HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
NVlabs
stylegan2
Python2019–2021
NVlabs / stylegan2

stylegan2

StyleGAN2 - Official TensorFlow Implementation

9Distinct people
12Mentions
0Explicit recommenders
11.2KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

StyleGAN2 - Official TensorFlow Implementation

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

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

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 4:59:52 AM 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 month12 dated mentions

Observed mentions: 2019-12-12 05:33:08 UTC to 2021-10-21 06:41:32 UTC.

01232019-12-01 00:00:00 UTC to 2020-01-01 00:00:00 UTC (exclusive): 3 mentions; 2 submissions, 1 commentsDec 20192020-01-01 00:00:00 UTC to 2020-02-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2020-02-01 00:00:00 UTC to 2020-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-03-01 00:00:00 UTC to 2020-04-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-04-01 00:00:00 UTC to 2020-05-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-05-01 00:00:00 UTC to 2020-06-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2020-06-01 00:00:00 UTC to 2020-07-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2020-07-01 00:00:00 UTC to 2020-08-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2020-08-01 00:00:00 UTC to 2020-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-09-01 00:00:00 UTC to 2020-10-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-10-01 00:00:00 UTC to 2020-11-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-11-01 00:00:00 UTC to 2020-12-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 commentsNov 20202020-12-01 00:00:00 UTC to 2021-01-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-01-01 00:00:00 UTC to 2021-02-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-02-01 00:00:00 UTC to 2021-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-03-01 00:00:00 UTC to 2021-04-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-04-01 00:00:00 UTC to 2021-05-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-05-01 00:00:00 UTC to 2021-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-06-01 00:00:00 UTC to 2021-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-07-01 00:00:00 UTC to 2021-08-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-08-01 00:00:00 UTC to 2021-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-09-01 00:00:00 UTC to 2021-10-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-10-01 00:00:00 UTC to 2021-11-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 commentsOct 2021

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
Dec 20192019-12-01 00:00:00 UTC2020-01-01 00:00:00 UTC321
Jan 20202020-01-01 00:00:00 UTC2020-02-01 00:00:00 UTC101
Feb 20202020-02-01 00:00:00 UTC2020-03-01 00:00:00 UTC000
Mar 20202020-03-01 00:00:00 UTC2020-04-01 00:00:00 UTC000
Apr 20202020-04-01 00:00:00 UTC2020-05-01 00:00:00 UTC000
May 20202020-05-01 00:00:00 UTC2020-06-01 00:00:00 UTC101
Jun 20202020-06-01 00:00:00 UTC2020-07-01 00:00:00 UTC101
Jul 20202020-07-01 00:00:00 UTC2020-08-01 00:00:00 UTC202
Aug 20202020-08-01 00:00:00 UTC2020-09-01 00:00:00 UTC000
Sep 20202020-09-01 00:00:00 UTC2020-10-01 00:00:00 UTC000
Oct 20202020-10-01 00:00:00 UTC2020-11-01 00:00:00 UTC000
Nov 20202020-11-01 00:00:00 UTC2020-12-01 00:00:00 UTC202
Dec 20202020-12-01 00:00:00 UTC2021-01-01 00:00:00 UTC000
Jan 20212021-01-01 00:00:00 UTC2021-02-01 00:00:00 UTC000
Feb 20212021-02-01 00:00:00 UTC2021-03-01 00:00:00 UTC000
Mar 20212021-03-01 00:00:00 UTC2021-04-01 00:00:00 UTC000
Apr 20212021-04-01 00:00:00 UTC2021-05-01 00:00:00 UTC000
May 20212021-05-01 00:00:00 UTC2021-06-01 00:00:00 UTC000
Jun 20212021-06-01 00:00:00 UTC2021-07-01 00:00:00 UTC000
Jul 20212021-07-01 00:00:00 UTC2021-08-01 00:00:00 UTC000
Aug 20212021-08-01 00:00:00 UTC2021-09-01 00:00:00 UTC000
Sep 20212021-09-01 00:00:00 UTC2021-10-01 00:00:00 UTC000
Oct 20212021-10-01 00:00:00 UTC2021-11-01 00:00:00 UTC202

What Hacker News says

1 sources
Oooh, you're so lucky you get to work on those kinds of problems. I know sometimes it feels frustrating to hunt for bottlenecks, but man is it satisfying to find it. We had a similar situation at one point. The problem turned out to be that our CPU wasn't generating input data fast enough. So the first step is to confirm that your input pipeline isn't the issue. The next step would be to break down the problem: Can you extract the smallest part of the codebase into a separate program, and try to make that run under full load? That's not the technique I used, though. To figure out the multicore stuff, the trick for me was to comment out almost all of the code, until you're left with only a small part that actually runs on the device. Ideally the smallest part. Basically, change your code so that the model file returns tf.no_op() (or as clo
Read the rest
se to that as possible while still letting your input pipeline run). You want to be in a situation where your training loop is doing an equivalent of while(true) { read_input(); } so that you can verify that your pipeline is able to peg your GPUs to 100% usage. If you get 100% usage, fantastic! That means you're left with an easy problem: start turning parts of the code back on until you find which part is reducing your performance. Then study that part to figure out why. If you're not at 100% usage, you're either running into a fundamental limitation (which sometimes happens) or the pipeline isn't designed correctly in some way. I would compare it against other popular codebases such as StyleGAN 2 https://github.com/NVlabs/stylegan2 which is designed to use 8 V100s. The optimizer.py file is pretty insightful: https://github.com/NVlabs/stylegan2/blob/eecd09cc8a067e09e12... Finally, my biggest tip would be to step back from the problem and think: is there something simple you can do to reframe the problem? When I find myself in a situation where I'm spending a lot of time and energy trying to get a certain thing to work, I can sometimes do X instead for 80% of the benefit. Try to find something like that in this case. FWIW the TPU profiler was the first tool I reached for. I never got it working. The bag of tricks above ended up giving me effective results on a variety of codebases with no profiler. (A usage graph is pretty crucial, though, which Colab TPUs don't provide.) So there are a bunch of general tips for solving weird bottlenecks blindfolded. To answer your question directly: I am assuming the profiler from Tensorflow works with TPUs in the same way it does with GPUs? Not really. You're supposed to use cloud_tpu_profiler: https://cloud.google.com/tpu/docs/cloud-tpu-tools But yeah, if you give specifics (ideally a link to a codebase + dataset + script that runs it) then I can try to look for candidates of what might be the bottleneck.
In AMD’s 64-Core Threadripper 3990X, only $3990 Coming February 7th

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.