hollance/Forge
A neural network toolkit for Metal
Forge helps iOS and macOS developers quickly integrate and run deep neural networks on Apple devices using their graphics hardware (Metal). It simplifies the process of defining network layers and handles data conversions between standard Swift arrays and the specialized Metal image formats. Developers can feed in image data and get back predictions or classifications from pre-trained models like Inception-v3 for image recognition or YOLO for object detection.
1,266 stars. No commits in the last 6 months.
Use this if you are an iOS/macOS developer building a mobile or desktop application that needs to perform fast, on-device neural network inference for tasks like image classification or object detection, and you prefer working directly with Apple's Metal Performance Shaders (MPSCNN) framework.
Not ideal if you are looking for a high-level machine learning framework for general-purpose model training or if your application runs on platforms other than Apple devices, as this toolkit is specifically designed for Metal and MPSCNN.
Stars
1,266
Forks
173
Language
Swift
License
MIT
Category
Last pushed
May 18, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hollance/Forge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apple/coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
hollance/YOLO-CoreML-MPSNNGraph
Tiny YOLO for iOS implemented using CoreML but also using the new MPS graph API.
tensorflow/swift-apis
Swift for TensorFlow Deep Learning Library
hanleyweng/CoreML-in-ARKit
Simple project to detect objects and display 3D labels above them in AR. This serves as a basic...
hollance/CoreMLHelpers
Types and functions that make it a little easier to work with Core ML in Swift.