Face Api.js Versions Save

JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js

0.22.2

4 years ago
  • bumped tfjs-core to version 1.7.0

0.22.1

4 years ago
  • bumped tfjs-core to version 1.5.2

0.22.0

4 years ago
  • bumped tfjs-core to version 1.4.0
  • merged tfjs-image-recognition-base into face-api.js

deprecations:

  • added deprecation warnigs for
    • allFaces*
    • mtcnn

breaking changes:

  • moved utils to faceapi.utils

0.21.0

4 years ago
  • bumped tfjs-core to version 1.2.9
  • added missing exports for WithAge/WithGender #339
  • JSON de/serialization for FaceMatcher and LabeledFaceDescriptors #397

0.20.1

4 years ago
  • bumped tfjs-core to version 1.2.2

0.20.0

5 years ago

features:

  • age and gender recognition (AgeGenderNet)
  • improved and more flexible drawing api accessible via faceapi.draw (see examples)
  • allow alignment via withFaceLandmarks before face classification (expression, age and gender prediction) for better accuracy
  • faceapi.matchDimensions helper function to resize media elements

breaking API changes:

  1. FaceExpressionNet.predictExpressions returns FaceExpressions instance instead of array now

  2. withFaceLandmarks() has to come first after detectAllFaces, detectSingleFace now, since its possible now to use face alignment for face classifcation to achieve more stable prediction results for face classification (expression, age and gender prediction):

await faceapi.detectAllFaces(input).withFaceExpressions().withFaceLandmarks()
-> await faceapi.detectAllFaces(input).withFaceLandmarks().withFaceExpressions()

await faceapi.detectAllFaces(input).withFaceLandmarks().withFaceExpressions().withFaceDescriptors()
-> await faceapi.detectAllFaces(input).withFaceLandmarks().withFaceExpressions().withFaceDescriptors()

await faceapi.detectSingleFace(input).withFaceExpressions().withFaceLandmarks()
-> await faceapi.detectSingleFace(input).withFaceLandmarks().withFaceExpressions()

await faceapi.detectSingleFace(input).withFaceExpressions().withFaceLandmarks().withFaceDescriptor()
-> await faceapi.detectSingleFace(input).withFaceLandmarks().withFaceExpressions().withFaceDescriptor()
  1. removed internals and old drawing api that have been exported:
  • BoxWithText
  • getDefaultDrawOptions
  • drawBox (use faceapi.draw.DrawBox(box).draw(canvas) instead)
  • drawDetection (use faceapi.draw.drawDetections instead)
  • drawFaceLandmarks (use faceapi.draw.drawFaceLandmarks instead)
  • drawFaceExpressions (use faceapi.draw.drawFaceExpressions instead)
  • drawText (use faceapi.draw.DrawTextField(text).draw(canvas) instead)

0.19.0

5 years ago
  • updated tfjs-core to 1.0.3

0.18.0

5 years ago
  • recompiled package with typescript 3.2.4
  • removed dependency to tfjs-tiny-yolov2

0.17.1

5 years ago

fixes:

  • removed absolute import, which has been causing build errors

0.17.0

5 years ago

Features:

  • face expression recognition

Breaking Changes:

The following two utility classes have been replaced: FaceDetectionWithLandmarks, FullFaceDescription. Now, plain objects are returned from the corresponding function calls instead of instances of abovementioned classes, which have to be resized by faceapi.resizeResults(results, { width: <width>, height: <height> }) instead of results.map(res => res.forSize(width, height)):

export function resizeResults<T>(results: T, { width, height }: IDimensions): T