oramasearch/onnx-go
onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.
For Go developers, this tool lets you integrate pre-trained machine learning models into your applications. It takes a model in the Open Neural Network Exchange (ONNX) format as input and allows you to run predictions directly within your Go code, making it easier to add AI capabilities without deep data science expertise. This is ideal for Go developers building applications that need to leverage existing neural network models.
877 stars. No commits in the last 6 months.
Use this if you are a Go developer who needs to incorporate existing machine learning models, like those from model zoos, into your Go applications without being tied to specific ML frameworks.
Not ideal if you are looking to train new machine learning models from scratch or if you need a backend that supports every single ONNX operator, as current implementation is partial.
Stars
877
Forks
83
Language
Go
License
MIT
Category
Last pushed
Sep 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/oramasearch/onnx-go"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SPFlow/SPFlow
Sum Product Flow: An Easy and Extensible Library for Sum-Product Networks
gomlx/gomlx
GoMLX: An Accelerated Machine Learning Framework For Go
montanaflynn/stats
A well tested and comprehensive Golang statistics library package with no dependencies.
mattn/go-tflite
Go binding for TensorFlow Lite
james-bowman/sparse
Sparse matrix formats for linear algebra supporting scientific and machine learning applications