Skip to content

Utils

Source

Script for utility functions needed by the LVAE model.

Interpolate

Bases: Module

Wrapper for torch.nn.functional.interpolate.

StableExponential

Class that redefines the definition of exp() to increase numerical stability. Naturally, also the definition of log() must change accordingly. However, it is worth noting that the two operations remain one the inverse of the other, meaning that x = log(exp(x)) and x = exp(log(x)) are always true.

Definition: exp(x) = { exp(x) if x<=0 x+1 if x>0 }

log(x) = {
    x        if x<=0
    log(1+x) if x>0
}

NOTE 1: Within the class everything is done on the tensor given as input to the constructor. Therefore, when exp() is called, self._tensor.exp() is computed. When log() is called, torch.log(self._tensor.exp()) is computed instead.

NOTE 2: Given the output from exp(), torch.log() or the log() method of the class give identical results.

StableLogVar

Class that provides a numerically stable implementation of Log-Variance. Specifically, it uses the exp() and log() formulas defined in StableExponential class.

is_3D property

Check if the _lv tensor is 3D.

Recall that, in this framework, tensors have shape (B, C, [Z], Y, X).

centercrop_to_size(size)

Centercrop the log-variance tensor to the desired size.

Parameters:

Name Type Description Default
size Sequence[int]

The desired size of the log-variance tensor.

 required

get_var()

Get Variance from Log-Variance.

StableMean

is_3D property

Check if the _mean tensor is 3D.

Recall that, in this framework, tensors have shape (B, C, [Z], Y, X).

centercrop_to_size(size)

Centercrop the mean tensor to the desired size.

Implemented only in the case of 2D tensors.

Parameters:

Name Type Description Default
size Sequence[int]

The desired size of the log-variance tensor.

 required

allow_numpy(func)

All optional arguments are passed as is. positional arguments are checked. if they are numpy array, they are converted to torch Tensor.

crop_img_tensor(x, size)

Crops a tensor. Crops a tensor of shape (batch, channels, h, w) to a desired height and width given by a tuple. Args: x (torch.Tensor): Input image size (list or tuple): Desired size (height, width)

Returns:

Type Description
The cropped tensor

kl_normal_mc(z, p_mulv, q_mulv)

One-sample estimation of element-wise KL between two diagonal multivariate normal distributions. Any number of dimensions, broadcasting supported (be careful). :param z: :param p_mulv: :param q_mulv: :return:

pad_img_tensor(x, size)

Pads a tensor

Pads a tensor of shape (B, C, [Z], Y, X) to desired spatial dimensions.

Parameters: 
x (torch.Tensor): Input image of shape (B, C, [Z], Y, X)
size (list or tuple): Desired size  ([Z*], Y*, X*)
Returns: 
The padded tensor