neilcz/libGDL
一个移动端跨平台的gpu+cpu并行计算的cnn框架(A mobile-side cross-platform gpu+cpu parallel computing CNN framework)
This is a framework for developers creating mobile applications that use Convolutional Neural Networks (CNNs). It helps integrate CNN models to run efficiently on both the GPU and CPU of mobile devices. Developers feed in a trained CNN model, and it produces optimized, cross-platform mobile application code that can perform tasks like image style transfer or classification on device.
No commits in the last 6 months.
Use this if you are a C++ developer building a mobile app that needs to run complex CNN models directly on users' phones, leveraging both GPU and CPU for speed.
Not ideal if you are looking for a high-level, production-ready library with extensive model support and compatibility testing for various Android devices, or if you are not a C++ developer.
Stars
92
Forks
34
Language
C++
License
GPL-3.0
Category
Last pushed
Nov 10, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/neilcz/libGDL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.