Yolo#

class model_api.models.yolo.DetectionBox(x, y, w, h)#

Bases: tuple

Create new instance of DetectionBox(x, y, w, h)

h#

Alias for field number 3

w#

Alias for field number 2

x#

Alias for field number 0

y#

Alias for field number 1

class model_api.models.yolo.YOLO(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

class Params(param, sides)#

Bases: object

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

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

class model_api.models.yolo.YOLOF(inference_adapter, configuration={}, preload=False)#

Bases: YOLO

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

class Params(classes, num, sides, anchors)#

Bases: object

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

class model_api.models.yolo.YOLOX(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

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

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

set_strides_grids()#
class model_api.models.yolo.YOLOv5(inference_adapter, configuration, preload=False)#

Bases: DetectionModel

Reimplementation of ultralytics.YOLO

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

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

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

class model_api.models.yolo.YOLOv8(inference_adapter, configuration, preload=False)#

Bases: YOLOv5

YOLOv5 and YOLOv8 are identical in terms of inference

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

class model_api.models.yolo.YoloV3ONNX(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

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

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.yolo.YoloV4(inference_adapter, configuration={}, preload=False)#

Bases: YOLO

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

class Params(classes, num, sides, anchors, mask, layout)#

Bases: object

classmethod parameters()#

Defines the description and type of configurable data parameters for the wrapper.

See types.py to find available types of the data parameter. For each parameter the type, default value and description must be provided.

The example of possible data parameter:
‘confidence_threshold’: NumericalValue(

default_value=0.5, description=”Threshold value for detection box confidence”

)

The method must be implemented in each specific inherited wrapper.

Returns:

  • the dictionary with defined wrapper data parameters

model_api.models.yolo.permute_to_N_HWA_K(tensor, K, output_layout)#

Transpose/reshape a tensor from (N, (A x K), H, W) to (N, (HxWxA), K)

model_api.models.yolo.sigmoid(x)#
model_api.models.yolo.xywh2xyxy(xywh)#