BuildingVectorOutputConfig#

Note

All Configs are derived from rastervision.pipeline.config.Config, which itself is a pydantic Model.

pydantic model BuildingVectorOutputConfig[source]#

Config for vectorized semantic segmentation predictions.

Intended to break up clusters of buildings.

Show JSON schema
{
   "title": "BuildingVectorOutputConfig",
   "description": "Config for vectorized semantic segmentation predictions.\n\nIntended to break up clusters of buildings.",
   "type": "object",
   "properties": {
      "uri": {
         "title": "Uri",
         "description": "URI of vector output. If None, and this Config is part of a SceneConfig and RVPipeline, this field will be auto-generated.",
         "type": "string"
      },
      "class_id": {
         "title": "Class Id",
         "description": "The prediction class that is to turned into vectors.",
         "type": "integer"
      },
      "denoise": {
         "title": "Denoise",
         "description": "Radius of the structural element used to remove high-frequency signals from the image. Smaller values will reduce less noise and make vectorization slower (especially for large images). Larger values will remove more noise and make vectorization faster but might also remove legitimate detections.",
         "default": 8,
         "type": "integer"
      },
      "type_hint": {
         "title": "Type Hint",
         "default": "building_vector_output",
         "enum": [
            "building_vector_output"
         ],
         "type": "string"
      },
      "min_area": {
         "title": "Min Area",
         "description": "Minimum area (in pixels^2) of anything that can be considered to be a building or a cluster of buildings. The goal is to distinguish between buildings and artifacts.",
         "default": 0.0,
         "type": "number"
      },
      "element_width_factor": {
         "title": "Element Width Factor",
         "description": "Width of the structural element used to break building clusters as a fraction of the width of the cluster.",
         "default": 0.5,
         "type": "number"
      },
      "element_thickness": {
         "title": "Element Thickness",
         "description": "Thickness of the structural element that is used to break building clusters.",
         "default": 0.001,
         "type": "number"
      }
   },
   "required": [
      "class_id"
   ],
   "additionalProperties": false
}

Config

  • extra: str = forbid

  • validate_assignment: bool = True

Fields
field class_id: int [Required]#

The prediction class that is to turned into vectors.

field denoise: int = 8#

Radius of the structural element used to remove high-frequency signals from the image. Smaller values will reduce less noise and make vectorization slower (especially for large images). Larger values will remove more noise and make vectorization faster but might also remove legitimate detections.

field element_thickness: float = 0.001#

Thickness of the structural element that is used to break building clusters.

field element_width_factor: float = 0.5#

Width of the structural element used to break building clusters as a fraction of the width of the cluster.

field min_area: float = 0.0#

Minimum area (in pixels^2) of anything that can be considered to be a building or a cluster of buildings. The goal is to distinguish between buildings and artifacts.

field type_hint: Literal['building_vector_output'] = 'building_vector_output'#
field uri: Optional[str] = None#

URI of vector output. If None, and this Config is part of a SceneConfig and RVPipeline, this field will be auto-generated.

build()#

Build an instance of the corresponding type of object using this config.

For example, BackendConfig will build a Backend object. The arguments to this method will vary depending on the type of Config.

get_mode() → str[source]#
Return type

str

recursive_validate_config()#

Recursively validate hierarchies of Configs.

This uses reflection to call validate_config on a hierarchy of Configs using a depth-first pre-order traversal.

revalidate()#

Re-validate an instantiated Config.

Runs all Pydantic validators plus self.validate_config().

Adapted from: https://github.com/samuelcolvin/pydantic/issues/1864#issuecomment-679044432

update(pipeline: Optional[RVPipelineConfig] = None, scene: Optional[SceneConfig] = None, uri_prefix: Optional[str] = None)#

Update any fields before validation.

Subclasses should override this to provide complex default behavior, for example, setting default values as a function of the values of other fields. The arguments to this method will vary depending on the type of Config.

Parameters
validate_config()#

Validate fields that should be checked after update is called.

This is to complement the builtin validation that Pydantic performs at the time of object construction.

validate_list(field: str, valid_options: List[str])#

Validate a list field.

Parameters

  • field (str) – name of field to validate

  • valid_options (List[str]) – values that field is allowed to take

Raises

ConfigError – if field is invalid