As our final project, we decided to create a compilation of Tensorflow best practices using GPU profiling tools. The final project, presented as a series of blog posts, can be found https://aistein.github.io/dlprof/.
- DeepCoNN - This directory contains examples involving the Joint Modeling of User and Item Review model.
- docs - This directory contains the source for the blog
- images - This directory contains images presented as a project update on 4/15/18
- intel_mkl - This directory contains all of the necessary code and scripts to build tensorflow from scratch with various different settings
- misc - This directory contains miscellaneous data files used to generate graphs or present results
- mnist_data_format - This directory contains examples testing data formats for convolutional networks
- mnist_xla - This directory contains tests and configurations to compile tensorflow from scratch using XLA and test it
- preprocessing - This directory contains code necessary for preprocessing text data for the DeepCoNN models
- report - This directory contains the latex source for our final report submission
Michael Alvarino - maa2282@columbia.edu Alexander Stein - as5281@columbia.edu