ReIdentification¶

class ReIdentificationPrediction(id, rank, distance)¶

A single prediction from ReIdentification.

Parameters

id (int) – The id corresponding to this prediction.
rank (int) – The rank of this prediction among results.
distance (float) – The cosine distance of this prediction.

property id¶

The id corresponding to this prediction.

Return type: int

property rank¶

The rank of this prediction among results.

Return type: int

property distance¶

The cosine distance of this prediction.

Return type: float

class ReIdentificationResults(predictions, distance_matrix, duration, image)¶

All the results of re-identification from ReIdentification.

Predictions are stored in sorted order, with descending order of rank.

Parameters

predictions (List[ReIdentificationPrediction]) – The list of predictions ordered by rank.
distance_matrix (Optional[ndarray]) – The cosine distance matrix for the re-identification.
duration (float) – The duration of the inference.
image (Optional[ndarray]) – The image that the inference was performed on.

property duration¶

The duration of the inference in seconds.

Return type: float

property predictions¶

The list of predictions.

Return type: List[ReIdentificationPrediction]

property distance_matrix¶

The cosine distance matrix for the re-identification.

Return type: Optional[ndarray]

property image¶

The image the results were processed on.

Image is not available when results are obtained from EyeCloud Cameras.

Return type: Optional[ndarray]

class ReIdentification(model_id, model_config=None)¶

Re-identify the object(image) against a set of known/tracked items.

Parameters: model_id (str) – The ID of the model you want to use for image classification.

set_per_id_gallery_limit(count, drop_method)¶

Set the limit of instances per ID to be maintained in the gallery

Parameters

count (int) – Number of instances per ID to be maintained in the gallery
drop_method (str) – instances to drop if needed when add_to_gallery() is called Supported values [“drop_oldest”, “drop_random”, “drop_latest”]

extract_features(image, flip_horizontal=True)¶

Compute feature matrix for the given image

Parameters

image (ndarray) – Image for which features are to be extracted and returned
flip_horizontal (bool) – Flag to enable horizontal flip of image during feature extraction

Return type

ndarray

get_distances(image, gallery_images, flip_horizontal=True, normalize_distance=True)¶

Calculate the distance matrix between given image and gallery images

Parameters

image (ndarray) – Image for which distances to gallery images will be returned
gallery_images (List[ndarray]) – List of images
flip_horizontal (bool) – Flag to enable horizontal flip of image during feature extraction
normalize_distance (bool) – Flag to return normalized distance matrix

Return type

ndarray

add_to_gallery(image, id, flip_horizontal=True)¶

Extract the features for the given image and add against the given ID to the gallery

Parameters

image (ndarray) – Image to store in gallery
id (int) – ID for the given image
flip_horizontal (bool) – Flag to enable horizontal flip of image during feature extraction

remove_from_gallery(id)¶

Remove all the features corresponding to given ID from the gallery

Parameters: id (int) – ID for which data needs to be removed

property accelerator¶

The accelerator being used.

Return type: Optional[Accelerator]

property colors¶

The auto-generated colors for the loaded model.

Note: Initialized to None when the model doesn’t have any labels. Note: To update, the new colors list must be same length as the label list.

Return type: Optional[ndarray]

property engine¶

The engine being used.

Return type: Optional[Engine]

property labels¶

The labels for the loaded model.

Note: Initialized to None when the model doesn’t have any labels.

Return type: Optional[List[str]]

load(engine=<Engine.DNN: 'DNN'>, accelerator=<Accelerator.DEFAULT: 'DEFAULT'>)¶

Load the model to an engine and accelerator.

Parameters

engine (Engine) – The engine to load the model to
accelerator (Accelerator) – The accelerator to load the model to

property model_config¶

The configuration of the model that was loaded

Return type: ModelConfig

property model_id¶

The ID of the loaded model.

Return type: str

property model_purpose¶

The purpose of the model being used.

Return type: str

publish_analytics(results, tag=None, **kwargs)¶

Publish results to the alwaysAI Analytics Service

Example usage:

try:
    inference.publish_analytics(results, tag='custom_tag')
except edgeiq.PublishError as e:
    # Retry publish
except edgeiq.ConnectionError as e:
    # Save state and exit app to reconnect

Parameters

results (~ResultsT) – The results to publish.
tag (Optional[Any]) – Additional information to assist in querying and visualizations.

Raises

ConnectionBlockedError when using connection to the alwaysAI Device Agent and resources are at capacity,

Raises

PacketRateError when publish rate exceeds current limit,

Raises

PacketSizeError when packet size exceeds current limit. Packet publish size and rate limits will be provided in the error message.

re_id_image(image, top_k=1, normalize_distance=True, flip_horizontal=True)¶

Re-identify the given object(image) against a set of known/tracked items (gallery).

Parameters

image (ndarray) – The image to re-identify
top_k (int) – Number of top predictions to return
normalize_distance (bool) – Flag to use normalized distance matrix
flip_horizontal (bool) – Flag to enable horizontal flip of image during feature extraction

Return type

ReIdentificationResults