François Chollet on Twitter: "The other day, I posted a Colab "Introduction to Keras for Researchers". Now, you can read "Introduction to Keras for Engineers". Very different focus & priorities :) https://t.co/CMqwjkLSxh"

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. François Chollet‏Verified account @fchollet 29 Apr 2020
  Here is the researcher intro:https://colab.research.google.com/drive/169PfzM0kvtA5UP4k6Sl1yCG9tsE2MLia …
  
  36 retweets 235 likes
  
  Show this thread
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Dr. Tirthajyoti Sarkar (data, AI, free thought)‏ @tirthajyotiS 29 Apr 2020
  Replying to @fchollet
  
  https://towardsdatascience.com/a-single-function-to-streamline-image-classification-with-keras-bd04f5cfe6df …
  
  2 retweets 7 likes
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Robin Ranjit Singh Chauhan‏ @robinc 29 Apr 2020
  Replying to @fchollet
  
  I like keras a lot and started with keras, and Im grateful to you for it! But when I had a nan problem that I couldnt get around, I moved to pytorch and havent had that issue there. (Though Im not clear if that issue isnt present in pytorch or I was just lucky.)
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Dr Antoine Dujon‏ @AMDujon 29 Apr 2020
  Replying to @fchollet
  
  I am an ecologist! The title doesn't matter too much, the code and comments in the document are way more interesting! Thanks for sharing them!
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Srihari Humbarwadi‏ @srihari_rh 29 Apr 2020
  Replying to @fchollet
  
  When we overide train_step, is it the users responsibility to scale the loss when training under distributed context and/or with AMP ? Or is it still taken care by the .fit method ?
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Erg ‏ @KrzemoweEcho 29 Apr 2020
  Replying to @fchollet
  
  very useful! thanks for working on that, François!
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Nuno Rodrigues‏ @nmvrodrigues 29 Apr 2020
  Replying to @fchollet
  
  Could you link the intro for researchers?
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. jeyasri subramanian‏ @jeyasriss 29 Apr 2020
  Replying to @fchollet
  
  This is really great.. thank you..
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Mohamed Niang‏ @Moha__niang 29 Apr 2020
  Replying to @fchollet
  
  Arigato ko zaymass @fchollet .
  
  1 like
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo
1. Fadi Badine‏ @fadibadine 29 Apr 2020
  Replying to @fchollet
  
  Great work! The end-to-end examples url are not working though
  
  1 like
  Thanks. Twitter will use this to make your timeline better. Undo
  
  Undo