facebookresearch / higher
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
☆1,615Updated 3 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☆2,025Updated last year
- A PyTorch Library for Meta-learning Research☆2,765Updated 10 months ago
- torch-optimizer -- collection of optimizers for Pytorch☆3,107Updated last year
- The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) p…☆805Updated last year
- Profiling and inspecting memory in pytorch☆1,056Updated 9 months ago
- Toolbox of models, callbacks, and datasets for AI/ML researchers.☆1,720Updated 3 weeks ago
- disentanglement_lib is an open-source library for research on learning disentangled representations.☆1,400Updated 3 years ago
- A simple way to calibrate your neural network.☆1,144Updated 3 years ago
- [NeurIPS'19] Deep Equilibrium Models☆748Updated 2 years ago
- Fast, differentiable sorting and ranking in PyTorch☆808Updated last year
- Efficient PyTorch Hessian eigendecomposition tools!☆373Updated last year
- PyTorch implementation of Contrastive Learning methods☆1,979Updated last year
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆580Updated 4 months ago
- An Implementation of Model-Agnostic Meta-Learning in PyTorch with Torchmeta☆233Updated 4 years ago
- Fast, general, and tested differentiable structured prediction in PyTorch☆1,111Updated 3 years ago
- Normalizing flows in PyTorch. Current intended use is education not production.☆861Updated 5 years ago
- Code for visualizing the loss landscape of neural nets☆2,972Updated 3 years ago
- A lightweight library for PyTorch training tools and utilities☆1,693Updated this week
- Pytorch Lightning code guideline for conferences☆1,262Updated last year
- Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"☆2,634Updated 5 years ago
- High-quality implementations of standard and SOTA methods on a variety of tasks.☆1,502Updated last week
- Fast Differentiable Sorting and Ranking☆600Updated last year
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆423Updated 2 years ago
- Approximating Wasserstein distances with PyTorch☆459Updated 2 years ago
- Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)☆2,397Updated 5 years ago
- On the Variance of the Adaptive Learning Rate and Beyond☆2,548Updated 3 years ago
- Riemannian Adaptive Optimization Methods with pytorch optim☆919Updated last year
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,201Updated last year
- GPU Accelerated t-SNE for CUDA with Python bindings☆1,857Updated 7 months ago
- A classified list of meta learning papers based on realm.☆359Updated 2 years ago