_frames: int,
                         X_true: List[np.ndarray], X_med: np.ndarray) -> None

Plot the check parameter - z-scored data and the filtered data.

Arguments:

  • cfg dict - Configuration parameters.
  • iqr_val float - IQR value.
  • num_frames int - Number of frames.
  • X_true List[np.ndarray] - List of true data.
  • X_med np.ndarray - Filtered data.
  • anchor_1 int - Index of the first anchor point (deprecated).
  • anchor_2 int - Index of the second anchor point (deprecated).

Returns:

None - Plot the z-scored data and the filtered data.

traindata_aligned​

def traindata_aligned(cfg: dict, files: List[str], testfraction: float,
                      savgol_filter: bool, check_parameter: bool) -> None

Create training dataset for aligned data.

Arguments:

  • cfg dict - Configuration parameters.
  • files List[str] - List of files.
  • testfraction float - Fraction of data to use as test data.
  • num_features int - Number of features (deprecated).
  • savgol_filter bool - Flag indicating whether to apply Savitzky-Golay filter.
  • check_parameter bool - If True, the function will plot the z-scored data and the filtered data.

Returns:

None - Save numpy arrays with the test/train info to the project folder.

traindata_fixed​

def traindata_fixed(cfg: dict, files: List[str], testfraction: float,
                    num_features: int, savgol_filter: bool,
                    check_parameter: bool,
                    pose_ref_index: Optional[List[int]]) -> None

Create training dataset for fixed data.

Arguments:

  • cfg dict - Configuration parameters.
  • files List[str] - List of files.
  • testfraction float - Fraction of data to use as test data.
  • num_features int - Number of features.
  • savgol_filter bool - Flag indicating whether to apply Savitzky-Golay filter.
  • check_parameter bool - If True, the function will plot the z-scored data and the filtered data.
  • pose_ref_index Optional[List[int]] - List of reference coordinate indices for alignment.

Returns:

None - Save numpy arrays with the test/train info to the project folder.

create_trainset​

@save_state(model=CreateTrainsetFunctionSchema)
def create_trainset(config: str,
                    pose_ref_index: Optional[List] = None,
                    check_parameter: bool = False,
                    save_logs: bool = False) -> None

Creates a training dataset for the VAME model.

Arguments:

  • config str - Path to the config file.
  • pose_ref_index Optional[List], optional - List of reference coordinate indices for alignment. Defaults to None.
  • check_parameter bool, optional - If True, the function will plot the z-scored data and the filtered data. Defaults to False.