Skip to content
The Daily Repo

palle-k / DL4S

Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux

Why this job: says: neural networks; topics: neural-networks, autograd, tensor, deep-learning, machine-learning

What it does

DL4S provides a high-level API for many accelerated operations common in neural networks and deep learning. It furthermore has automatic differentiation builtin, which allows you to create and train neural networks without needing to manually implement backpropagation - without needing a special Swift toolchain.

Get started

No single install command. Read the steps in the README (opens in new tab)

Maintenance
Active
Last commit 50 days ago
Stars
108
On GitHub
Licence
MIT
Allows business use
Downloads for
None listed
No release files
Latest version
None yet
No releases
Built with
Swift
99% of the code

Is it looked after?

Contributors
Not stated
Last 90 days
Issues
80% closed
1 still open
Pull requests
13 merged
2 waiting
Releases
None
Never published

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
pytorch / pytorch105,450todayCustomNo downloads
raskr / rust-autograd5055 months agoMITNo downloads
google-deepmind / dm-haiku3,30116 days agoApache-2.0No downloads
More: languages, topics, project record and preview image

Languages

  • Swift 99%
  • Python <1%
  • C <1%

Topics

  • autograd
  • automatic-differentiation
  • convolutional-neural-networks
  • deep-learning
  • deep-neural-networks
  • derivatives
  • gradient-descent
  • machine-learning
  • neural-networks
  • optimizers
  • recurrent-networks
  • recurrent-neural-networks

Project record

  • JobAI libraries and models
  • StatusListed
  • Commits347
  • Forks13
  • Watching5
  • Stars in 28 days0
  • CreatedMar 10, 2019
  • First seen by usNov 7, 2026
  • CheckedNov 8, 2026

Project preview image

Preview image from palle-k/DL4S

Type to search.

Try