Skip to content

Tensorflow

Projects done in Tensorflow - either using Graph Execution or Eager Execution.

Tensorflow ODE Solver

A library built to replicate the TorchDiffEq library built for the Neural Ordinary Differential Equations paper by Chen et al, running entirely on Tensorflow Eager Execution.

All credits for the codebase go to @rtqichen for providing an excellent base to reimplement from.

Similar to the PyTorch codebase, this library provides ordinary differential equation (ODE) solvers implemented in Tensorflow Eager. For usage of ODE solvers in deep learning applications, see Neural Ordinary Differential Equations paper.

As the solvers are implemented in Tensorflow, algorithms in this repository are fully supported to run on the GPU.

PySHAC - Sequential Halving and Classification

PySHAC is a python library to use the Sequential Halving and Classification algorithm from the paper Parallel Architecture and Hyperparameter Search via Successive Halving and Classification with ease.