Skip to content

Simple examples demonstrating techniques of deep learning model manipulation.

Notifications You must be signed in to change notification settings

DT42/neural-network-model-manipulations

Repository files navigation

Introduction

Simple examples demonstrating techniques of deep learning model manipulation.

  • mnist-nn.py: 3-layer neural network as digit recognizer (MNIST).
  • mnist-nn-gpu.py: mnist-nn with GPU computing.
  • mnist-nn-data-parallelism.py: mnist-nn with data parallelism (MPI and GPU).

Job file is the wrapper of a MPI command. To distribute a program via MPI, you can indicate the configurations of worknodes (address or hostname, processor numbers, etc.) in a hostfile or CLI. For more details about hostfile, you can refer to Open MPI's Q&A.

Setup development environment

Please refer to .

About

Simple examples demonstrating techniques of deep learning model manipulation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published