Contents

gpytorch 1.13

0

An implementation of Gaussian Processes in Pytorch

An implementation of Gaussian Processes in Pytorch

Stars: 3543, Watchers: 3543, Forks: 557, Open Issues: 376

The cornellius-gp/gpytorch repo was created 7 years ago and the last code push was Yesterday.
The project is very popular with an impressive 3543 github stars!

How to Install gpytorch

You can install gpytorch using pip

pip install gpytorch

or add it to a project with poetry

poetry add gpytorch

Package Details

Author
Jake Gardner, Geoff Pleiss
License
MIT
Homepage
https://gpytorch.ai
PyPi:
https://pypi.org/project/gpytorch/
Documentation:
https://gpytorch.readthedocs.io
GitHub Repo:
https://github.com/cornellius-gp/gpytorch

Classifiers

No  gpytorch  pypi packages just yet.

Errors

A list of common gpytorch errors.

Code Examples

Here are some gpytorch code examples and snippets.

GitHub Issues

The gpytorch package has 376 open issues on GitHub

  • tighten test_unwhitened_svgp_regression.py::test_regression_error bound
  • tigthen test_batch_svgp_gp_regression.py::test_regression_error bound
  • Independent GP Inputs
  • Computing a (mixture of hyperparameters) posterior predictive – with a custom method.
  • [Question] Extract one GP from Hadamard Multitask
  • The "predict" method in the Deep GP tutorial does not work correctly.
  • Variational GP, Multitask models
  • [Docs] Is it possible to derive the cholesky factorization of a huge PSD matrix on GPU using GPytorch?
  • [Bug] Gradient computation with KeOps kernel only works with low number of training data, fails otherwise
  • [Bug] Error in the "initialize" method of BatchIndependentMultitaskGPModel.
  • [Bug][Docs] Exact GP with Missing Observations
  • Student T Processes
  • [Question] Implementation of ConstantKernel as in sklearn
  • [Draft] Add Fantasy Strategy for Variational GPs
  • [Question] GridInterpolationVariationalStrategy input for SVDKL

See more issues on GitHub

Related Packages & Articles

flair 0.14.0

A very simple framework for state-of-the-art NLP

fastai 2.7.17

fastai simplifies training fast and accurate neural nets using modern best practices

easyocr 1.7.2

End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution

deepspeed 0.15.2

DeepSpeed is a Python package developed by Microsoft that provides a deep learning optimization library designed to scale across multiple GPUs and servers. It is capable of training models with billions or even trillions of parameters, achieving excellent system throughput and efficiently scaling to thousands of GPUs.

DeepSpeed is particularly useful for training and inference of large language models, and it falls under the category of Machine Learning Frameworks and Libraries. It is designed to work with PyTorch and offers system innovations such as Zero Redundancy Optimizer (ZeRO), 3D parallelism, and model-parallelism to enable efficient training of large models.

datasets 3.0.1

HuggingFace community-driven open-source library of datasets