WWDC21: Accelerate machine learning with Metal Performance Shaders Graph | Apple

  Рет қаралды 43

Apple Developer

Apple Developer

Күн бұрын

Metal Performance Shaders Graph is a compute engine that helps you build, compile, and execute customized multidimensional graphs for linear algebra, machine learning, computer vision, and image processing. Discover how MPSGraph can accelerate the popular TensorFlow platform through a Metal backend for Apple products. Learn how to add control flow to your graphs, manage the graph compilation for optimal performance, and use the MPSGraph operations to accelerate the hardest compute applications with only a few lines of code.
Explore related documentation, sample code, and more:
Metal Performance Shaders: developer.appl...
Metal: developer.appl...
Training a Neural Network with Metal Performance Shaders: developer.appl...
Metal Shading Language Specification: developer.appl...
Accelerate machine learning with Metal: developer.appl...
Build customized ML models with the Metal Performance Shaders Graph: developer.appl...
More Apple Developer resources:
Video sessions: apple.co/Video...
Documentation: apple.co/Devel...
Forums: apple.co/Devel...
App: apple.co/Devel...

Пікірлер
WWDC21: Classify hand poses and actions with Create ML | Apple
26:50
WWDC22: Debug Swift debugging with LLDB | Apple
20:04
Apple Developer
Рет қаралды 149
Support each other🤝
00:31
ISSEI / いっせい
Рет қаралды 81 МЛН
Sigma Kid Mistake #funny #sigma
00:17
CRAZY GREAPA
Рет қаралды 30 МЛН
WWDC21: Bring Core Data concurrency to Swift and SwiftUI | Apple
27:04
WWDC21: Develop advanced web content | Apple
36:32
Apple Developer
Рет қаралды 149
WWDC22: Create custom catalogs at scale with ShazamKit | Apple
19:44
WWDC22: Create camera extensions with Core Media IO | Apple
32:09
Apple Developer
Рет қаралды 253
WWDC21: Discover Web Inspector improvements | Apple
28:40
Apple Developer
Рет қаралды 90
WWDC21: Build interactive tutorials using DocC | Apple
22:14
Apple Developer
Рет қаралды 80
WWDC21: Coordinate media experiences with Group Activities | Apple
37:59
Support each other🤝
00:31
ISSEI / いっせい
Рет қаралды 81 МЛН