Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @theshawwn
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @theshawwn
-
Prikvačeni tweet
#laarc now has a "suggest title" link on the submission page. Submit a story! https://www.laarc.io/ Thanks to the https://lobste.rs/ crew for suggesting this.pic.twitter.com/DvOMpSkBUG
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Biggan paper: https://arxiv.org/abs/1809.11096
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In section 4 of the biggan paper, they present a technique that seems to predict mode collapse. Anyone know how these graphs were made? Or describe it in pseudocode?pic.twitter.com/dCdiJABoxs
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Shawn Presser proslijedio/la je Tweet
i made another one because i like them and also why not

#pixelart#gamedev#indiedevpic.twitter.com/dokvk2lGodPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
That feeling when you want the TPUs to preempt so that you can reset them and go to bed. I should really stop creating TPUs at 1am.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Shawn Presser proslijedio/la je Tweet
i guess it was a matter of time before someone tried feeding tentacle porn to a styleganhttps://twitter.com/theshawwn/status/1223707550194880512 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The “outside ML/AI” caveat made me smile. It’s why I fucking love working in AI. The field is so new! Small ideas from other fields can have huge impacts here. (Making it easy to add beautiful UI for AI projects, for example.)https://twitter.com/dvirsky/status/1223325470764101632 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Shawn Presser proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
I wonder when twitter will mark these as sensitive content. By the way, you can watch it train here: https://animefaces.now.sh/octo128 pic.twitter.com/lB45wW8kkl
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Shawn Presser proslijedio/la je Tweet
random walk looks kinda cool. I might try to get a bigger dataset or play with hyperparams to train it further. This is ~300 kimgpic.twitter.com/QKpp4XaSFF
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Started training stylegan2 on tentacle porn last night. The early results are neat (and SFW). I decided to do tentacle porn because it seems challenging for stylegan to learn, and the idea was too funny to pass up. Credit to that one dude on IRC who gathered 2,483 images.pic.twitter.com/QO9N5KBcyT
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Shawn Presser proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Shawn Presser proslijedio/la je Tweet
Cooperative Communication Networks (CCNs [or whatever we want to call them]) allow us to generate interesting, noise-robust representations with no dataset. See http://www.joelsimon.net/dimensions-of-dialogue.html … andhttps://github.com/noahtren/GlyphNet …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Shawn Presser proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Shawn Presser proslijedio/la je Tweet
Have you ever wanted to interpolate with categorical variables? What does that even mean? Let me show you!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Idea: An optimizer like Adam (one estimate per weight) + LARS (a learning rate per layer). https://arxiv.org/abs/1708.03888 I’m not sure it makes sense, but it seems worth exploring.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
7. Beautiful code. I was surprised just how pretty the benchmark code was. And I think it’s why it’s fast. Wild animals are beautiful because they have hard lives. This code is beautiful because it has zero overhead. Nothing is wasted.https://github.com/mlperf/training_results_v0.6/blob/master/Google/benchmarks/resnet/implementations/tpu-v3-512-resnet/resnet/imagenet_input.py …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
6. LARS optimizer: https://arxiv.org/pdf/1708.03888.pdf … For TPUv3-256 and above, the batch size is 32,768. Such huge batch sizes cause problems, because you have to raise the learning rate as you increase the batch size. Normally this causes divergence. LARS has a learning rate per layer.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
They exploit this by decoding the jpeg on the TPU’s CPU, random cropping it, then sending it to an individual TPU core for processing. Input processing happens in parallel with resnet training. The TPU’s CPU prepares the next inputs while each TPU core trains on the prev batch.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
”It’s pronounced ‘a sssscalar’.”