Plate Config
License Plate OCR config. This config file defines how license plate images and text should be preprocessed for OCR model training and inference.
PlateOCRConfig ¶
Bases: BaseModel
Model License Plate OCR config.
max_plate_slots
instance-attribute
¶
Max number of plate slots supported. This represents the number of model classification heads.
pad_char
instance-attribute
¶
Padding character for plates which length is smaller than MAX_PLATE_SLOTS.
keep_aspect_ratio
class-attribute
instance-attribute
¶
keep_aspect_ratio: bool = False
Keep aspect ratio of the input image.
interpolation
class-attribute
instance-attribute
¶
interpolation: ImageInterpolation = 'linear'
Interpolation method used for resizing the input image.
image_color_mode
class-attribute
instance-attribute
¶
image_color_mode: ImageColorMode = 'grayscale'
Input image color mode. Use 'grayscale' for single-channel input or 'rgb' for 3-channel input.
load_plate_config_from_yaml ¶
load_plate_config_from_yaml(
yaml_path: PathLike,
) -> PlateOCRConfig
Reads and parses a YAML file containing the plate configuration.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
yaml_path
|
PathLike
|
Path to the YAML file containing the plate config. |
required |
Returns:
Name | Type | Description |
---|---|---|
PlateOCRConfig |
PlateOCRConfig
|
Parsed and validated plate configuration. |
Raises:
Type | Description |
---|---|
FileNotFoundError
|
If the YAML file does not exist. |