pfnet-research/menoh
Menoh: fast DNN inference library with multiple programming language support
This helps developers integrate pre-trained Deep Neural Network (DNN) models into their applications for image classification or other inference tasks. It takes an ONNX-formatted DNN model and image data as input, and outputs the classification results or other model predictions. This is for software developers looking to deploy DNN models on CPUs quickly and efficiently.
279 stars. No commits in the last 6 months.
Use this if you are a developer building an application and need to quickly run existing ONNX-compatible deep learning models on a CPU for tasks like image recognition.
Not ideal if you need to train new deep learning models, require GPU acceleration for inference, or if the specific operators your model uses are not yet supported.
Stars
279
Forks
34
Language
C++
License
MIT
Category
Last pushed
Jan 02, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pfnet-research/menoh"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
davisking/dlib
A toolkit for making real world machine learning and data analysis applications in C++
ZigRazor/CXXGraph
Header-Only C++ Library for Graph Representation and Algorithms
apache/singa
a distributed deep learning platform
mlpack/mlpack
mlpack: a fast, header-only C++ machine learning library
hosseinmoein/DataFrame
C++ DataFrame for statistical, financial, and ML analysis in modern C++