Augmentations
CAREamics transformation Pydantic models.
NORM_AND_SPATIAL_UNION = Annotated[Union[NormalizeConfig, XYFlipConfig, XYRandomRotate90Config], Discriminator('name')]
module-attribute
All transforms including normalization.
SPATIAL_TRANSFORMS_UNION = Annotated[Union[XYFlipConfig, XYRandomRotate90Config], Discriminator('name')]
module-attribute
Available spatial transforms in CAREamics.
N2VManipulateConfig
Bases: TransformConfig
Pydantic model used to represent N2V manipulation.
Attributes:
| Name | Type | Description |
|---|---|---|
name |
Literal['N2VManipulate']
|
Name of the transformation. |
roi_size |
int
|
Size of the masking region, by default 11. |
masked_pixel_percentage |
float
|
Percentage of masked pixels, by default 0.2. |
strategy |
Literal['uniform', 'median']
|
Strategy pixel value replacement, by default "uniform". |
struct_mask_axis |
Literal['horizontal', 'vertical', 'none']
|
Axis of the structN2V mask, by default "none". |
struct_mask_span |
int
|
Span of the structN2V mask, by default 5. |
seed |
int
|
Random seed for reproducibility. |
masked_pixel_percentage = Field(default=0.2, ge=0.05, le=10.0)
class-attribute
instance-attribute
Percentage of masked pixels per image.
roi_size = Field(default=11, ge=3, le=21)
class-attribute
instance-attribute
Size of the region where the pixel manipulation is applied.
seed = Field(default_factory=generate_random_seed, gt=0)
class-attribute
instance-attribute
Random seed for reproducibility. If not specified, a random seed is generated.
strategy = Field(default='uniform')
class-attribute
instance-attribute
Strategy for pixel value replacement.
struct_mask_axis = Field(default='none')
class-attribute
instance-attribute
Orientation of the structN2V mask. Set to "non" to not apply StructN2V.
struct_mask_span = Field(default=5, ge=3, le=15)
class-attribute
instance-attribute
Size of the structN2V mask.
model_dump(**kwargs)
odd_value(v)
classmethod
Validate that the value is odd.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
v
|
int
|
Value to validate. |
required |
Returns:
| Type | Description |
|---|---|
int
|
The validated value. |
Raises:
| Type | Description |
|---|---|
ValueError
|
If the value is even. |
NormalizeConfig
Bases: TransformConfig
Pydantic model used to represent Normalize transformation.
The Normalize transform is a zero mean and unit variance transformation.
Attributes:
| Name | Type | Description |
|---|---|---|
name |
Literal['Normalize']
|
Name of the transformation. |
mean |
float
|
Mean value for normalization. |
std |
float
|
Standard deviation value for normalization. |
model_dump(**kwargs)
validate_means_stds()
Validate that the means and stds have the same length.
Returns:
| Type | Description |
|---|---|
Self
|
The instance of the model. |
TransformConfig
Bases: BaseModel
Pydantic model used to represent a transformation.
The model_dump method is overwritten to exclude the name field.
Attributes:
| Name | Type | Description |
|---|---|---|
name |
str
|
Name of the transformation. |
XYFlipConfig
Bases: TransformConfig
Pydantic model used to represent XYFlip transformation.
Attributes:
| Name | Type | Description |
|---|---|---|
name |
Literal['XYFlip']
|
Name of the transformation. |
p |
float
|
Probability of applying the transform, by default 0.5. |
seed |
Optional[int]
|
Seed for the random number generator, by default None. |
XYRandomRotate90Config
Bases: TransformConfig
Pydantic model used to represent the XY random 90 degree rotation transformation.
Attributes:
| Name | Type | Description |
|---|---|---|
name |
Literal['XYRandomRotate90']
|
Name of the transformation. |
p |
float
|
Probability of applying the transform, by default 0.5. |
seed |
Optional[int]
|
Seed for the random number generator, by default None. |