Postprocessor Module

PySDK API Reference Guide. InferenceResults containers.

This API Reference is based on PySDK 0.17.1.

degirum.postprocessor.InferenceResults

Inference results container class.

This class is a base class for a set of classes designed to handle inference results of particular model types such as classification, detection etc.

You never construct model objects yourself. Objects of those classes are returned by various predict methods of degirum.model.Model class.

image

degirum.postprocessor.InferenceResults.image

property

Original image.

Returned image object type is defined by the selected graphical backend (see degirum.model.Model.image_backend).

image_model

degirum.postprocessor.InferenceResults.image_model

property

Model input image data: image converted to AI model input specifications.

Image type is raw binary array.

image_overlay

degirum.postprocessor.InferenceResults.image_overlay

property

Image with AI inference results drawn on top of the original image.

Drawing details depend on the inference result type:

• For classification models the list of class labels with probabilities is printed below the original image.

• For object detection models bounding boxes of detected object are drawn on the original image.

• For pose detection models detected keypoints and keypoint connections are drawn on the original image.

• For segmentation models detected segments are drawn on the original image.

Returned image object type is defined by the selected graphical backend (see degirum.model.Model.image_backend).

info

degirum.postprocessor.InferenceResults.info

property

Input data frame information object.

overlay_alpha

degirum.postprocessor.InferenceResults.overlay_alpha

property writable

Alpha-blend weight for overlay details.

overlay_blur

degirum.postprocessor.InferenceResults.overlay_blur

property writable

Overlay blur option. None for no blur, "all" to blur all objects, a class label or list of class labels to blur specific objects.

overlay_color

degirum.postprocessor.InferenceResults.overlay_color

property writable

Color for inference results drawing on overlay image.

3-element RGB tuple or list of 3-element RGB tuples.

overlay_fill_color

degirum.postprocessor.InferenceResults.overlay_fill_color

property writable

Image fill color in case of image padding.

3-element RGB tuple.

overlay_font_scale

degirum.postprocessor.InferenceResults.overlay_font_scale

property writable

Font scale to use for overlay text.

overlay_line_width

degirum.postprocessor.InferenceResults.overlay_line_width

property writable

Line width in pixels for inference results drawing on overlay image.

overlay_show_labels

degirum.postprocessor.InferenceResults.overlay_show_labels

property writable

Specifies if class labels should be drawn on overlay image.

overlay_show_probabilities

degirum.postprocessor.InferenceResults.overlay_show_probabilities

property writable

Specifies if class probabilities should be drawn on overlay image.

results

degirum.postprocessor.InferenceResults.results

property

Inference results list.

Each element of the list is a dictionary containing information about one inference result. The dictionary contents depends on the AI model.

For classification models each inference result dictionary contains the following keys:

• category_id: class numeric ID.

• label: class label string.

• score: class probability.

Example

[
    {'category_id': 0, 'label': 'cat', 'score': 0.99},
    {'category_id': 1, 'label': 'dog', 'score': 0.01}
]

For multi-label classification models each inference result dictionary contains the following keys:

• classifier: object class string.

• results: list of class labels and its scores. Scores are optional.

The results list element is a dictionary with the following keys:

• label: class label string.

• score: optional class label probability.

Example

[
    {
        'classifier': 'vehicle color',
        'results': [
            {'label': 'red', 'score': 0.99},
            {'label': 'blue', 'score': 0.01}
         ]
    },
    {
        'classifier': 'vehicle type',
        'results': [
            {'label': 'car', 'score': 0.99},
            {'label': 'truck', 'score': 0.01}
        ]
    }
]

For object detection models each inference result dictionary may contain the following keys:

• category_id: detected object class numeric ID.

• label: detected object class label string.

• score: detected object probability.

• bbox: detected object bounding box list [xtop, ytop, xbot, ybot].

• landmarks: optional list of keypoints or landmarks. It is the list of dictionaries, one per each keypoint/landmark.

• mask: optional dictionary of run-length encoded (RLE) object segmentation mask array representation.

• angle: optional angle (in radians) for rotating bounding box around its center. This is used in the case of oriented bounding boxes.

The landmarks list is defined for special cases like pose detection of face points detection results. Each landmarks list element is a dictionary with the following keys:

• category_id: keypoint numeric ID.

• label: keypoint label string.

• score: keypoint detection probability.

• landmark: keypoint coordinate list [x,y,visibility,a,b,...].

• connect: optional list of IDs of connected keypoints.

The mask dictionary is defined for the special case of object segmentation results, with the following keys:

• x_min: x-coordinate in the model input image at which the top-left corner of the box enclosing this mask should be placed.

• y_min: y-coordinate in the model input image at which the top-left corner of the box enclosing this mask should be placed.

• height: height of segmentation mask array

• width: width of segmentation mask array

• data: string representation of a buffer of unsigned 32-bit integers carrying the RLE segmentation mask array.

The object detection keys (bbox, score, label, and category_id) must be either all present or all absent. In the former case the result format is suitable to represent pure object detection results. In the later case, one of the following keys must be present:

• the landmarks key

• the mask key

The following statements are then true:

• If the landmarks key is present, the result format is suitable to represent pure landmark detection results, such as pose detection.

• If the mask key is present, the result format is suitable to represent pure segmentation results. If, optionally, the category_id key is also present, the result format is suitable to represent semantic segmentation results.

When both object detection keys and the landmarks key are present, the result format is suitable to represent mixed model results, when the model detects not only object bounding boxes, but also keypoints/landmarks within the bounding box.

When both object detection keys and the mask key are present, the result format is suitable to represent mixed model results, when the model detects not only object bounding boxes, but also segmentation masks within the bounding box (i.e. instance segmentation).

Example of pure object detection results:

Example

[
    {'category_id': 0, 'label': 'cat', 'score': 0.99, 'bbox': [10, 20, 100, 200]},
    {'category_id': 1, 'label': 'dog', 'score': 0.01, 'bbox': [200, 100, 300, 400]}
]

Example of oriented object detection results:

Example

[
    {'category_id': 0, 'label': 'car', 'score': 0.99, 'bbox': [10, 20, 100, 200], 'angle': 0.79}
]

Example of landmark object detection results:

Example

[
    {
        'landmarks': [
            {'category_id': 0, 'label': 'Nose', 'score': 0.99, 'landmark': [10, 20]},
            {'category_id': 1, 'label': 'LeftEye', 'score': 0.98, 'landmark': [15, 25]},
            {'category_id': 2, 'label': 'RightEye', 'score': 0.97, 'landmark': [18, 28]}
        ]
    }
]

Example of segmented object detection results:

Example

[
    {
        'mask': {'x_min': 1, 'y_min': 1, 'height': 2, 'width': 2, 'data': 'AAAAAAEAAAAAAAAAAQAAAAIAAAABAAAA'}
    }
]

For hand palm detection models each inference result dictionary contains the following keys:

• score: probability of detected hand.

• handedness: probability of right hand.

• landmarks: list of dictionaries, one per each hand keypoint.

Each landmarks list element is a dictionary with the following keys:

• label: classified object class label.

• category_id: classified object class index.

• landmark: landmark point coordinate list [x, y, z].

• world_landmark: metric world landmark point coordinate list [x, y, z].

• connect: list of adjacent landmarks indexes.

Example

[
    {
        'score': 0.99,
        'handedness': 0.98,
        'landmarks': [
            {
                'label': 'Wrist',
                'category_id': 0,
                'landmark': [10, 20, 30],
                'world_landmark': [10, 20, 30],
                'connect': [1]
            },
            {
                'label': 'Thumb',
                'category_id': 1,
                'landmark': [15, 25, 35],
                'world_landmark': [15, 25, 35],
                'connect': [0]
            }
        ]
    }
]

For segmentation models inference result is a single-element list. That single element is a dictionary, containing single key data. The value of this key is 2D numpy array of integers, where each integer value represents a class ID of the corresponding pixel. The class IDs are defined by the model label dictionary.

Example

[
    {
        'data': numpy.array([
            [0, 0, 0, 1, 1, 1],
            [0, 0, 0, 1, 1, 1],
            [0, 0, 0, 1, 1, 1],
            [2, 2, 2, 3, 3, 3],
            [2, 2, 2, 3, 3, 3],
            [2, 2, 2, 3, 3, 3],
        ])
    }
]

generate_colors

degirum.postprocessor.InferenceResults.generate_colors()

staticmethod

Generate a list of unique RGB color tuples.

generate_overlay_color(num_classes, ...)

degirum.postprocessor.InferenceResults.generate_overlay_color(num_classes, label_dict)

staticmethod

Overlay colors generator.

Parameters:

Name	Type	Description	Default
num_classes	int	number of class categories.	required
label_dict	dict	Model labels dictionary.	required

Returns:

Type	Description
Union[list, tuple]	Overlay color tuple or list of tuples.

supported_types

degirum.postprocessor.InferenceResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._InferenceResults.InferenceResults

Inference results container class.

This class is a base class for a set of classes designed to handle inference results of particular model types such as classification, detection etc.

You never construct model objects yourself. Objects of those classes are returned by various predict methods of degirum.model.Model class.

image

degirum.postprocessor._InferenceResults.InferenceResults.image

property

Original image.

Returned image object type is defined by the selected graphical backend (see degirum.model.Model.image_backend).

image_model

degirum.postprocessor._InferenceResults.InferenceResults.image_model

property

Model input image data: image converted to AI model input specifications.

Image type is raw binary array.

image_overlay

degirum.postprocessor._InferenceResults.InferenceResults.image_overlay

property

Image with AI inference results drawn on top of the original image.

Drawing details depend on the inference result type:

• For classification models the list of class labels with probabilities is printed below the original image.

• For object detection models bounding boxes of detected object are drawn on the original image.

• For pose detection models detected keypoints and keypoint connections are drawn on the original image.

• For segmentation models detected segments are drawn on the original image.

Returned image object type is defined by the selected graphical backend (see degirum.model.Model.image_backend).

info

degirum.postprocessor._InferenceResults.InferenceResults.info

property

Input data frame information object.

overlay_alpha

degirum.postprocessor._InferenceResults.InferenceResults.overlay_alpha

property writable

Alpha-blend weight for overlay details.

overlay_blur

degirum.postprocessor._InferenceResults.InferenceResults.overlay_blur

property writable

Overlay blur option. None for no blur, "all" to blur all objects, a class label or list of class labels to blur specific objects.

overlay_color

degirum.postprocessor._InferenceResults.InferenceResults.overlay_color

property writable

Color for inference results drawing on overlay image.

3-element RGB tuple or list of 3-element RGB tuples.

overlay_fill_color

degirum.postprocessor._InferenceResults.InferenceResults.overlay_fill_color

property writable

Image fill color in case of image padding.

3-element RGB tuple.

overlay_font_scale

degirum.postprocessor._InferenceResults.InferenceResults.overlay_font_scale

property writable

Font scale to use for overlay text.

overlay_line_width

degirum.postprocessor._InferenceResults.InferenceResults.overlay_line_width

property writable

Line width in pixels for inference results drawing on overlay image.

overlay_show_labels

degirum.postprocessor._InferenceResults.InferenceResults.overlay_show_labels

property writable

Specifies if class labels should be drawn on overlay image.

overlay_show_probabilities

degirum.postprocessor._InferenceResults.InferenceResults.overlay_show_probabilities

property writable

Specifies if class probabilities should be drawn on overlay image.

results

degirum.postprocessor._InferenceResults.InferenceResults.results

property

Inference results list.

Each element of the list is a dictionary containing information about one inference result. The dictionary contents depends on the AI model.

For classification models each inference result dictionary contains the following keys:

• category_id: class numeric ID.

• label: class label string.

• score: class probability.

Example

[
    {'category_id': 0, 'label': 'cat', 'score': 0.99},
    {'category_id': 1, 'label': 'dog', 'score': 0.01}
]

For multi-label classification models each inference result dictionary contains the following keys:

• classifier: object class string.

• results: list of class labels and its scores. Scores are optional.

The results list element is a dictionary with the following keys:

• label: class label string.

• score: optional class label probability.

Example

[
    {
        'classifier': 'vehicle color',
        'results': [
            {'label': 'red', 'score': 0.99},
            {'label': 'blue', 'score': 0.01}
         ]
    },
    {
        'classifier': 'vehicle type',
        'results': [
            {'label': 'car', 'score': 0.99},
            {'label': 'truck', 'score': 0.01}
        ]
    }
]

For object detection models each inference result dictionary may contain the following keys:

• category_id: detected object class numeric ID.

• label: detected object class label string.

• score: detected object probability.

• bbox: detected object bounding box list [xtop, ytop, xbot, ybot].

• landmarks: optional list of keypoints or landmarks. It is the list of dictionaries, one per each keypoint/landmark.

• mask: optional dictionary of run-length encoded (RLE) object segmentation mask array representation.

• angle: optional angle (in radians) for rotating bounding box around its center. This is used in the case of oriented bounding boxes.

The landmarks list is defined for special cases like pose detection of face points detection results. Each landmarks list element is a dictionary with the following keys:

• category_id: keypoint numeric ID.

• label: keypoint label string.

• score: keypoint detection probability.

• landmark: keypoint coordinate list [x,y,visibility,a,b,...].

• connect: optional list of IDs of connected keypoints.

The mask dictionary is defined for the special case of object segmentation results, with the following keys:

• x_min: x-coordinate in the model input image at which the top-left corner of the box enclosing this mask should be placed.

• y_min: y-coordinate in the model input image at which the top-left corner of the box enclosing this mask should be placed.

• height: height of segmentation mask array

• width: width of segmentation mask array

• data: string representation of a buffer of unsigned 32-bit integers carrying the RLE segmentation mask array.

The object detection keys (bbox, score, label, and category_id) must be either all present or all absent. In the former case the result format is suitable to represent pure object detection results. In the later case, one of the following keys must be present:

• the landmarks key

• the mask key

The following statements are then true:

• If the landmarks key is present, the result format is suitable to represent pure landmark detection results, such as pose detection.

• If the mask key is present, the result format is suitable to represent pure segmentation results. If, optionally, the category_id key is also present, the result format is suitable to represent semantic segmentation results.

When both object detection keys and the landmarks key are present, the result format is suitable to represent mixed model results, when the model detects not only object bounding boxes, but also keypoints/landmarks within the bounding box.

When both object detection keys and the mask key are present, the result format is suitable to represent mixed model results, when the model detects not only object bounding boxes, but also segmentation masks within the bounding box (i.e. instance segmentation).

Example of pure object detection results:

Example

[
    {'category_id': 0, 'label': 'cat', 'score': 0.99, 'bbox': [10, 20, 100, 200]},
    {'category_id': 1, 'label': 'dog', 'score': 0.01, 'bbox': [200, 100, 300, 400]}
]

Example of oriented object detection results:

Example

[
    {'category_id': 0, 'label': 'car', 'score': 0.99, 'bbox': [10, 20, 100, 200], 'angle': 0.79}
]

Example of landmark object detection results:

Example

[
    {
        'landmarks': [
            {'category_id': 0, 'label': 'Nose', 'score': 0.99, 'landmark': [10, 20]},
            {'category_id': 1, 'label': 'LeftEye', 'score': 0.98, 'landmark': [15, 25]},
            {'category_id': 2, 'label': 'RightEye', 'score': 0.97, 'landmark': [18, 28]}
        ]
    }
]

Example of segmented object detection results:

Example

[
    {
        'mask': {'x_min': 1, 'y_min': 1, 'height': 2, 'width': 2, 'data': 'AAAAAAEAAAAAAAAAAQAAAAIAAAABAAAA'}
    }
]

For hand palm detection models each inference result dictionary contains the following keys:

• score: probability of detected hand.

• handedness: probability of right hand.

• landmarks: list of dictionaries, one per each hand keypoint.

Each landmarks list element is a dictionary with the following keys:

• label: classified object class label.

• category_id: classified object class index.

• landmark: landmark point coordinate list [x, y, z].

• world_landmark: metric world landmark point coordinate list [x, y, z].

• connect: list of adjacent landmarks indexes.

Example

[
    {
        'score': 0.99,
        'handedness': 0.98,
        'landmarks': [
            {
                'label': 'Wrist',
                'category_id': 0,
                'landmark': [10, 20, 30],
                'world_landmark': [10, 20, 30],
                'connect': [1]
            },
            {
                'label': 'Thumb',
                'category_id': 1,
                'landmark': [15, 25, 35],
                'world_landmark': [15, 25, 35],
                'connect': [0]
            }
        ]
    }
]

For segmentation models inference result is a single-element list. That single element is a dictionary, containing single key data. The value of this key is 2D numpy array of integers, where each integer value represents a class ID of the corresponding pixel. The class IDs are defined by the model label dictionary.

Example

[
    {
        'data': numpy.array([
            [0, 0, 0, 1, 1, 1],
            [0, 0, 0, 1, 1, 1],
            [0, 0, 0, 1, 1, 1],
            [2, 2, 2, 3, 3, 3],
            [2, 2, 2, 3, 3, 3],
            [2, 2, 2, 3, 3, 3],
        ])
    }
]

__init__(*, ...)

degirum.postprocessor._InferenceResults.InferenceResults.__init__(*, inference_results, conversion, input_image=None, model_image=None, draw_color=(255, 255, 128), line_width=3, show_labels=True, show_probabilities=False, alpha='auto', font_scale=1.0, fill_color=(0, 0, 0), blur=None, frame_info=None, label_dictionary={}, input_shape=None)

Constructor.

You never construct InferenceResults objects yourself – the ancestors of this class are returned as results of AI inferences from degirum.model.Model.predict, degirum.model.Model.predict_batch, and degirum.model.Model.predict_dir methods.

Parameters:

Name	Type	Description	Default
inference_results	list	Inference results data.	required
conversion	Callable	Coordinate conversion function accepting two arguments (x,y) and returning two-element tuple. This function should convert model-based coordinates to input image coordinates.	required
input_image	any	Original input data.	None
model_image	any	Input data converted per AI model input specifications.	None
draw_color	tuple	Color for inference results drawing on overlay image.	(255, 255, 128)
line_width	int	Line width in pixels for inference results drawing on overlay image.	3
show_labels	bool	True to draw class labels on overlay image.	True
show_probabilities	bool	True to draw class probabilities on overlay image.	False
alpha	Union[float, str]	Alpha-blend weight for overlay details.	'auto'
font_scale	float	Font scale to use for overlay text.	1.0
fill_color	tuple	RGB color tuple to use for filling if any form of padding is used.	(0, 0, 0)
blur	Union[str, list, None]	Optional blur parameter to apply to the overlay image. If None, no blur is applied. If "all" all objects are blurred. If a class label or a list of class labels is provided, only objects with those labels are blurred.	None
frame_info	any	Input data frame information object.	None
label_dictionary	dict[str, str]	Model label dictionary.	{}
input_shape(list)		Model input shape. Mandatory for image-type postprocessing.	required

__str__

degirum.postprocessor._InferenceResults.InferenceResults.__str__()

Conversion to string

generate_colors

degirum.postprocessor._InferenceResults.InferenceResults.generate_colors()

staticmethod

Generate a list of unique RGB color tuples.

generate_overlay_color(num_classes, ...)

degirum.postprocessor._InferenceResults.InferenceResults.generate_overlay_color(num_classes, label_dict)

staticmethod

Overlay colors generator.

Parameters:

Name	Type	Description	Default
num_classes	int	number of class categories.	required
label_dict	dict	Model labels dictionary.	required

Returns:

Type	Description
Union[list, tuple]	Overlay color tuple or list of tuples.

supported_types

degirum.postprocessor._InferenceResults.InferenceResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._DetectionResults.DetectionResults

Bases: InferenceResults

InferenceResult class implementation for detection results type

image_overlay

degirum.postprocessor._DetectionResults.DetectionResults.image_overlay

property

Image with AI inference results drawn. Image type is defined by the selected graphical backend.

__str__

degirum.postprocessor._DetectionResults.DetectionResults.__str__()

Convert inference results to string

generate_overlay_color(num_classes, ...)

degirum.postprocessor._DetectionResults.DetectionResults.generate_overlay_color(num_classes, label_dict)

staticmethod

Overlay colors generator.

Parameters:

Name	Type	Description	Default
num_classes	int	number of class categories.	required
label_dict	dict	Model labels dictionary.	required

Returns:

Type	Description
list	general overlay color data for segmentation results

supported_types

degirum.postprocessor._DetectionResults.DetectionResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._ClassificationResults.ClassificationResults

Bases: InferenceResults

InferenceResult class implementation for classification results type

image_overlay

degirum.postprocessor._ClassificationResults.ClassificationResults.image_overlay

property

Image with AI inference results drawn. Image type is defined by the selected graphical backend. Each time this property is accessed, new overlay image object is created and all overlay details are redrawn according to the current settings of overlay_*** properties.

overlay_show_labels_below

degirum.postprocessor._ClassificationResults.ClassificationResults.overlay_show_labels_below

property writable

Specifies if overlay labels should be drawn below the image or on image itself

__str__

degirum.postprocessor._ClassificationResults.ClassificationResults.__str__()

Convert inference results to string

supported_types

degirum.postprocessor._ClassificationResults.ClassificationResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._MultiLabelClassificationResults.MultiLabelClassificationResults

Bases: InferenceResults

InferenceResult class implementation for multi-label classification results type

image_overlay

degirum.postprocessor._MultiLabelClassificationResults.MultiLabelClassificationResults.image_overlay

property

Image with AI inference results drawn. Image type is defined by the selected graphical backend. Each time this property is accessed, new overlay image object is created and all overlay details are redrawn according to the current settings of overlay_*** properties.

overlay_show_labels_below

degirum.postprocessor._MultiLabelClassificationResults.MultiLabelClassificationResults.overlay_show_labels_below

property writable

Specifies if overlay labels should be drawn below the image or on image itself

__str__

degirum.postprocessor._MultiLabelClassificationResults.MultiLabelClassificationResults.__str__()

Convert inference results to string

supported_types

degirum.postprocessor._MultiLabelClassificationResults.MultiLabelClassificationResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._SegmentationResults.SegmentationResults

Bases: InferenceResults

InferenceResult class implementation for segmentation results type

image_overlay

degirum.postprocessor._SegmentationResults.SegmentationResults.image_overlay

property

Image with AI inference results drawn. Image type is defined by the selected graphical backend.

__str__

degirum.postprocessor._SegmentationResults.SegmentationResults.__str__()

Convert inference results to string

generate_overlay_color(num_classes, ...)

degirum.postprocessor._SegmentationResults.SegmentationResults.generate_overlay_color(num_classes, label_dict)

staticmethod

Overlay colors generator.

Parameters:

Name	Type	Description	Default
num_classes	int	number of class categories.	required
label_dict	dict	Model labels dictionary.	required

Returns:

Type	Description
list	general overlay color data for segmentation results

supported_types

degirum.postprocessor._SegmentationResults.SegmentationResults.supported_types()

staticmethod

List supported result types for this postprocessor.

degirum.postprocessor._Hand_DetectionResults.Hand_DetectionResults

Bases: InferenceResults

InferenceResult class implementation for pose detection results type

image_overlay

degirum.postprocessor._Hand_DetectionResults.Hand_DetectionResults.image_overlay

property

Image with AI inference results drawn. Image type is defined by the selected graphical backend.

__str__

degirum.postprocessor._Hand_DetectionResults.Hand_DetectionResults.__str__()

Convert inference results to string

supported_types

degirum.postprocessor._Hand_DetectionResults.Hand_DetectionResults.supported_types()

staticmethod

List supported result types for this postprocessor.