Skip to content

Support

Source

Supported configuration options.

Used throughout the code to ensure consistency. These should be kept in sync with the corresponding configuration options in the Pydantic models.

SupportedActivation

Bases: StrEnum

Supported activation functions.

  • None, no activation will be used.
  • Sigmoid
  • Softmax
  • Tanh
  • ReLU
  • LeakyReLU

All activations are defined in PyTorch.

See: https://pytorch.org/docs/stable/nn.html#loss-functions

SupportedAlgorithm

Bases: StrEnum

Algorithms available in CAREamics.

These definitions are the same as the keyword name of the algorithm configurations.

CARE = 'care' class-attribute instance-attribute

Content-aware image restoration, a supervised algorithm used for a variety of tasks.

DENOISPLIT = 'denoisplit' class-attribute instance-attribute

An image splitting and denoising approach based on ladder VAE architectures.

HDN = 'hdn' class-attribute instance-attribute

Hierarchical Denoising Network, an unsupervised denoising algorithm

MICROSPLIT = 'microsplit' class-attribute instance-attribute

A micro-level image splitting approach based on ladder VAE architectures.

MUSPLIT = 'musplit' class-attribute instance-attribute

An image splitting approach based on ladder VAE architectures.

N2N = 'n2n' class-attribute instance-attribute

Noise2Noise algorithm, a self-supervised denoising scheme based on comparing noisy images of the same sample.

N2V = 'n2v' class-attribute instance-attribute

Noise2Void algorithm, a self-supervised approach based on blind denoising.

PN2V = 'pn2v' class-attribute instance-attribute

Probabilistic Noise2Void. A extension of Noise2Void is not restricted to Gaussian noise models or Gaussian intensity predictions.

SupportedArchitecture

Bases: StrEnum

Supported architectures.

LVAE = 'LVAE' class-attribute instance-attribute

Ladder Variational Autoencoder used for muSplit and denoiSplit.

UNET = 'UNet' class-attribute instance-attribute

UNet architecture used with N2V, CARE and Noise2Noise.

SupportedData

Bases: StrEnum

Supported data types.

Attributes:

  • ARRAY (str) –

    Array data.

  • TIFF (str) –

    TIFF image data.

  • CZI (str) –

    CZI image data.

  • ZARR (str) –

    Zarr data.

  • CUSTOM (str) –

    Custom data.

get_extension(data_type) classmethod

Get file extension of corresponding data type.

Parameters:

Returns:

  • str –

    Corresponding extension.

get_extension_pattern(data_type) classmethod

Get Path.rglob and fnmatch compatible extension.

Parameters:

Returns:

  • str –

    Corresponding extension pattern.

SupportedLogger

Bases: StrEnum

Available loggers.

SupportedLoss

Bases: StrEnum

Supported losses.

Attributes:

  • MSE (str) –

    Mean Squared Error loss.

  • MAE (str) –

    Mean Absolute Error loss.

  • N2V (str) –

    Noise2Void loss.

SupportedNormalization

Bases: StrEnum

Normalization strategies supported by Careamics.

MEAN_STD = 'mean_std' class-attribute instance-attribute

Mean and std normalization strategy.

MINMAX = 'min_max' class-attribute instance-attribute

Min-max normalization strategy.

NONE = 'none' class-attribute instance-attribute

No normalization strategy.

QUANTILE = 'quantile' class-attribute instance-attribute

Quantile normalization strategy.

SupportedOptimizer

Bases: StrEnum

Supported optimizers.

Attributes:

  • Adam (str) –

    Adam optimizer.

  • AdamW (str) –

    AdamW optimizer.

  • Adamax (str) –

    Adamax optimizer.

  • SGD (str) –

    Stochastic Gradient Descent optimizer.

SupportedPixelManipulation

Bases: StrEnum

Supported Noise2Void pixel manipulations.

  • Uniform: Replace masked pixel value by a (uniformly) randomly selected neighbor pixel value.
  • Median: Replace masked pixel value by the mean of the neighborhood.

SupportedScheduler

Bases: StrEnum

Supported schedulers.

Attributes:

  • ReduceLROnPlateau (str) –

    Reduce learning rate on plateau.

  • StepLR (str) –

    Step learning rate.

SupportedStructAxis

Bases: StrEnum

Supported structN2V mask axes.

Attributes:

  • HORIZONTAL (str) –

    Horizontal axis.

  • VERTICAL (str) –

    Vertical axis.

  • NONE (str) –

    No axis, the mask is not applied.

SupportedTransform

Bases: StrEnum

Transforms officially supported by CAREamics.