Semantic Segmentation

class model_api.tilers.semantic_segmentation.SemanticSegmentationTiler(model, configuration={}, execution_mode='async')

Bases: Tiler

Tiler for segmentation models.

Base constructor for creating a tiling pipeline

Parameters:

• model – underlying model

• configuration (dict) – it contains values for parameters accepted by specific tiler (tile_size, tiles_overlap etc.) which are set as data attributes.

• execution_mode (str) – Controls inference mode of the tiler (async or sync).

__call__(inputs)

Applies full pipeline of tiling inference in one call.

Parameters:

inputs – raw input data, the data type is defined by underlying model wrapper

Returns:

• postprocessed data in the format defined by underlying model wrapper