Classification¶
-
class
ClassificationPrediction
(confidence, label)¶ A single prediction from
Classification
.-
property
label
¶ The label describing this prediction result.
- Type
string
-
property
confidence
¶ The confidence of this prediction.
- Type
float
-
property
-
class
ClassificationResults
(predictions, duration, image)¶ All the results of classification from
Classification
.Predictions are stored in sorted order, with descending order of confidence.
-
property
duration
¶ The duration of the inference in seconds.
- Type
float
-
property
predictions
¶ The list of predictions.
- Type
list of
ClassificationPrediction
-
property
image
¶ The image the results were processed on.
Image is not available when results are obtained from EyeCloud Cameras.
- Type
numpy array – The image in BGR format
-
property
-
class
Classification
(model_id)¶ Identify the most prominent object in an image.
Typical usage:
classifier = edgeiq.Classification('alwaysai/googlenet') classifier.load(engine=edgeiq.Engine.DNN) <get image> results = classifier.classify_image(image) for prediction in results.predictions: print('Label: {}, confidence: {}'.format( prediction.label, prediction.confidence))
- Parameters
model_id (string) – The ID of the model you want to use for image classification.
-
classify_image
(image, confidence_level=0.3)¶ Identify the most prominent object in the specified image.
- Parameters
image (numpy array of image) – The image to analyze.
confidence_level (float in range [0.0, 1.0]) – The minimum confidence level required to successfully accept a classification.
- Returns
-
publish_analytics
(results, tag=None)¶ Publish Classification results to the alwaysAI Analytics Service
- Parameters
results (
ClassificationResults
) – The results to publish.tag (JSON-serializable object) – Additional information to assist in querying and visualizations.
-
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
List
[Tuple
[int
,int
,int
]]
-
property
labels
¶ The labels for the loaded model.
Note: Initialized to None when the model doesn’t have any labels.
- Return type
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 toaccelerator (
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