lessw2020 / Ranger21
Ranger deep learning optimizer rewrite to use newest components
☆328Updated last year
Alternatives and similar repositories for Ranger21:
Users that are interested in Ranger21 are comparing it to the libraries listed below
- Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable☆212Updated 3 years ago
- Learning Rate Warmup in PyTorch☆403Updated 3 weeks ago
- NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/☆344Updated last year
- Over9000 optimizer☆427Updated 2 years ago
- Provides everything needed for high performance data loading and augmentation in pytorch.☆319Updated last year
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,196Updated last year
- Implementation of ConvMixer for "Patches Are All You Need? 🤷"☆1,064Updated 2 years ago
- ☆450Updated last year
- Tiny PyTorch library for maintaining a moving average of a collection of parameters.☆421Updated 5 months ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆251Updated 2 years ago
- Escaping the Big Data Paradigm with Compact Transformers, 2021 (Train your Vision Transformers in 30 mins on CIFAR-10 with a single GPU!)☆515Updated 3 months ago
- Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)☆483Updated 3 years ago
- ☆584Updated 4 months ago
- Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.☆233Updated 2 years ago
- PyTorch dataset extended with map, cache etc. (tensorflow.data like)☆328Updated 2 years ago
- Implementation of Nyström Self-attention, from the paper Nyströmformer☆127Updated last year
- Loss function which directly targets ROC-AUC☆245Updated 2 years ago
- Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)☆217Updated this week
- Fast, differentiable sorting and ranking in PyTorch☆792Updated last year
- Collection of PyTorch Lightning implementations of Generative Adversarial Network varieties presented in research papers.☆166Updated 2 years ago
- Code for the Convolutional Vision Transformer (ConViT)☆466Updated 3 years ago
- A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to fac…☆226Updated last month
- Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.☆319Updated last year
- Implementation of Linformer for Pytorch☆270Updated last year
- Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".☆159Updated 3 years ago
- Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"☆1,060Updated 6 months ago
- Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.☆490Updated last year
- Implementation of a U-net complete with efficient attention as well as the latest research findings☆274Updated 10 months ago
- optimizer & lr scheduler & loss function collections in PyTorch☆277Updated this week
- A learning rate range test implementation in PyTorch☆949Updated 3 months ago