792438 – dev-cpp/tiny-dnn: header only, dependency-free deep learning framework in C++14 new package

Bug 792438 - dev-cpp/tiny-dnn: header only, dependency-free deep learning framework in C++14 new package

Summary: dev-cpp/tiny-dnn: header only, dependency-free deep learning framework in C++...

Status:	UNCONFIRMED

Alias:	None

Product:	Gentoo Linux
Classification:	Unclassified
Component:	New packages (show other bugs)
Hardware:	All Linux

Importance:	Normal normal (vote)
Assignee:	Default Assignee for New Packages

URL:	https://github.com/tiny-dnn/tiny-dnn
Whiteboard:
Keywords:	InOverlay

Depends on:
Blocks:

Reported:	2021-05-27 08:45 UTC by Alessandro Barbieri
Modified:	2021-05-27 14:50 UTC (History)
CC List:	0 users

See Also:
Package list:
Runtime testing required:	---

Attachments
Add an attachment (proposed patch, testcase, etc.)

Note You need to log in before you can comment on or make changes to this bug.

Description Alessandro Barbieri 2021-05-27 08:45:32 UTC

Currently bundled with opencv

LICENSE: BSD

Features

Reasonably fast, without GPU:
With TBB threading and SSE/AVX vectorization.
98.8% accuracy on MNIST in 13 minutes training (@Core i7-3520M).
Portable & header-only:
Runs anywhere as long as you have a compiler which supports C++14.
Just include tiny_dnn.h and write your model in C++. There is nothing to install.
Easy to integrate with real applications:
No output to stdout/stderr.
A constant throughput (simple parallelization model, no garbage collection).
Works without throwing an exception.
Can import caffe's model.
Simply implemented:
A good library for learning neural networks

Comment 1 Alessandro Barbieri 2021-05-27 09:37:10 UTC

now in guru