pytomography.priors.gibbs
#
Module Contents#
Classes#
Implementation of priors where gradients depend on difference and the sum of neighbouring voxels: |
|
Implentation of SmoothnessPrior where \(\phi\) is the the QClear Function (DEFINE HERE) |
Functions#
|
- class pytomography.priors.gibbs.DiffAndSumSmoothnessPrior(beta, phi, device='cpu', **kwargs)#
Bases:
pytomography.priors.prior.Prior
Implementation of priors where gradients depend on difference and the sum of neighbouring voxels: \(\frac{\partial V}{\partial f_r}=\frac{\beta}{\delta}\sum_{r,s}w_{s}\phi\left(\frac{f_r-f_s}{\delta}\right)\) where \(V\) is from the log-posterior probability \(\log P(g | f) - \beta V(f)\).
- Parameters:
beta (float) –
phi (collections.abc.Callable) –
device (str) –
- get_kernel(sign=1)#
Obtains the kernel used to get \(\frac{\partial V}{\partial f_r}\) (this is an array with the same dimensions as the object space image)
- Parameters:
sign (float) – Kernel computes image \(f_r + \text{sign} \cdot f_k\) for all 26 nearest neighbours \(k\) (i.e. a 3D image is returned with 26 channels). Defaults to 1.
- Returns:
Kernel used for convolution (number of output channels equal to number of \(s\)), and array of weights \(w_s\) used in expression for gradient.
- Return type:
(torch.nn.Conv3d, torch.tensor)
- set_kernel(object_meta)#
Sets the kernel using get_kernel and the corresponding object metadata.
- Parameters:
object_meta (ObjectMeta) – Metadata for object space.
- Return type:
None
- forward()#
Computes the prior on
self.object
- Returns:
Tensor of shape [batch_size, Lx, Ly, Lz] representing \(\frac{\partial V}{\partial f_r}\)
- Return type:
torch.tensor
- class pytomography.priors.gibbs.QClearPrior(beta=1, gamma=1, device='cpu')#
Bases:
DiffAndSumSmoothnessPrior
Implentation of SmoothnessPrior where \(\phi\) is the the QClear Function (DEFINE HERE)
- Parameters:
beta (float) –
gamma (float) –
device (str) –
- pytomography.priors.gibbs.QClear(sum, diff, gamma, eps=1e-11)#