Jason Antic on Twitter: "Ohh that’s right. So what you need to do is look for the set of weights that work of all the checkpoints that are saved. Select it, and rename in to what you need here. This is the pain in the ass part of NoGAN at this point. Larger batch size helps a lot in stabilization.… https://t.co/bXObdd8rbr"

Country	Code	For customers of
United States	40404	(any)
Canada	21212	(any)
United Kingdom	86444	Vodafone, Orange, 3, O2
Brazil	40404	Nextel, TIM
Haiti	40404	Digicel, Voila
Ireland	51210	Vodafone, O2
India	53000	Bharti Airtel, Videocon, Reliance
Indonesia	89887	AXIS, 3, Telkomsel, Indosat, XL Axiata
Italy	4880804	Wind
3424486444	Vodafone
» See SMS short codes for other countries

Jason Antic‏ @citnaj 2 Jun 2019

Report Tweet
Report NetzDG Violation

Jason Antic Retweeted Remy

I swear there will be a proper pdf with math galore for NoGAN eventually. I do think it has a lot of potential for to make training better so for now we can at least tweet and blog about it!https://twitter.com/remykarem/status/1135183936227749888 …

Jason Antic added,

Remy @remykarem

NoGAN - a transfer learning technique in GANs: G - generator D - discriminator 1. Pretrain G using perceptual loss 2. Save generated imgs from pretrained G 3. Pretrain D as binary classifier 4. Train both G & D in a normal GAN setting https://www.fast.ai/2019/05/03/decrappify/ …

3 replies 1 retweet 18 likes

David Gillespie‏ @CpnTaters 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @citnaj

I will get round to trying it at some point! Is it set up as a jupyter notebook in Deoldify github?

1 reply 0 retweets 2 likes

Jason Antic‏ @citnaj 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @CpnTaters

NoGAN training is, correct. Just make sure to read the instructions- it's not 100% top down execution.

1 reply 0 retweets 1 like

Brad Dwyer { }‏ @braddwyer 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @citnaj @CpnTaters

I ran into a few errors but I’m pretty sure it’s because I was doing something wrong. Where’s the best place to post for discussion/pointers once I inevitably get stuck? Github issue?

1 reply 0 retweets 0 likes

Jason Antic‏ @citnaj 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @braddwyer @CpnTaters

If it's something you think is useful for others, sure that'd probably be the best place. Otherwise feel free to dm me!

1 reply 0 retweets 2 likes

Brad Dwyer { }‏ @braddwyer 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @citnaj @CpnTaters

I’ve been having trouble getting the repeatable GAN process to run the second time. Still working on investigating. But I’ll follow later this week.

3 replies 0 retweets 0 likes

Jason Antic‏ @citnaj 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @braddwyer @CpnTaters

I carried over a habit from fastai notebooks which may not necessarily be great for this case which is that you have to run some cells carefully before doing the repeat. Namely- you'll need to make sure data_gen is initialized under 64px again. That part is dumb and I know it.

1 reply 0 retweets 0 likes

Brad Dwyer { }‏ @braddwyer 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @citnaj @CpnTaters

If I recall correctly it was that when I switched that part from 0 to 1 it wasn’t finding the 0 checkpoint it had tried to save.

2 replies 0 retweets 1 like

Jason Antic‏ @citnaj 2 Jun 2019

Report Tweet
Report NetzDG Violation

Replying to @braddwyer @CpnTaters

Ohh that’s right. So what you need to do is look for the set of weights that work of all the checkpoints that are saved. Select it, and rename in to what you need here. This is the pain in the ass part of NoGAN at this point. Larger batch size helps a lot in stabilization.

6:41 PM - 2 Jun 2019

1 Like

4 replies 0 retweets 1 like

1. Show replies
1. David Gillespie‏ @CpnTaters 3 Jun 2019
  
  Report Tweet
  
  Report NetzDG Violation
  Replying to @citnaj @braddwyer
  
  So need to save this thread to come back too
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

Tweets

Jason Antic

@citnaj

Tweets

Loading seems to be taking a while.

false

Saved searches

Tweets

Jason Antic

@citnaj

Tweets

Go to a person's profile

Saved searches

Promote this Tweet

Block

Tweet with a location

Your lists

Create a new list

Copy link to Tweet

Embed this Tweet

Embed this Video

Preview

Why you're seeing this ad

Log in to Twitter

Sign up for Twitter

Not on Twitter? Sign up, tune into the things you care about, and get updates as they happen.

Two-way (sending and receiving) short codes:

Confirmation

Welcome home!

Tweets not working for you?

Say a lot with a little

Spread the word

Join the conversation

Learn the latest

Get more of what you love

Find what's happening

Never miss a Moment

Loading seems to be taking a while.

Promoted Tweet

false