You can call `compile()` & `fit()` on this bad boy. It handles callbacks, it has built-in distribution support, etc. It does everything `fit()` usually does. But with your own low-level training algorithm.pic.twitter.com/m2mmbRtcH2
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
You can call `compile()` & `fit()` on this bad boy. It handles callbacks, it has built-in distribution support, etc. It does everything `fit()` usually does. But with your own low-level training algorithm.pic.twitter.com/m2mmbRtcH2
This is *progressive disclosure of complexity* at work: exactly the amount of low-level control over the details that you need, together with the highest achievable amount of high-level convenience & performance optimization. That's exactly the reason why to use a framework.
Hey @fchollet, I just started learning Keras from your book and I am already in love with Keras(which is my first Machine Learning/ Deep Learning Framework). I hope to read the new version of your book soon.
Sir, I have a small question regarding using GAN's for Image processing. Would it be possible to increase the quality of an ordinary image into that of say a DSLR image using GAN's assuming that I am using Keras
I think it’s more dependent on the GAN architecture you use than the framework... Super Res GAN flavors implemented in Keras (and other frameworks) abound
Hi! the unroll you asked for: @fchollet: The most modern way to implement a GAN in Keras is actually simply this. You can call `compile()` & `fit()`… https://threadreaderapp.com/thread/1250622989541838848.html … Share this if you think it's interesting. 
What does adding random noise to the labels do to help in training?
I believe this is a "label smoothing" technique, which seems to have a regularizing effect. In practice, what it does is changing a "hard label" (1.0) to a "soft label" (1.2), for example.
@reebiesss check this out
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.