Skip to content
By using Twitter’s services you agree to our Cookies Use. We and our partners operate globally and use cookies, including for analytics, personalisation, and ads.
  • Home Home Home, current page.
  • About

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @
  • Language: English
    • Bahasa Indonesia
    • Bahasa Melayu
    • Català
    • Čeština
    • Dansk
    • Deutsch
    • English UK
    • Español
    • Filipino
    • Français
    • Hrvatski
    • Italiano
    • Magyar
    • Nederlands
    • Norsk
    • Polski
    • Português
    • Română
    • Slovenčina
    • Suomi
    • Svenska
    • Tiếng Việt
    • Türkçe
    • Ελληνικά
    • Български език
    • Русский
    • Српски
    • Українська мова
    • עִבְרִית
    • العربية
    • فارسی
    • मराठी
    • हिन्दी
    • বাংলা
    • ગુજરાતી
    • தமிழ்
    • ಕನ್ನಡ
    • ภาษาไทย
    • 한국어
    • 日本語
    • 简体中文
    • 繁體中文
  • Have an account? Log in
    Have an account?
    · Forgot password?
    New to Twitter?
    Sign up
fchollet's profile
François Chollet
François Chollet
François Chollet
Verified account
@fchollet

Tweets

François CholletVerified account

@fchollet

Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.

United States
fchollet.com
Joined August 2009

Tweets

  • © 2021 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Cookies
  • Ads info
Dismiss
Previous
Next

Go to a person's profile

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @

Promote this Tweet

Block

  • Tweet with a location

    You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more

    Your lists

    Create a new list

    Under 100 characters, optional
    Privacy

    Copy link to Tweet

    Embed this Tweet

    Embed this Video

    Add this Tweet to your website by copying the code below. Learn more

    Add this video to your website by copying the code below. Learn more

    Hmm, there was a problem reaching the server.

    By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.

    Preview

    Why you're seeing this ad

    Log in to Twitter

    · Forgot password?
    Don't have an account? Sign up »

    Sign up for Twitter

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

    Sign up
    Have an account? Log in »

    Two-way (sending and receiving) short codes:

    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

    Confirmation

     

    Welcome home!

    This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.

    Tweets not working for you?

    Hover over the profile pic and click the Following button to unfollow any account.

    Say a lot with a little

    When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.

    Spread the word

    The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.

    Join the conversation

    Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.

    Learn the latest

    Get instant insight into what people are talking about now.

    Get more of what you love

    Follow more accounts to get instant updates about topics you care about.

    Find what's happening

    See the latest conversations about any topic instantly.

    Never miss a Moment

    Catch up instantly on the best stories happening as they unfold.

    1. François Chollet‏Verified account @fchollet Jul 12

      This builds the following graph:pic.twitter.com/WQzvf6bJZh

      1 reply 1 retweet 24 likes
      Show this thread
    2. François Chollet‏Verified account @fchollet Jul 12

      Now, of course, you could also define such a model as a Python class. It would then look like this:pic.twitter.com/2oU0vjOIHe

      3 replies 1 retweet 26 likes
      Show this thread
    3. François Chollet‏Verified account @fchollet Jul 12

      But there are several key advantages of the Functional approach over the subclassing approach: 1. Your model has known inputs shapes. 2. You get access to the internal connectivity graph. 3. The model is a data structure, not a piece of bytecode. Let's see what these are about.

      2 replies 0 retweets 33 likes
      Show this thread
    4. François Chollet‏Verified account @fchollet Jul 12

      1. Because the model has known input shapes, it's capable of running input validation checks, for easy debugging:pic.twitter.com/1B8E7GXmK1

      1 reply 1 retweet 19 likes
      Show this thread
    5. François Chollet‏Verified account @fchollet Jul 12

      Further, it's even capable of standardizing inputs to what it expects: if you pass data of shape (batch_size,) to a model that expects (batch_size, 1), it will just reshape it. Likewise for dtype conversion (e.g. float64 will get converted to float32).

      1 reply 0 retweets 15 likes
      Show this thread
    6. François Chollet‏Verified account @fchollet Jul 12

      2. You get access to the internal connectivity graph. This means you can plot the model, for instance. This is great for debugging. Like this:pic.twitter.com/ZnG6ym9yei

      1 reply 0 retweets 38 likes
      Show this thread
    7. François Chollet‏Verified account @fchollet Jul 12

      Having access to internal nodes also means you can access an intermediate layer output and leverage it in a new model. This is a killer feature for feature extraction, fine-tuning, and ensembling. Let's add an extra output to the model above:pic.twitter.com/gCxafm21UF

      1 reply 0 retweets 27 likes
      Show this thread
    8. François Chollet‏Verified account @fchollet Jul 12

      3. The model is a data structure, not a piece of bytecode. This means it can be cleanly serialized and deserialized -- even across platforms. keras.Model.from_config(functional_model.get_config()) reconstructs the exact same model as the original.

      1 reply 1 retweet 24 likes
      Show this thread
    9. François Chollet‏Verified account @fchollet Jul 12

      If your model is a Python subclass, to serialize it you could either: a. Pickle the bytecode -- which it completely unsafe, won't work for production, and won't work across platforms

      2 replies 2 retweets 15 likes
      Show this thread
    10. jΞff‏ @feedyurhed Jul 12
      Replying to @fchollet

      c. Decouple your persistence from your object model :)

      1 reply 0 retweets 1 like
      François Chollet‏Verified account @fchollet Jul 12
      Replying to @feedyurhed

      I guess you mean only saving the weights, and always re-executing the original code when loading the model. This is definitely better than saving the bytecode, but it's limited: it implies you will still have access to the original code, and it won't work across platforms.

      2:34 PM - 12 Jul 2021
      1 reply 0 retweets 0 likes
        1. New conversation
        1. François Chollet‏Verified account @fchollet Jul 12
          Replying to @fchollet @feedyurhed

          So if you want to load your model in JavaScript, you'd have to write a JS version of your model first, then you'd load your saved weights. This is potentially error-prone. With the Functional API, you can save your model in Python then reload it in JS w/o writing any model code.

          1 reply 0 retweets 0 likes
        2. jΞff‏ @feedyurhed Jul 12
          Replying to @fchollet

          Honestly I don’t know what I’m talking about but my preference would always be to create that abstraction and yes, serialize the weights and couple that to a bound representation. Out of curiosity do you guys ever define architectures by just zeroizing large parts of the matrix?

          1 reply 0 retweets 0 likes
        3. Show replies

      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.

        Promoted Tweet

        false

        • © 2021 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Cookies
        • Ads info