SDK Loop¶
SDK Task¶
A task that determinants a set of biometric features estimated from input images or samples. All features are divided into 3 groups:
face detection features: face detection, landmarks, eyes, gaze direction, ags.
samples(warp) features: emotions, mouth state, warp quality.
face attributes: age, gender, ethnicity, descriptor.
Face detection features are estimated on images, other features are estimated on warped images.
Task pipeline¶
SDK loop is a structure for task processing. There exist 3 stages of task processing:
detector stage
warp estimator stage
extractor stage
All features in estimated in the corresponding stage. Loop determines a pipeline for every task which is an order list of stages. Communication between stage handlers is done through queues. Loop sends a task to a queue which is corresponding first task pipeline stage. The task is put to a queue which corresponding next stage in the pipeline after stage processing. A task is put to a common results queue if it is failed or done. Loop gets a task from the results queue and transfers to a task customer.
Helpers enums.
- class luna_handlers.sdk.sdk_loop.enums.Estimators(value)[source]¶
Available loop estimators
- basicAttributes = 'basicAttributes'¶
basic attributes (age, gender, ethnicity)
- bodyAttributes = 'bodyAttributes'¶
body attributes
- bodyDescriptor = 'bodyDescriptor'¶
body descriptors
- bodyDetection = 'bodyDetection'¶
body detection
- bodyWarp = 'bodyWarp'¶
body warp
- emotions = 'emotions'¶
emotions
- eyebrowExpression = 'eyebrow_expression'¶
eyebrow expression
- eyes = 'eyes'¶
eyes state, points
- faceDescriptor = 'faceDescriptor'¶
face descriptor
- faceDetection = 'faceDetection'¶
face detection
- faceDetectionBackground = 'face_detection_background'¶
face detection background
- faceLandmarks5 = 'face_landmarks5'¶
face landmarks5
- faceLandmarks68 = 'face_landmarks68'¶
face landmarks68
- faceNaturalLight = 'face_natural_light'¶
face natural light
- faceWarp = 'faceWarp'¶
face warp
- fisheye = 'fisheye'¶
fisheye
- gazeDirection = 'gaze'¶
gaze direction
- glasses = 'glasses'¶
glasses
- headPose = 'headPose'¶
head pose
- headwear = 'headwear'¶
headwear
- humanDetection = 'humaDetection'¶
human detection (face and body)
- imageColorType = 'image_color_type'¶
image color type
- imageOrientation = 'imageOrientation'¶
image orientation
- livenessV1 = 'livenessV1'¶
livenessv1
- mask = 'mask'¶
mask
- mouthState = 'mouthState'¶
mouth state
- quality = 'warpQuality'¶
warp quality
- redEyes = 'red_eyes'¶
red-eyes
- class luna_handlers.sdk.sdk_loop.enums.LoopEstimations(value)[source]¶
SDK Loop estimations enum. Name - estimation target.
- basicAttributes = 'basic_attributes'¶
basic attributes (age, gender, ethnicity)
- bodyAttributes = 'body_attributes'¶
body attributes
- bodyDescriptor = 'body_descriptor'¶
body descriptor
- bodyDetection = 'body_detection'¶
body detection
- bodyLandmarks17 = 'body_landmarks17'¶
body landmarks
- bodyWarp = 'body_warp'¶
body warp
- emotions = 'emotions'¶
emotions
- eyebrowExpression = 'eyebrow_expression'¶
eyebrow expression
- eyes = 'eyes'¶
eyes state, points
- faceDescriptor = 'face_descriptor'¶
face descriptor
- faceDetection = 'face_detection'¶
face detection
- faceDetectionBackground = 'face_detection_background'¶
face detection background
- faceLandmarks5 = 'face_landmarks5'¶
face landmarks68
- faceLandmarks68 = 'face_landmarks68'¶
face landmarks68
- faceNaturalLight = 'face_natural_light'¶
face natural light
- faceWarp = 'face_warp'¶
face warp
- faceWarpQuality = 'face_warp_quality'¶
face warp quality
- fisheye = 'fisheye'¶
fisheye
- gaze = 'gaze'¶
gaze direction
- glasses = 'glasses'¶
glasses
- headPose = 'head_pose'¶
head pose
- headwear = 'headwear'¶
headwear
- imageColorType = 'image_color_type'¶
image color type
- imageOrientation = 'image_orientation'¶
image orientation
- livenessV1 = 'livenessV1'¶
livenessV1
- mask = 'mask'¶
mask
- mouthAttributes = 'mouth_state'¶
mouth state
- redEyes = 'red_eyes'¶
red-eyes