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. Alex J. Champandard‏ @alexjc 1 May 2016
      Replying to @yoavgo

      @yoavgo The images are exactly the same, only the NN changes: no data is loaded and it's basically Lasagne's default weight initialization.

      1 reply 1 retweet 1 like
    2. (((ل()(ل() 'yoav)))) 👾‏ @yoavgo 1 May 2016
      Replying to @alexjc

      @alexjc no, I meant: the doodles pretty much move the rock/bushes/etc around. What if

      1 reply 0 retweets 1 like
    3. (((ل()(ل() 'yoav)))) 👾‏ @yoavgo 1 May 2016
      Replying to @yoavgo

      @alexjc what if you introduce a completely new element in the doodle that was not in image?

      1 reply 0 retweets 1 like
    4. Alex J. Champandard‏ @alexjc 1 May 2016
      Replying to @yoavgo

      @yoavgo The doodle is just a semantic "prior" on the patch selection. I have other completely randomly generated textures (see yesterday).

      1 reply 1 retweet 1 like
    5. (((ل()(ل() 'yoav)))) 👾‏ @yoavgo 1 May 2016
      Replying to @alexjc

      @alexjc I did not understand what is the input to the random textures.

      1 reply 0 retweets 1 like
    6. Alex J. Champandard‏ @alexjc 1 May 2016
      Replying to @yoavgo

      @yoavgo The seed buffer for the optimization is random noise, then photo of wall is used as target for optimization.pic.twitter.com/SgsTMhFC8V

      1 reply 1 retweet 3 likes
    7. (((ل()(ل() 'yoav)))) 👾‏ @yoavgo 1 May 2016
      Replying to @alexjc

      @alexjc can you post original and result of random net side by side? (sorry for nagging..)

      2 replies 0 retweets 0 likes
    8. Alex J. Champandard‏ @alexjc 1 May 2016
      Replying to @yoavgo

      @yoavgo I have a pre-rendered one but networks of difference size. Left is VGG, right is random about 10x smaller.pic.twitter.com/Z4b3bWxnp5

      3 replies 0 retweets 4 likes
    9. deliprao.eth ( 📜, 📜)‏ @deliprao 1 May 2016
      Replying to @alexjc

      @alexjc @yoavgo okay, significant textural differences but still a great tradeoff for 10x

      1 reply 0 retweets 1 like
    10. Alex J. Champandard‏ @alexjc 1 May 2016
      Replying to @deliprao

      @deliprao @yoavgo I think I can remove the noise by just loading pre-trained lowest layer... Still experimenting. It's crazy!

      2 replies 0 retweets 2 likes
      François Chollet‏Verified account @fchollet 1 May 2016
      Replying to @alexjc

      @alexjc @deliprao @yoavgo you could also try it with non-learned first layer kernels (Gabor filters, etc)

      1:17 AM - 1 May 2016
      • 1 Like
      • Alex J. Champandard
      1 reply 0 retweets 1 like
        1. New conversation
        1. deliprao.eth ( 📜, 📜)‏ @deliprao 1 May 2016
          Replying to @fchollet

          @fchollet @alexjc @yoavgo now you are doing feature engineering

          1 reply 0 retweets 1 like
        2. Alex J. Champandard‏ @alexjc 1 May 2016
          Replying to @deliprao

          @deliprao @fchollet @yoavgo :-) It's acceptable if I can scale quality up and down. There's a huge need for that in applications!

          1 reply 0 retweets 1 like
        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