Mittwoch 26 September 2018 um 13:03

Keras

Von Eric Antoine Scuccimarra

When I first started working with TensorFlow I didn't really like Keras. It seemed like a dumbed down interface to TensorFlow and I preferred having greater control over everything to the ease of use of Keras. However I have recently changed my mind. When you use Keras with a TensorFlow back-end you can still use TensorFlow if you need to tweak something that you can't in Keras, but otherwise Keras just provides an easier to use way to access TensorFlow's functionality. This is especially useful for prototyping models since you can easily make changes without having to write or rewrite a lot of code. I used to write my own functions to do things like make a convolutional layer, but most of that was duplicating functionality that already exists in Keras. 

My original opinion was incorrect, Keras is a valuable tool for creating neural networks, and since you can mix TensorFlow in, there is nothing lost by using it.

Etiketten: machine_learning, tensorflow, keras


Bemerkungen

Anmeldung oder Registrieren einen Kommentar hinterlassen..


Jarvisicets

Sep 29, 2018 at 04:26 am

Привет всем участникам форума! Нашел приколы за день на этом сайте: http://coolrobo.ru : http://coolrobo.ru/foto-prikoly-interesnoe/3557-fotograf-catherine-servel.html <b> Фотограф Catherine Servel </b> <a href=http://coolrobo.ru/foto-prikoly-interesnoe/2997-krasivye-devushki-27.html> Красивые девушки #27 </a> http://coolrobo.ru/foto-prikoly-interesnoe/3938-fotograf-pascal-amoyel.html

Archiv