HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
tensorflow
tensorflow
C++2015–2025
tensorflow / tensorflow

tensorflow

An Open Source Machine Learning Framework for Everyone

AI & Machine LearningSystems & InfrastructureLearning & ReferenceNetworking
Explore on GitHubRead Hacker News discussions
220Distinct people
304Mentions
2Explicit recommenders
201.6KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

An Open Source Machine Learning Framework for Everyone

GitHub

Where it is used

  • Twitter Home Timeline — Twitter Home Timeline uses TensorFlow to serve all production traffic for its ranking system using a split-network architecture. Source
  • Airbnb — Airbnb uses TensorFlow to classify images and detect objects at scale to improve the guest experience. This describes a concrete ML application in Airbnb’s product. Source

What people are saying

My friend, you've come to the right place. I happen to be a 33yo fellow dinosaur. If you thought I was some ML guru, know that I spent the last few months watching an 18yo and…

sillysaurusx used a recommendation phrase. 2 indexed comments match. This is a phrase match, not a verdict.

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

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 6:01:08 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 year304 dated mentions

Observed mentions: 2015-11-09 14:23:42 UTC to 2025-11-25 02:58:19 UTC.

0204060802015-01-01 00:00:00 UTC to 2016-01-01 00:00:00 UTC (exclusive): 12 mentions; 2 submissions, 10 comments20152016-01-01 00:00:00 UTC to 2017-01-01 00:00:00 UTC (exclusive): 61 mentions; 16 submissions, 45 comments2017-01-01 00:00:00 UTC to 2018-01-01 00:00:00 UTC (exclusive): 83 mentions; 22 submissions, 61 comments2018-01-01 00:00:00 UTC to 2019-01-01 00:00:00 UTC (exclusive): 51 mentions; 17 submissions, 34 comments2019-01-01 00:00:00 UTC to 2020-01-01 00:00:00 UTC (exclusive): 27 mentions; 13 submissions, 14 comments2020-01-01 00:00:00 UTC to 2021-01-01 00:00:00 UTC (exclusive): 20 mentions; 6 submissions, 14 comments20202021-01-01 00:00:00 UTC to 2022-01-01 00:00:00 UTC (exclusive): 22 mentions; 6 submissions, 16 comments2022-01-01 00:00:00 UTC to 2023-01-01 00:00:00 UTC (exclusive): 11 mentions; 1 submissions, 10 comments2023-01-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 10 mentions; 1 submissions, 9 comments2024-01-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 4 mentions; 3 submissions, 1 comments2025-01-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 3 mentions; 1 submissions, 2 comments2025

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
20152015-01-01 00:00:00 UTC2016-01-01 00:00:00 UTC12210
20162016-01-01 00:00:00 UTC2017-01-01 00:00:00 UTC611645
20172017-01-01 00:00:00 UTC2018-01-01 00:00:00 UTC832261
20182018-01-01 00:00:00 UTC2019-01-01 00:00:00 UTC511734
20192019-01-01 00:00:00 UTC2020-01-01 00:00:00 UTC271314
20202020-01-01 00:00:00 UTC2021-01-01 00:00:00 UTC20614
20212021-01-01 00:00:00 UTC2022-01-01 00:00:00 UTC22616
20222022-01-01 00:00:00 UTC2023-01-01 00:00:00 UTC11110
20232023-01-01 00:00:00 UTC2024-01-01 00:00:00 UTC1019
20242024-01-01 00:00:00 UTC2025-01-01 00:00:00 UTC431
20252025-01-01 00:00:00 UTC2026-01-01 00:00:00 UTC312

What Hacker News says

12 sources
Smerity·Dec 29, 2015
Given how many deep learning toolkits have popped up and the complexities involved, these evaluations are quite useful. Code comparisons would be even better but I feel that's asking too much given how quickly things move :) One important note, if you're looking to actually do standard tasks, use a higher level library. My favourite is fchollet's Keras[1] given that it supports using both Theano and TensorFlow as backends. It will likely support more in the future, giving you better performance (i.e. Neon is likely the next contender) and helping prevent legacy toolkit specific code. I'm confident many of the issues with TensorFlow will be cleared up sooner than later, especially given it was only open sourced a month and a half ago. As an example, bidirectional RNNs are trivial to implement by yourself (~5 lines of code) but additionally
Read the rest
TensorFlow has working code for that already in TensorFlow 0.6[2], the API is just not publicly listed. Most important for this, single device performance is already at cuDNNv2 Torch levels for TensorFlow given the 0.6 update[3]. Both soumith and this evaluation haven't updated the numbers but Google replicated the benchmarks and presented them at NIPS. They're working on adding cuDNNv3 support, which should be another speed jump. [1]: http://keras.io/ [2]: https://github.com/tensorflow/tensorflow/blob/master/tensorf... [3]: https://twitter.com/deliprao/status/673888452736245760
In Evaluation of Deep Learning Toolkits
takeda·Nov 18, 2015
TensorFlow and App Engine are both released by Google which prefers Py2 because of the FUD, although regarding TF hopefully it won't be for too long. The first issue created on GitHub[1] is basically about adding Py3 support. Regarding GIL and JIT. Those problems are mostly performance related and not easy. As you mentioned GIL is available everywhere so it's not a good argument regarding py2 vs py3. As for JIT you get it with PyPy which by itself is not 100% compatible with CPython (for example as of now majority of python modules written in C simply won't work). Although they do have PyPy compatible with Python 3 although it is not as stable, but since Py3 is picking up hopefully it will be becoming more popular. For me, it's the other way around, I have not used PyPy primarily because it's compatible 2.7 and I don't use Python for perf
Read the rest
ormance, but if I could get performant Py3 implementation then why wouldn't I want to use it? [1] https://github.com/tensorflow/tensorflow/issues/1
In Python 3 makes it easier to develop high-quality software
Smerity·Nov 12, 2015
Honestly, there are enough issues with TensorFlow right now due to CUDA 3.0 that using it with AWS is highly problematic. I appreciate the author's attempt, but there's no way the five lines of code he changed to allow CUDA 3.0 has fixed any of the issues found in [1], such as NaNs during training, equally slow training on a g2.2xlarge as a g2.8xlarge, etc ... If you're just interested in playing around, then your laptop will do fine - TensorFlow is happy with just about any hardware you throw at it. Hell, your modern Android phone will run it =] If you're interested in a more involved experiment, develop and debug your task locally on your laptop. By the time you're ready for large scale training, there might be a stable and battle tested AMI such that people are no longer reporting issues in [1] about it. Again, if you're interested, fo
Read the rest
llow the CUDA 3.0 issue on GitHub[1] - this is nowhere near a solved problem and will only cause headaches if you're using it for education. [1]: https://github.com/tensorflow/tensorflow/issues/25
In Show HN: TensorFlow for AWS on a Real GPU
albertzeyer·Nov 9, 2015
I'm looking at the RNN implementation right now (https://github.com/tensorflow/tensorflow/blob/master/tensorf...). It looks like the loop over the time frames is actually in Python itself. for time, input_ in enumerate(inputs): ... This confuses me a bit. Maybe the shape is not symbolic but must be fixed. I also haven't seen some theano.scan equivalent. Which is not needed in many cases when you know the shape in advance.
In TensorFlow: open-source library for machine intelligence

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.