HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
clab
dynet
C++2016–2017
clab / dynet

dynet

DyNet: The Dynamic Neural Network Toolkit

AI & Machine LearningSystems & InfrastructureNetworking
Explore on GitHubRead Hacker News discussions
4Distinct people
4Mentions
0Explicit recommenders
3.4KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

DyNet: The Dynamic Neural Network Toolkit

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:03:16 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week4 dated mentions

Observed mentions: 2016-10-16 16:26:57 UTC to 2017-02-15 22:40:50 UTC. Weeks start Monday, UTC.

012016-10-10 00:00:00 UTC to 2016-10-17 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsOct 102016-10-17 00:00:00 UTC to 2016-10-24 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2016-10-24 00:00:00 UTC to 2016-10-31 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-10-31 00:00:00 UTC to 2016-11-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-11-07 00:00:00 UTC to 2016-11-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-11-14 00:00:00 UTC to 2016-11-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-11-21 00:00:00 UTC to 2016-11-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-11-28 00:00:00 UTC to 2016-12-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-12-05 00:00:00 UTC to 2016-12-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-12-12 00:00:00 UTC to 2016-12-19 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsDec 122016-12-19 00:00:00 UTC to 2016-12-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-12-26 00:00:00 UTC to 2017-01-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-02 00:00:00 UTC to 2017-01-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-09 00:00:00 UTC to 2017-01-16 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-16 00:00:00 UTC to 2017-01-23 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2017-01-23 00:00:00 UTC to 2017-01-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-30 00:00:00 UTC to 2017-02-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-02-06 00:00:00 UTC to 2017-02-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-02-13 00:00:00 UTC to 2017-02-20 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsFeb 13

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Oct 102016-10-10 00:00:00 UTC2016-10-17 00:00:00 UTC110
Oct 172016-10-17 00:00:00 UTC2016-10-24 00:00:00 UTC101
Oct 242016-10-24 00:00:00 UTC2016-10-31 00:00:00 UTC000
Oct 312016-10-31 00:00:00 UTC2016-11-07 00:00:00 UTC000
Nov 72016-11-07 00:00:00 UTC2016-11-14 00:00:00 UTC000
Nov 142016-11-14 00:00:00 UTC2016-11-21 00:00:00 UTC000
Nov 212016-11-21 00:00:00 UTC2016-11-28 00:00:00 UTC000
Nov 282016-11-28 00:00:00 UTC2016-12-05 00:00:00 UTC000
Dec 52016-12-05 00:00:00 UTC2016-12-12 00:00:00 UTC000
Dec 122016-12-12 00:00:00 UTC2016-12-19 00:00:00 UTC000
Dec 192016-12-19 00:00:00 UTC2016-12-26 00:00:00 UTC000
Dec 262016-12-26 00:00:00 UTC2017-01-02 00:00:00 UTC000
Jan 22017-01-02 00:00:00 UTC2017-01-09 00:00:00 UTC000
Jan 92017-01-09 00:00:00 UTC2017-01-16 00:00:00 UTC000
Jan 162017-01-16 00:00:00 UTC2017-01-23 00:00:00 UTC101
Jan 232017-01-23 00:00:00 UTC2017-01-30 00:00:00 UTC000
Jan 302017-01-30 00:00:00 UTC2017-02-06 00:00:00 UTC000
Feb 62017-02-06 00:00:00 UTC2017-02-13 00:00:00 UTC000
Feb 132017-02-13 00:00:00 UTC2017-02-20 00:00:00 UTC101

What Hacker News says

4 sources
vonnik·Feb 15, 2017
This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0] Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends. All of the missing libs have significant advantages over TensorFlow, which appears to be winning chiefly on Github stars. Notably speed and integrations. [0] https://deeplearning4j.org/ http://chainer.org/ https://github.com/clab/dynet https://github.com/PaddlePaddle/Paddle
In Getting Started with Deep Learning: A Review of Available Tools
Smerity·Jan 18, 2017
Only a few months ago people saying that the deep learning library ecosystem was starting to stabilize. I never saw that as the case. The latest frontier for deep learning libraries is ensuring efficient support for dynamic computation graphs. Dynamic computation graphs arise whenever the amount of work that needs to be done is variable. This may be when we're processing text, one example being a few words while another being paragraphs of text, or when we are performing operations against a tree structure of variable size. This problem is particularly prominent in particular subfields, such as natural language processing, where I spend most of my time. PyTorch tackles this very well, as do Chainer[1] and DyNet[2]. Indeed, PyTorch construction was directly informed from Chainer[3], though re-architected and designed to be even faster stil
Read the rest
l. I have seen all of these receive renewed interest in recent months, particularly amongst many researchers performing cutting edge research in the domain. When you're working with new architectures, you want the most flexibility possible, and these frameworks allow for that. As a counterpoint, TensorFlow does not handle these dynamic graph cases well at all. There are some primitive dynamic constructs but they're not flexible and usually quite limiting. In the near future there are plans to allow TensorFlow to become more dynamic, but adding it in after the fact is going to be a challenge, especially to do efficiently. Disclosure: My team at Salesforce Research use Chainer extensively and my colleague James Bradbury was a contributor to PyTorch whilst it was in stealth mode. We're planning to transition from Chainer to PyTorch for future work. [1]: http://chainer.org/ [2]: https://github.com/clab/dynet [3]: https://twitter.com/jekbradbury/status/821786330459836416
In PyTorch – Tensors and Dynamic neural networks in Python
eveningcoffee·Oct 17, 2016
I am wondering what do they mean by "works well with networks that have dynamic structures that change for every training instance". Can somebody explain why it could be useful and point towards some use case? I checked the only currently given example https://github.com/clab/dynet/blob/master/doc/tutorial.md and it seems to be just a very simple neural network. Their papers indicate that their main interest is in textual models that is a bit different from the main focus of my interest.
In DyNet – Dynamic neural network library

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.