Skip to content

Computation using data flow graphs for scalable machine learning

License

Notifications You must be signed in to change notification settings

TimoHackel/ILA-SCNN

 
 

Repository files navigation




ILA-SCNN

This repository contains the source code of our paper: Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks Our implementation extents tensorflow by providing GPU implementations for layers that are able efficiently process large-scale, sparse data. For more details please refer to our paper.

Installation

After cloning this repository:

  1. Follow: Installing TensorFlow to install tensorflow from source code.

  2. build our sparse modules:

bazel build -c opt --config=cuda --strip=never -s //tensorflow/core/user_ops:direct_sparse_conv_kd.so
  1. set environment variables
echo 'export LD_LIBRARY_PATH="${LD_LIBRARY_PATH}:$HOME/src/ILA-SCNN/bazel-bin/tensorflow/core/user_ops"' >> ~/.bashrc
echo 'export PYTHONPATH="$PYTHONPATH:$HOME/src/ILA-SCNN/tensorflow/core/user_ops"' >> ~/.bashrc
source ~/.bashrc

Examples

We provide the following examples:

  1. Modelnet Application
  2. MNIST Application

The correct data sets will be downloaded automatically when running the scripts.

About

Computation using data flow graphs for scalable machine learning

Resources

License

Code of conduct

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 47.1%
  • Python 41.2%
  • HTML 5.9%
  • Jupyter Notebook 2.5%
  • Go 1.3%
  • Java 0.7%
  • Other 1.3%