BLACK LIVES MATTER
Join us and donate
The premier IDE for R
RStudio anywhere using a web browser
Put Shiny applications online
Shiny, R Markdown, Tidyverse and more
Do, share, teach and learn data science
An easy way to access R packages
Let us host your Shiny applications
A single home for R & Python Data Science Teams
RStudio for the Enterprise
Easily share your insights
Control and distribute packages
RStudio
RStudio Server
Shiny Server
R Packages
RStudio Cloud
RStudio Public Package Manager
shinyapps.io
RStudio Team
RStudio Server Pro
RStudio Connect
RStudio Package Manager
rstudio::conf 2019 modeling
Why TensorFlow eager execution matters
January 25, 2019
In current deep learning with Keras and TensorFlow, when you've mastered the basics and are ready to dive into more involved applications (such as generative networks, sequence-to-sequence or attention mechanisms), you may find that surprisingly, the learning curve doesn't get much flatter. This is largely due to restrictions imposed by TensorFlow's traditional static graph paradigm. With TensorFlow Eager Execution, available since summer and announced to be the default mode in the upcoming major release, model architectures become more flexible, readable, composable, and last not least, debuggable. In this session, we'll see how with Eager, we can code sophisticated architectures like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) in a straightforward way.
Sigrid has experience a psychologist, software developer and data scientist. She is passionate about exploring the frontiers of deep learning and helping users employ the power of deep learning from R. When she’s not tuning neural networks she loves doing outdoor sports- among her favorites are cycling, running and cross country skiing.