Skip to content

๐Ÿ““ Internship report on the static analysis and optimization of TensorFlow models.

Notifications You must be signed in to change notification settings

liautaud/snips-internship-report

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

2 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

snips-internship-report

LaTeX sources for my internship report on the static analysis and optimization of TensorFlow models.

โžก๏ธ Latest PDF release of the report and slides.

Summary.

This report summarizes my 2018 internship at Snips under the supervision of Mathieu Poumeyrol, where I worked on improving the performance and energy-efficiency of https://github.com/sonos/tract, their neural network inference engine for single-board computers and embedded devices. This lead to the design and implementation of a static analyzer and optimizer for TensorFlow graphs, as well as the formalization of streaming semantics for TensorFlow graphs.

About

๐Ÿ““ Internship report on the static analysis and optimization of TensorFlow models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published