careamics 0.0.9__py3-none-any.whl → 0.0.10__py3-none-any.whl

careamics/__init__.py

@@ -11,8 +11,6 @@ __all__ = [
     "CAREamist",
     "Configuration",
     "algorithm_factory",
-    "configuration_factory",
-    "data_factory",
     "load_configuration",
     "save_configuration",
 ]
@@ -21,8 +19,6 @@ from .careamist import CAREamist
 from .config import (
     Configuration,
     algorithm_factory,
-    configuration_factory,
-    data_factory,
     load_configuration,
     save_configuration,
 )

careamics/careamist.py

@@ -157,7 +157,6 @@ class CAREamist:
                 self.cfg = load_configuration(source)
 
                 # instantiate model
-                # TODO call model factory here
                 if isinstance(self.cfg.algorithm_config, UNetBasedAlgorithm):
                     self.model = FCNModule(
                         algorithm_config=self.cfg.algorithm_config,

careamics/config/__init__.py

@@ -8,29 +8,22 @@ while `*_configuration` is reserved for the main configuration models, including
 
 __all__ = [
     "CAREAlgorithm",
-    "CAREConfiguration",
     "CheckpointModel",
     "Configuration",
     "DataConfig",
     "GaussianMixtureNMConfig",
-    "GeneralDataConfig",
     "InferenceConfig",
     "LVAELossConfig",
     "MultiChannelNMConfig",
     "N2NAlgorithm",
-    "N2NConfiguration",
     "N2VAlgorithm",
-    "N2VConfiguration",
-    "N2VDataConfig",
     "TrainingConfig",
     "UNetBasedAlgorithm",
     "VAEBasedAlgorithm",
     "algorithm_factory",
-    "configuration_factory",
     "create_care_configuration",
     "create_n2n_configuration",
     "create_n2v_configuration",
-    "data_factory",
     "load_configuration",
     "save_configuration",
 ]
@@ -43,21 +36,16 @@ from .algorithms import (
     VAEBasedAlgorithm,
 )
 from .callback_model import CheckpointModel
-from .care_configuration import CAREConfiguration
 from .configuration import Configuration
 from .configuration_factories import (
     algorithm_factory,
-    configuration_factory,
     create_care_configuration,
     create_n2n_configuration,
     create_n2v_configuration,
-    data_factory,
 )
 from .configuration_io import load_configuration, save_configuration
-from .data import DataConfig, GeneralDataConfig, N2VDataConfig
+from .data import DataConfig
 from .inference_model import InferenceConfig
 from .loss_model import LVAELossConfig
-from .n2n_configuration import N2NConfiguration
-from .n2v_configuration import N2VConfiguration
 from .nm_model import GaussianMixtureNMConfig, MultiChannelNMConfig
 from .training_model import TrainingConfig

careamics/config/algorithms/care_algorithm_model.py

@@ -2,6 +2,7 @@
 
 from typing import Annotated, Literal
 
+from bioimageio.spec.generic.v0_3 import CiteEntry
 from pydantic import AfterValidator
 
 from careamics.config.architectures import UNetModel
@@ -12,6 +13,23 @@ from careamics.config.validators import (
 
 from .unet_algorithm_model import UNetBasedAlgorithm
 
+CARE = "CARE"
+
+CARE_DESCRIPTION = (
+    "Content-aware image restoration (CARE) is a deep-learning-based "
+    "algorithm that uses a U-Net architecture to restore images. CARE "
+    "is a supervised algorithm that requires pairs of noisy and "
+    "clean images to train the network. The algorithm learns to "
+    "predict the clean image from the noisy image. CARE is "
+    "particularly useful for denoising images acquired in low-light "
+    "conditions, such as fluorescence microscopy images."
+)
+CARE_REF = CiteEntry(
+    text='Weigert, Martin, et al. "Content-aware image restoration: pushing the '
+    'limits of fluorescence microscopy." Nature methods 15.12 (2018): 1090-1097.',
+    doi="10.1038/s41592-018-0216-7",
+)
+
 
 class CAREAlgorithm(UNetBasedAlgorithm):
     """CARE algorithm configuration.
@@ -36,3 +54,69 @@ class CAREAlgorithm(UNetBasedAlgorithm):
         AfterValidator(model_without_final_activation),
     ]
     """UNet without a final activation function and without the `n2v2` modifications."""
+
+    def get_algorithm_friendly_name(self) -> str:
+        """
+        Get the algorithm friendly name.
+
+        Returns
+        -------
+        str
+            Friendly name of the algorithm.
+        """
+        return CARE
+
+    def get_algorithm_keywords(self) -> list[str]:
+        """
+        Get algorithm keywords.
+
+        Returns
+        -------
+        list[str]
+            List of keywords.
+        """
+        return [
+            "restoration",
+            "UNet",
+            "3D" if self.model.is_3D() else "2D",
+            "CAREamics",
+            "pytorch",
+            CARE,
+        ]
+
+    def get_algorithm_references(self) -> str:
+        """
+        Get the algorithm references.
+
+        This is used to generate the README of the BioImage Model Zoo export.
+
+        Returns
+        -------
+        str
+            Algorithm references.
+        """
+        return CARE_REF.text + " doi: " + CARE_REF.doi
+
+    def get_algorithm_citations(self) -> list[CiteEntry]:
+        """
+        Return a list of citation entries of the current algorithm.
+
+        This is used to generate the model description for the BioImage Model Zoo.
+
+        Returns
+        -------
+        List[CiteEntry]
+            List of citation entries.
+        """
+        return [CARE_REF]
+
+    def get_algorithm_description(self) -> str:
+        """
+        Get the algorithm description.
+
+        Returns
+        -------
+        str
+            Algorithm description.
+        """
+        return CARE_DESCRIPTION

careamics/config/algorithms/n2n_algorithm_model.py

@@ -2,6 +2,7 @@
 
 from typing import Annotated, Literal
 
+from bioimageio.spec.generic.v0_3 import CiteEntry
 from pydantic import AfterValidator
 
 from careamics.config.architectures import UNetModel
@@ -12,6 +13,24 @@ from careamics.config.validators import (
 
 from .unet_algorithm_model import UNetBasedAlgorithm
 
+N2N = "Noise2Noise"
+
+N2N_DESCRIPTION = (
+    "Noise2Noise is a deep-learning-based algorithm that uses a U-Net "
+    "architecture to restore images. Noise2Noise is a self-supervised "
+    "algorithm that requires only noisy images to train the network. "
+    "The algorithm learns to predict the clean image from the noisy "
+    "image. Noise2Noise is particularly useful when clean images are "
+    "not available for training."
+)
+
+N2N_REF = CiteEntry(
+    text="Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., "
+    'Aittala, M. and Aila, T., 2018. "Noise2Noise: Learning image restoration '
+    'without clean data". arXiv preprint arXiv:1803.04189.',
+    doi="10.48550/arXiv.1803.04189",
+)
+
 
 class N2NAlgorithm(UNetBasedAlgorithm):
     """Noise2Noise Algorithm configuration."""
@@ -28,3 +47,69 @@ class N2NAlgorithm(UNetBasedAlgorithm):
         AfterValidator(model_without_final_activation),
     ]
     """UNet without a final activation function and without the `n2v2` modifications."""
+
+    def get_algorithm_friendly_name(self) -> str:
+        """
+        Get the algorithm friendly name.
+
+        Returns
+        -------
+        str
+            Friendly name of the algorithm.
+        """
+        return N2N
+
+    def get_algorithm_keywords(self) -> list[str]:
+        """
+        Get algorithm keywords.
+
+        Returns
+        -------
+        list[str]
+            List of keywords.
+        """
+        return [
+            "restoration",
+            "UNet",
+            "3D" if self.model.is_3D() else "2D",
+            "CAREamics",
+            "pytorch",
+            N2N,
+        ]
+
+    def get_algorithm_references(self) -> str:
+        """
+        Get the algorithm references.
+
+        This is used to generate the README of the BioImage Model Zoo export.
+
+        Returns
+        -------
+        str
+            Algorithm references.
+        """
+        return N2N_REF.text + " doi: " + N2N_REF.doi
+
+    def get_algorithm_citations(self) -> list[CiteEntry]:
+        """
+        Return a list of citation entries of the current algorithm.
+
+        This is used to generate the model description for the BioImage Model Zoo.
+
+        Returns
+        -------
+        List[CiteEntry]
+            List of citation entries.
+        """
+        return [N2N_REF]
+
+    def get_algorithm_description(self) -> str:
+        """
+        Get the algorithm description.
+
+        Returns
+        -------
+        str
+            Algorithm description.
+        """
+        return N2N_DESCRIPTION

careamics/config/algorithms/n2v_algorithm_model.py

@@ -2,9 +2,13 @@
 
 from typing import Annotated, Literal
 
-from pydantic import AfterValidator
+from bioimageio.spec.generic.v0_3 import CiteEntry
+from pydantic import AfterValidator, ConfigDict, model_validator
+from typing_extensions import Self
 
 from careamics.config.architectures import UNetModel
+from careamics.config.support import SupportedPixelManipulation, SupportedStructAxis
+from careamics.config.transformations import N2VManipulateModel
 from careamics.config.validators import (
     model_matching_in_out_channels,
     model_without_final_activation,
@@ -12,18 +16,282 @@ from careamics.config.validators import (
 
 from .unet_algorithm_model import UNetBasedAlgorithm
 
+N2V = "Noise2Void"
+N2V2 = "N2V2"
+STRUCT_N2V = "StructN2V"
+STRUCT_N2V2 = "StructN2V2"
+
+N2V_REF = CiteEntry(
+    text='Krull, A., Buchholz, T.O. and Jug, F., 2019. "Noise2Void - Learning '
+    'denoising from single noisy images". In Proceedings of the IEEE/CVF '
+    "conference on computer vision and pattern recognition (pp. 2129-2137).",
+    doi="10.1109/cvpr.2019.00223",
+)
+
+N2V2_REF = CiteEntry(
+    text="Höck, E., Buchholz, T.O., Brachmann, A., Jug, F. and Freytag, A., "
+    '2022. "N2V2 - Fixing Noise2Void checkerboard artifacts with modified '
+    'sampling strategies and a tweaked network architecture". In European '
+    "Conference on Computer Vision (pp. 503-518).",
+    doi="10.1007/978-3-031-25069-9_33",
+)
+
+STRUCTN2V_REF = CiteEntry(
+    text="Broaddus, C., Krull, A., Weigert, M., Schmidt, U. and Myers, G., 2020."
+    '"Removing structured noise with self-supervised blind-spot '
+    'networks". In 2020 IEEE 17th International Symposium on Biomedical '
+    "Imaging (ISBI) (pp. 159-163).",
+    doi="10.1109/isbi45749.2020.9098336",
+)
+
+N2V_DESCRIPTION = (
+    "Noise2Void is a UNet-based self-supervised algorithm that "
+    "uses blind-spot training to denoise images. In short, in every "
+    "patches during training, random pixels are selected and their "
+    "value replaced by a neighboring pixel value. The network is then "
+    "trained to predict the original pixel value. The algorithm "
+    "relies on the continuity of the signal (neighboring pixels have "
+    "similar values) and the pixel-wise independence of the noise "
+    "(the noise in a pixel is not correlated with the noise in "
+    "neighboring pixels)."
+)
+
+N2V2_DESCRIPTION = (
+    "N2V2 is a variant of Noise2Void. "
+    + N2V_DESCRIPTION
+    + "\nN2V2 introduces blur-pool layers and removed skip "
+    "connections in the UNet architecture to remove checkboard "
+    "artefacts, a common artefacts ocurring in Noise2Void."
+)
+
+STR_N2V_DESCRIPTION = (
+    "StructN2V is a variant of Noise2Void. "
+    + N2V_DESCRIPTION
+    + "\nStructN2V uses a linear mask (horizontal or vertical) to replace "
+    "the pixel values of neighbors of the masked pixels by a random "
+    "value. Such masking allows removing 1D structured noise from the "
+    "the images, the main failure case of the original N2V."
+)
+
+STR_N2V2_DESCRIPTION = (
+    "StructN2V2 is a a variant of Noise2Void that uses both "
+    "structN2V and N2V2. "
+    + N2V_DESCRIPTION
+    + "\nStructN2V2 uses a linear mask (horizontal or vertical) to replace "
+    "the pixel values of neighbors of the masked pixels by a random "
+    "value. Such masking allows removing 1D structured noise from the "
+    "the images, the main failure case of the original N2V."
+    "\nN2V2 introduces blur-pool layers and removed skip connections in "
+    "the UNet architecture to remove checkboard artefacts, a common "
+    "artefacts ocurring in Noise2Void."
+)
+
 
 class N2VAlgorithm(UNetBasedAlgorithm):
     """N2V Algorithm configuration."""
 
+    model_config = ConfigDict(validate_assignment=True)
+
     algorithm: Literal["n2v"] = "n2v"
     """N2V Algorithm name."""
 
     loss: Literal["n2v"] = "n2v"
     """N2V loss function."""
 
+    n2v_config: N2VManipulateModel = N2VManipulateModel()
+
     model: Annotated[
         UNetModel,
         AfterValidator(model_matching_in_out_channels),
         AfterValidator(model_without_final_activation),
     ]
+
+    @model_validator(mode="after")
+    def validate_n2v2(self) -> Self:
+        """Validate that the N2V2 strategy and models are set correctly.
+
+        Returns
+        -------
+        Self
+            The validateed configuration.
+
+        Raises
+        ------
+        ValueError
+            If N2V2 is used with the wrong pixel manipulation strategy.
+        """
+        if self.model.n2v2:
+            if self.n2v_config.strategy != SupportedPixelManipulation.MEDIAN.value:
+                raise ValueError(
+                    f"N2V2 can only be used with the "
+                    f"{SupportedPixelManipulation.MEDIAN} pixel manipulation strategy. "
+                    f"Change the `strategy` parameters in `n2v_config` to "
+                    f"{SupportedPixelManipulation.MEDIAN}."
+                )
+        else:
+            if self.n2v_config.strategy != SupportedPixelManipulation.UNIFORM.value:
+                raise ValueError(
+                    f"N2V can only be used with the "
+                    f"{SupportedPixelManipulation.UNIFORM} pixel manipulation strategy."
+                    f" Change the `strategy` parameters in `n2v_config` to "
+                    f"{SupportedPixelManipulation.UNIFORM}."
+                )
+        return self
+
+    def set_n2v2(self, use_n2v2: bool) -> None:
+        """
+        Set the configuration to use N2V2 or the vanilla Noise2Void.
+
+        This method ensures that N2V2 is set correctly and remain coherent, as opposed
+        to setting the different parameters individually.
+
+        Parameters
+        ----------
+        use_n2v2 : bool
+            Whether to use N2V2.
+        """
+        if use_n2v2:
+            self.n2v_config.strategy = SupportedPixelManipulation.MEDIAN.value
+            self.model.n2v2 = True
+        else:
+            self.n2v_config.strategy = SupportedPixelManipulation.UNIFORM.value
+            self.model.n2v2 = False
+
+    def is_struct_n2v(self) -> bool:
+        """Check if the configuration is using structN2V.
+
+        Returns
+        -------
+        bool
+            Whether the configuration is using structN2V.
+        """
+        return self.n2v_config.struct_mask_axis != SupportedStructAxis.NONE.value
+
+    def get_algorithm_friendly_name(self) -> str:
+        """
+        Get the friendly name of the algorithm.
+
+        Returns
+        -------
+        str
+            Friendly name.
+        """
+        use_n2v2 = self.model.n2v2
+        use_structN2V = self.is_struct_n2v()
+
+        if use_n2v2 and use_structN2V:
+            return STRUCT_N2V2
+        elif use_n2v2:
+            return N2V2
+        elif use_structN2V:
+            return STRUCT_N2V
+        else:
+            return N2V
+
+    def get_algorithm_keywords(self) -> list[str]:
+        """
+        Get algorithm keywords.
+
+        Returns
+        -------
+        list[str]
+            List of keywords.
+        """
+        use_n2v2 = self.model.n2v2
+        use_structN2V = self.is_struct_n2v()
+
+        keywords = [
+            "denoising",
+            "restoration",
+            "UNet",
+            "3D" if self.model.is_3D() else "2D",
+            "CAREamics",
+            "pytorch",
+            N2V,
+        ]
+
+        if use_n2v2:
+            keywords.append(N2V2)
+        if use_structN2V:
+            keywords.append(STRUCT_N2V)
+
+        return keywords
+
+    def get_algorithm_references(self) -> str:
+        """
+        Get the algorithm references.
+
+        This is used to generate the README of the BioImage Model Zoo export.
+
+        Returns
+        -------
+        str
+            Algorithm references.
+        """
+        use_n2v2 = self.model.n2v2
+        use_structN2V = self.is_struct_n2v()
+
+        references = [
+            N2V_REF.text + " doi: " + N2V_REF.doi,
+            N2V2_REF.text + " doi: " + N2V2_REF.doi,
+            STRUCTN2V_REF.text + " doi: " + STRUCTN2V_REF.doi,
+        ]
+
+        # return the (struct)N2V(2) references
+        if use_n2v2 and use_structN2V:
+            return "\n".join(references)
+        elif use_n2v2:
+            references.pop(-1)
+            return "\n".join(references)
+        elif use_structN2V:
+            references.pop(-2)
+            return "\n".join(references)
+        else:
+            return references[0]
+
+    def get_algorithm_citations(self) -> list[CiteEntry]:
+        """
+        Return a list of citation entries of the current algorithm.
+
+        This is used to generate the model description for the BioImage Model Zoo.
+
+        Returns
+        -------
+        List[CiteEntry]
+            List of citation entries.
+        """
+        use_n2v2 = self.model.n2v2
+        use_structN2V = self.is_struct_n2v()
+
+        references = [N2V_REF]
+
+        if use_n2v2:
+            references.append(N2V2_REF)
+
+        if use_structN2V:
+            references.append(STRUCTN2V_REF)
+
+        return references
+
+    def get_algorithm_description(self) -> str:
+        """
+        Return a description of the algorithm.
+
+        This method is used to generate the README of the BioImage Model Zoo export.
+
+        Returns
+        -------
+        str
+            Description of the algorithm.
+        """
+        use_n2v2 = self.model.n2v2
+        use_structN2V = self.is_struct_n2v()
+
+        if use_n2v2 and use_structN2V:
+            return STR_N2V2_DESCRIPTION
+        elif use_n2v2:
+            return N2V2_DESCRIPTION
+        elif use_structN2V:
+            return STR_N2V_DESCRIPTION
+        else:
+            return N2V_DESCRIPTION

careamics/config/configuration.py

@@ -10,10 +10,20 @@ from bioimageio.spec.generic.v0_3 import CiteEntry
 from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 from typing_extensions import Self
 
-from careamics.config.algorithms import UNetBasedAlgorithm, VAEBasedAlgorithm
-from careamics.config.data import GeneralDataConfig
+from careamics.config.algorithms import (
+    CAREAlgorithm,
+    N2NAlgorithm,
+    N2VAlgorithm,
+)
+from careamics.config.data import DataConfig
 from careamics.config.training_model import TrainingConfig
 
+ALGORITHMS = Union[
+    CAREAlgorithm,
+    N2NAlgorithm,
+    N2VAlgorithm,
+]
+
 
 class Configuration(BaseModel):
     """
@@ -87,7 +97,7 @@ class Configuration(BaseModel):
     Examples
     --------
     Minimum example:
-    >>> from careamics import configuration_factory
+    >>> from careamics import Configuration
     >>> config_dict = {
     ...         "experiment_name": "N2V_experiment",
     ...         "algorithm_config": {
@@ -106,7 +116,7 @@ class Configuration(BaseModel):
     ...             "axes": "SYX",
     ...         },
     ...     }
-    >>> config = configuration_factory(config_dict)
+    >>> config = Configuration(**config_dict)
     """
 
     model_config = ConfigDict(
@@ -123,13 +133,11 @@ class Configuration(BaseModel):
     """Name of the experiment, used to name logs and checkpoints."""
 
     # Sub-configurations
-    algorithm_config: Union[UNetBasedAlgorithm, VAEBasedAlgorithm] = Field(
-        discriminator="algorithm"
-    )
+    algorithm_config: ALGORITHMS = Field(discriminator="algorithm")
     """Algorithm configuration, holding all parameters required to configure the
     model."""
 
-    data_config: GeneralDataConfig
+    data_config: DataConfig
     """Data configuration, holding all parameters required to configure the training
     data loader."""
 
@@ -233,7 +241,7 @@ class Configuration(BaseModel):
         str
             Algorithm name.
         """
-        raise ValueError("Unknown algorithm.")
+        return self.algorithm_config.get_algorithm_friendly_name()
 
     def get_algorithm_description(self) -> str:
         """
@@ -246,7 +254,7 @@ class Configuration(BaseModel):
         str
             Description of the algorithm.
         """
-        raise ValueError("No algorithm description available.")
+        return self.algorithm_config.get_algorithm_description()
 
     def get_algorithm_citations(self) -> list[CiteEntry]:
         """
@@ -259,7 +267,7 @@ class Configuration(BaseModel):
         List[CiteEntry]
             List of citation entries.
         """
-        raise ValueError("No algorithm citations available.")
+        return self.algorithm_config.get_algorithm_citations()
 
     def get_algorithm_references(self) -> str:
         """
@@ -272,7 +280,7 @@ class Configuration(BaseModel):
         str
             Algorithm references.
         """
-        raise ValueError("No algorithm references available.")
+        return self.algorithm_config.get_algorithm_references()
 
     def get_algorithm_keywords(self) -> list[str]:
         """
@@ -283,7 +291,7 @@ class Configuration(BaseModel):
         list[str]
             List of keywords.
         """
-        return ["CAREamics"]
+        return self.algorithm_config.get_algorithm_keywords()
 
     def model_dump(
         self,