All Versions
19
Latest Version
Avg Release Cycle
72 days
Latest Release
644 days ago

Changelog History
Page 1

  • v1.4.0 Changes

    September 26, 2020
    • โฌ‡๏ธ Dropping support for Python 2.x
    • ๐Ÿ’ป --upsample a parameter for command line face_recognition
  • v1.3.0 Changes

    February 20, 2020
    • โฌ‡๏ธ Drop support for Python 3.4 and add 3.8
    • Blink detection example
  • v1.2.3 Changes

    August 21, 2018
    • You can now pass model="small" to face_landmarks() to use the 5-point face model instead of the 68-point model.
    • ๐Ÿ‘ Now officially supporting Python 3.7
    • ๐Ÿ†• New example of using this library in a Jupyter Notebook
  • v1.2.2 Changes

    April 02, 2018
    • โž• Added the face_detection CLI command
    • โœ‚ Removed dependencies on scipy to make installation easier
    • ๐Ÿ›  Cleaned up KNN example and fixed a bug with drawing fonts to label detected faces in the demo
  • v1.2.1 Changes

    February 01, 2018
    • ๐Ÿ›  Fixed version numbering inside of module code.
  • v1.2.0 Changes

    February 01, 2018
    • ๐Ÿ›  Fixed a bug where batch size parameter didn't work correctly when doing batch face detections on GPU.
    • โšก๏ธ Updated OpenCV examples to do proper BGR -> RGB conversion
    • โšก๏ธ Updated webcam examples to avoid common mistakes and reduce support questions
    • โž• Added a KNN classification example
    • โž• Added an example of automatically blurring faces in images or videos
    • โšก๏ธ Updated Dockerfile example to use dlib v19.9 which removes the boost dependency.
  • v1.1.0 Changes

    September 23, 2017
    • Will use dlib's 5-point face pose estimator when possible for speed (instead of 68-point face pose esimator)
    • dlib v19.7 is now the minimum required version
    • face_recognition_models v0.3.0 is now the minimum required version
  • v1.0.0 Changes

    August 29, 2017
    • โž• Added support for dlib's CNN face detection model via model="cnn" parameter on face detecion call
    • โž• Added support for GPU batched face detections using dlib's CNN face detector model
    • Added find_faces_in_picture_cnn.py to examples
    • Added find_faces_in_batches.py to examples
    • Added face_rec_from_video_file.py to examples
    • dlib v19.5 is now the minimum required version
    • face_recognition_models v0.2.0 is now the minimum required version
  • v0.2.2 Changes

    July 07, 2017
    • โž• Added --show-distance to cli
    • ๐Ÿ›  Fixed a bug where --tolerance was ignored in cli if testing a single image
    • โž• Added benchmark.py to examples
  • v0.2.1 Changes

    July 03, 2017
    • โž• Added --tolerance to cli