frameworks.ultralytics.parameters.augmentation_parameters¶
augmentation_parameters
¶
Classes:
| Name | Description |
|---|---|
UltralyticsAugmentationParameters |
Defines data augmentation parameters for Ultralytics-based training. |
UltralyticsAugmentationParameters(log_data)
¶
Bases: AugmentationParameters
Defines data augmentation parameters for Ultralytics-based training.
This class extracts and validates augmentation parameters from Picsellia logs.
Each parameter is automatically parsed and type-checked using extract_parameter.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
|
LogDataType
|
The dictionary of logged parameters from the Picsellia platform. |
required |
Methods:
| Name | Description |
|---|---|
extract_parameter |
Extract a parameter using keys, type, optional default, and optional value range. |
to_dict |
Return parameters as a dictionary, excluding internal fields. |
validate_log_data |
Validate and return log data if it's a dictionary. |
Attributes:
| Name | Type | Description |
|---|---|---|
hsv_h |
|
|
hsv_s |
|
|
hsv_v |
|
|
degrees |
|
|
translate |
|
|
scale |
|
|
shear |
|
|
perspective |
|
|
flipud |
|
|
fliplr |
|
|
bgr |
|
|
mosaic |
|
|
mixup |
|
|
copy_paste |
|
|
auto_augment |
|
|
erasing |
|
|
crop_fraction |
|
|
parameters_data |
|
|
defaulted_keys |
set[str]
|
|
hsv_h = self.extract_parameter(keys=['hsv_h'], expected_type=float, default=0.015, range_value=(0.0, 1.0))
instance-attribute
¶
hsv_s = self.extract_parameter(keys=['hsv_s'], expected_type=float, default=0.7, range_value=(0.0, 1.0))
instance-attribute
¶
hsv_v = self.extract_parameter(keys=['hsv_v'], expected_type=float, default=0.4, range_value=(0.0, 1.0))
instance-attribute
¶
degrees = self.extract_parameter(keys=['degrees'], expected_type=float, default=0.0, range_value=(-180.0, 180.0))
instance-attribute
¶
translate = self.extract_parameter(keys=['translate'], expected_type=float, default=0.1, range_value=(0.0, 1.0))
instance-attribute
¶
scale = self.extract_parameter(keys=['scale'], expected_type=float, default=0.5, range_value=(0.0, float('inf')))
instance-attribute
¶
shear = self.extract_parameter(keys=['shear'], expected_type=float, default=0.0, range_value=(-180.0, 180.0))
instance-attribute
¶
perspective = self.extract_parameter(keys=['perspective'], expected_type=float, default=0.0, range_value=(0.0, 0.001))
instance-attribute
¶
flipud = self.extract_parameter(keys=['flipud'], expected_type=float, default=0.0, range_value=(0.0, 1.0))
instance-attribute
¶
fliplr = self.extract_parameter(keys=['fliplr'], expected_type=float, default=0.5, range_value=(0.0, 1.0))
instance-attribute
¶
bgr = self.extract_parameter(keys=['bgr'], expected_type=float, default=0.0, range_value=(0.0, 1.0))
instance-attribute
¶
mosaic = self.extract_parameter(keys=['mosaic'], expected_type=float, default=1.0, range_value=(0.0, 1.0))
instance-attribute
¶
mixup = self.extract_parameter(keys=['mixup'], expected_type=float, default=0.0, range_value=(0.0, 1.0))
instance-attribute
¶
copy_paste = self.extract_parameter(keys=['copy_paste'], expected_type=float, default=0.0, range_value=(0.0, 1.0))
instance-attribute
¶
auto_augment = self.extract_parameter(keys=['auto_augment'], expected_type=str, default='randaugment')
instance-attribute
¶
erasing = self.extract_parameter(keys=['erasing'], expected_type=float, default=0.4, range_value=(0.0, 1.0))
instance-attribute
¶
crop_fraction = self.extract_parameter(keys=['crop_fraction'], expected_type=float, default=1.0, range_value=(0.1, 1.0))
instance-attribute
¶
parameters_data = self.validate_log_data(log_data)
instance-attribute
¶
defaulted_keys = set()
instance-attribute
¶
extract_parameter(keys, expected_type, default=..., range_value=None)
¶
extract_parameter(keys: list, expected_type: type[T], default: Any = ..., range_value: tuple[Any, Any] | None = None) -> T
extract_parameter(keys: list, expected_type: Any, default: Any = ..., range_value: tuple[Any, Any] | None = None) -> Any
Extract a parameter using keys, type, optional default, and optional value range.
Examples:
Extract a required string parameter that cannot be None:
parameter = self.extract_parameter(keys=["key1", "key2"], expected_type=str)
Extract a required integer parameter that can be None:
parameter = self.extract_parameter(keys=["key1"], expected_type=int | None)
Extract an optional float parameter within a specific range:
parameter = self.extract_parameter(keys=["key1"], expected_type=float, default=0.5, range_value=(0.0, 1.0))
Extract an optional string parameter with a default value:
parameter = self.extract_parameter(keys=["key1"], expected_type=str, default="default_value")
Extract an optional string parameter that can be None:
parameter = self.extract_parameter(keys=["key1"], expected_type=Union[str, None], default=None)
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
|
list
|
A list of possible keys to extract the parameter. |
required |
|
type[T]
|
The expected type of the parameter, can use Union for optional types. |
required |
|
Any
|
The default value if the parameter is not found. Use ... for required parameters. |
...
|
|
tuple[Any, Any] | None
|
A tuple of two numbers representing the allowed range of the parameter. |
None
|
Returns:
| Type | Description |
|---|---|
Any
|
The parsed parameter. |
to_dict()
¶
Return parameters as a dictionary, excluding internal fields.
validate_log_data(log_data)
¶
Validate and return log data if it's a dictionary.