OrthoPDM

class menpofit.modelinstance.OrthoPDM(data, max_n_components=None)

Bases: GlobalPDM

Class for building a Point Distribution Model that also stores a Global Alignment transform. The final transform couples the Global Alignment transform to a statistical linear model, so that its weights are fully specified by both the weights of statistical model and the weights of the similarity transform.

This transform (in contrast to the :map`GlobalPDM`) additionally orthonormalises both the global and the model basis against each other, ensuring that orthogonality and normalization is enforced across the unified bases.

Parameters:

• data (list of menpo.shape.PointCloud or menpo.model.PCAModel instance) – If a list of menpo.shape.PointCloud, then a menpo.model.PCAModel will be trained from those training shapes. Otherwise, a trained menpo.model.PCAModel instance can be provided.
• max_n_components (int or None, optional) – The maximum number of components that the model will keep. If None, then all the components will be kept.

as_vector(**kwargs)

Returns a flattened representation of the object as a single vector.

Returns:vector ((N,) ndarray) – The core representation of the object, flattened into a single vector. Note that this is always a view back on to the original object, but is not writable.

copy()

Generate an efficient copy of this object.

Note that Numpy arrays and other Copyable objects on self will be deeply copied. Dictionaries and sets will be shallow copied, and everything else will be assigned (no copy will be made).

Classes that store state other than numpy arrays and immutable types should overwrite this method to ensure all state is copied.

Returns:type(self) – A copy of this object

d_dp(points)

The derivative with respect to the parametrisation changes evaluated at points.

Parameters:points ((n_points, n_dims) ndarray) – The spatial points at which the derivative should be evaluated. Returns:d_dp ((n_points, n_parameters, n_dims) ndarray) – The Jacobian with respect to the parametrisation.

from_vector(vector)

Build a new instance of the object from it’s vectorized state.

self is used to fill out the missing state required to rebuild a full object from it’s standardized flattened state. This is the default implementation, which is which is a deepcopy of the object followed by a call to from_vector_inplace(). This method can be overridden for a performance benefit if desired.

Parameters:vector ((n_parameters,) ndarray) – Flattened representation of the object. Returns:object (type(self)) – An new instance of this class.

from_vector_inplace(vector)

Deprecated. Use the non-mutating API, from_vector.

For internal usage in performance-sensitive spots, see _from_vector_inplace()

Parameters:vector ((n_parameters,) ndarray) – Flattened representation of this object

has_nan_values()

Tests if the vectorized form of the object contains nan values or not. This is particularly useful for objects with unknown values that have been mapped to nan values.

Returns:has_nan_values (bool) – If the vectorized object contains nan values.

increment(shapes, n_shapes=None, forgetting_factor=1.0, max_n_components=None, verbose=False)

Update the eigenvectors, eigenvalues and mean vector of this model by performing incremental PCA on the given samples.

Parameters:

• shapes (list of menpo.shape.PointCloud) – List of new shapes to update the model from.
• n_shapes (int or None, optional) – If int, then shapes must be an iterator that yields n_shapes. If None, then shapes has to be a list (so we know how large the data matrix needs to be).
• forgetting_factor ([0.0, 1.0] float, optional) – Forgetting factor that weights the relative contribution of new samples vs old samples. If 1.0, all samples are weighted equally and, hence, the results is the exact same as performing batch PCA on the concatenated list of old and new simples. If <1.0, more emphasis is put on the new samples. See [1] for details.
• max_n_components (int or None, optional) – The maximum number of components that the model will keep. If None, then all the components will be kept.
• verbose (bool, optional) – If True, then information about the progress will be printed.

References

[1]	D. Ross, J. Lim, R.S. Lin, M.H. Yang. “Incremental Learning for Robust Visual Tracking”. International Journal on Computer Vision, 2007.

set_target(new_target)

Update this object so that it attempts to recreate the new_target.

Parameters:new_target (PointCloud) – The new target that this object should try and regenerate.

global_parameters

The parameters for the global transform.

Type:(n_global_parameters,) ndarray

n_active_components

The number of components currently in use on this model.

Type:int

n_dims

The number of dimensions of the spatial instance of the model

Type:int

n_global_parameters

The number of parameters in the global_transform

Type:int

n_parameters

The length of the vector that this object produces.

Type:int

n_points

The number of points on the target.

Type:int

n_weights

The number of parameters in the linear model.

Type:int

target

The current menpo.shape.PointCloud that this object produces.

Type:menpo.shape.PointCloud

weights

The weights of the model.

Type:(n_weights,) ndarray