Mediapipe-based library to redact faces from videos and images

Files in scope This concerns all files referenced in MediaPipe or Magritte graphs, for example TensorFlow Lite ML models used in a face detection graph or the sticker image file in the sticker …

Introduction Magritte is based on MediaPipe, but for now you only need the following two notions about MediaPipe: Graph An entity that defines how images or other types of content are treated. For …

Mediapipe-based library to redact faces from videos and images

Magritte Architecture The Magritte library consists of MediaPipe graphs and calculators. It is designed in a modular way that makes it easy to plug graphs together in many different ways to build solutions …

For the face detection models, please refer to MediaPipe’s documentation to understand their precision. Getting started If you want to try out some demos, see Trying out Magritte If you’re an engineer and …

Mediapipe-based library to redact faces from videos and images

SchemaItem API SchemaItem is a DataItem subclass that represents a schema. SchemaItem.get_item_schema(self) -> SchemaItem Returns the item schema of a List schema`. …

kd_ext API Operators under the kd_ext.xxx modules for extension utilities. Importing from the following module is needed: from koladata import kd_ext

kd.bitwise API Bitwise operators kd.bitwise.bitwise_and(x, y) Aliases: kd.bitwise_and Computes pointwise bitwise x & y. kd.bitwise.bitwise_or(x, y) Aliases: kd.bitwise_or Computes pointwise bitwise …