Avg Release Cycle
644 days ago
- ⬇️ Dropping support for Python 2.x
- 💻 --upsample a parameter for command line face_recognition
- ⬇️ Drop support for Python 3.4 and add 3.8
- Blink detection example
- You can now pass model="small" to face_landmarks() to use the 5-point face model instead of the 68-point model.
- 👍 Now officially supporting Python 3.7
- 🆕 New example of using this library in a Jupyter Notebook
- ➕ Added the face_detection CLI command
- ✂ Removed dependencies on scipy to make installation easier
- 🛠 Cleaned up KNN example and fixed a bug with drawing fonts to label detected faces in the demo
- 🛠 Fixed version numbering inside of module code.
- 🛠 Fixed a bug where batch size parameter didn't work correctly when doing batch face detections on GPU.
- ⚡️ Updated OpenCV examples to do proper BGR -> RGB conversion
- ⚡️ Updated webcam examples to avoid common mistakes and reduce support questions
- ➕ Added a KNN classification example
- ➕ Added an example of automatically blurring faces in images or videos
- ⚡️ Updated Dockerfile example to use dlib v19.9 which removes the boost dependency.
- 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
- ➕ Added support for dlib's CNN face detection model via model="cnn" parameter on face detecion call
- ➕ 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
- ➕ Added --show-distance to cli
- 🛠 Fixed a bug where --tolerance was ignored in cli if testing a single image
- ➕ Added benchmark.py to examples
- ➕ Added --tolerance to cli