Ssd#

class model_api.models.ssd.BoxesLabelsParser(layers, input_size, labels_layer='labels', default_label=0)#

Bases: object

__call__(outputs)#

Parse model outputs.

Note: Bounding boxes layer from outputs are expected to be in format [xmin, ymin, xmax, ymax, score].

Parameters:

outputs (dict) – Model outputs wrapped in dict.

Returns:

Parsed model outputs.

Return type:

DetectionResult

static find_layer_bboxes_output(layers)#
class model_api.models.ssd.MultipleOutputParser(layers, bboxes_layer='bboxes', scores_layer='scores', labels_layer='labels')#

Bases: object

__call__(outputs)#

Parse model outputs.

Parameters:

outputs (dict) – Model outputs wrapped in dict.

Returns:

Parsed model outputs.

Return type:

DetectionResult

class model_api.models.ssd.SSD(inference_adapter, configuration={}, preload=False)#

Bases: DetectionModel

Detection Model constructor

It extends the ImageModel construtor.

Parameters:

  • inference_adapter (InferenceAdapter) – allows working with the specified executor

  • configuration (dict, optional) – it contains values for parameters accepted by specific wrapper (confidence_threshold, labels etc.) which are set as data attributes

  • preload (bool, optional) – a flag whether the model is loaded to device while initialization. If preload=False, the model must be loaded via load method before inference

Raises:

WrapperError – if the model has more than 1 image inputs

postprocess(outputs, meta)#

Interface for postprocess method.

Parameters:

  • outputs (dict) –

    model raw output in the following format: {

    ’output_layer_name_1’: raw_result_1, ‘output_layer_name_2’: raw_result_2, …

    }

  • meta (dict) – the input metadata obtained from preprocess method

Return type:

DetectionResult

Returns:

  • postprocessed data in the format defined by wrapper

preprocess(dict_inputs, meta)#

Interface for preprocess hook.

Parameters:

  • dict_inputs (dict) – preprocessed data

  • meta (dict) – input metadata

Return type:

tuple[dict, dict]

Returns:

  • the preprocessed data

  • the input metadata

class model_api.models.ssd.SingleOutputParser(all_outputs)#

Bases: object

__call__(outputs)#

Parse model outputs.

Parameters:

outputs (dict) – Model outputs wrapped in dict.

Returns:

Parsed model outputs.

Return type:

DetectionResult

model_api.models.ssd.find_layer_by_name(name, layers)#