DeepReduce

Sparse tensor comms

A framework for efficient communication of sparse tensors in distributed deep learning

A Sparse-tensor Communication Framework for Distributed Deep Learning

GitHub

13 stars
1 watching
7 forks
Language: Python
last commit: about 3 years ago
communicationcompressiondeep-learningdistributed-systemsmachine-learningsparse

Related projects:

Repository Description Stars
tensorflow/mesh A library that enables distributed deep learning by partitioning tensors across processors in a mesh topology. 1,597
uncomplicate/deep-diamond A fast Clojure library for computing with tensors and neural networks on CPUs and GPUs. 433
stitchfix/ntflib A library designed to factorize highly sparse tensors with guaranteed cost-function decrease 48
jeankossaifi/tensorly-notebooks Tutorials and examples on tensor learning with Python implementations using various deep learning frameworks 429
hoff97/tensorjs A JavaScript library for accelerated tensor computation in web browsers 36
lifanghe/neurips18_surf A toolbox implementing a sparse and low-rank tensor regression algorithm with boosting 12
google/tensornetwork A library for easy and efficient manipulation of tensor networks. 1,826
eaplatanios/tensorflow_scala A Scala API for TensorFlow's deep learning functionality 939
google-research/tf-slim A lightweight library for defining and training neural networks in TensorFlow. 373
vlang/vtl A C library providing an n-dimensional tensor data structure and linear algebra routines 148
palle-k/dl4s A Swift-based library for accelerated tensor operations and dynamic neural networks using reverse mode automatic differentiation. 104
tensorflow/haskell Haskell bindings for a popular machine learning framework, allowing developers to build and deploy neural networks in the Haskell programming language. 1,584
leopiney/tensor-safe A Haskell framework for defining and compiling valid deep learning models to external frameworks like TensorFlow JS or Keras. 101
tensorly/tensorly A Python library providing tools and methods for working with tensors, including decomposition and learning techniques. 1,576
tensorflow/tensorflow An end-to-end platform for building and deploying machine learning applications 186,822