Upstream software project

frugally-deep

Header-only library for using Keras (TensorFlow) models in C++

About frugally-deep

Header-only library for using Keras (TensorFlow) models in C++

This project links 3 native package records across 3 recorded operating-system releases. Compare the retained versions and architectures below, then open the package for your own release.

These are catalog observations, not a guarantee of installation, compatibility, or upstream support.

Project pictures and package coverage

frugally-deep repository preview from GitHub
Project repository preview, supplied by GitHub. Open source repository
Debian 13 (Trixie): 1 package records; Fedora 43: 1 package records; Fedora 44: 1 package records. Catalog coverage diagram, not an application screenshot.frugally-deep: recorded package coverageDebian 13 (Trixie)1 recordsFedora 431 recordsFedora 441 records
OpenFactory diagram of linked package records. It is not an application screenshot.

Project identity

Project
frugally-deep
Publisher
Not authoritatively mapped
Native package records
3
Operating systems
debian-13, fedora-43, fedora-44
License expression
MIT
Source repository
Open source repository

Source-reported description

The fullest retained description is shown with its source. Distribution packaging descriptions may include downstream details.

Would you like to build/train a model using Keras/Python? And would you like to run the prediction (forward pass) on your model in C++ without linking your application against TensorFlow? Then frugally-deep is exactly for you. frugally-deep * is a small header-only library written in modern and pure C++. * is very easy to integrate and use. * depends only on FunctionalPlus, Eigen and json - also header-only libraries. * supports inference (model.predict) not only for sequential models but also for computational graphs with a more complex topology, created with the functional API. * re-implements a (small) subset of TensorFlow, i.e., the operations needed to support prediction. * results in a much smaller binary size than linking against TensorFlow. * works out-of-the-box also when compiled into a 32-bit executable. (Of course, 64 bit is fine too.) * avoids temporarily allocating (potentially large chunks of) additional RAM during convolutions (by not materializing the im2col input matrix). * utterly ignores even the most powerful GPU in your system and uses only one CPU core per prediction. ;-) * but is quite fast on one CPU core, and you can run multiple predictions in parallel, thus utilizing as many CPUs as you like to improve the overall prediction throughput of your application/pipeline.

Description source

Packages by operating system

Compare recorded versions, then open a package for dependency, file, checksum, and repository evidence. Version strings are distribution-specific, not a ranking of newer software.

Debian 13 (Trixie)

  1. Package libfdeep-dev

    trixie (Debian 13 (Trixie)) (libdevel): use Keras models in C++

    0.17.1-1: all

    Source: frugally-deep

Fedora 43

  1. Package frugally-deep-devel

    43 (Fedora 43) (Unspecified): Header-only library for using Keras (TensorFlow) models in C++

    0.15.30-9.fc43: aarch64 i686 x86_64

    Source: frugally-deep

Fedora 44

  1. Package frugally-deep-devel

    44 (Fedora 44) (Unspecified): Header-only library for using Keras (TensorFlow) models in C++

    0.15.30-11.fc44: aarch64 i686 x86_64

    Source: frugally-deep

Project resources and further reading

Mapping provenance

Only source-backed identity signals create public cross-OS links. A reviewer can later approve or dispute an inferred relationship without rewriting native package history.

No field-level source record is published yet.