facebookresearch / higher
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
☆1,610Updated 2 years ago
Alternatives and similar repositories for higher:
Users that are interested in higher are comparing it to the libraries listed below
- A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch☆2,014Updated last year
- A PyTorch Library for Meta-learning Research☆2,729Updated 9 months ago
- Fast and Easy Infinite Neural Networks in Python☆2,323Updated last year
- Toolbox of models, callbacks, and datasets for AI/ML researchers.☆1,717Updated 2 weeks ago
- disentanglement_lib is an open-source library for research on learning disentangled representations.☆1,397Updated 3 years ago
- Profiling and inspecting memory in pytorch☆1,049Updated 7 months ago
- Pytorch library for fast transformer implementations☆1,686Updated last year
- Pytorch Lightning code guideline for conferences☆1,258Updated last year
- PyTorch implementation of Contrastive Learning methods☆1,966Updated last year
- A lightweight library for PyTorch training tools and utilities☆1,683Updated this week
- An Implementation of Model-Agnostic Meta-Learning in PyTorch with Torchmeta☆233Updated 4 years ago
- Normalizing flows in PyTorch. Current intended use is education not production.☆858Updated 5 years ago
- PyTorch implementations of algorithms for density estimation☆578Updated 3 years ago
- torch-optimizer -- collection of optimizers for Pytorch☆3,092Updated 11 months ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆572Updated 2 months ago
- Pytorch implementation of set transformer☆569Updated 5 years ago
- The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) p…☆802Updated last year
- Fast, differentiable sorting and ranking in PyTorch☆796Updated last year
- High-quality implementations of standard and SOTA methods on a variety of tasks.☆1,493Updated last month
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆420Updated 2 years ago
- Code for visualizing the loss landscape of neural nets☆2,932Updated 2 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆370Updated last year
- This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural P…☆993Updated 4 years ago
- A highly efficient implementation of Gaussian Processes in PyTorch☆3,664Updated last week
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,078Updated 3 weeks ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,414Updated this week
- Fast Differentiable Sorting and Ranking☆592Updated last year
- A dataset of datasets for learning to learn from few examples☆775Updated 9 months ago
- Constrained optimization toolkit for PyTorch☆670Updated 3 years ago
- Code snippets created for the PyTorch discussion board☆557Updated 4 years ago