François Chollet on Twitter: "If you're using the standalone Keras package ("keras" from PyPI or from https://t.co/x6ipPP693D -- *not* tf.keras), what backend do you use?"

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

1. Tucker Clark‏ @TuckerClark19 25 Mar 2019
  Replying to @fchollet
  
  PlaidML for laptop usually. I’ve noticed some applications run the same speed, especially hyperparameter grid search in my case
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. kelvindotchan‏ @kelvindotchan 25 Mar 2019
  Replying to @fchollet
  
  Anyone here know if there’s if any systematic performance diff between standalone keras vs. tf.keras in some reasonably Apple 2 Apple case...
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Rao Zvorovski‏ @RaoZvorovski 26 Mar 2019
  Replying to @fchollet
  
  PlaidML
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Bojan Tunguz‏ @tunguz 26 Mar 2019
  Replying to @fchollet
  
  Thank used to be my preference, but since development of it ceased, I have pretty much no choice but to use TF.
  
  3 retweets 4 likes
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Pierre-Michel Danton‏ @pmdanton 26 Mar 2019
  Replying to @fchollet
  
  TF, but switching to tf.keras for things like http://tf.data .Dataset.
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Syco Circus‏ @syco_circus 26 Mar 2019
  Replying to @fchollet
  
  Theano was fantastic, but beheaded by Tensorflow...
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Chan Kha Vu‏ @chankhavu 27 Mar 2019
  Replying to @fchollet
  
  I have a sad feeling that very soon, standalone keras will be put on stale and new features (that requires backend tweaks) will only be developed for tf.keras :(( (Not a Theano/CNTK user tho so im still happy with that)
  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

François CholletVerified account

@fchollet

Tweets

Loading seems to be taking a while.

false

Saved searches

Tweets

François CholletVerified account

@fchollet

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