loshchil / AdamW-and-SGDW
Decoupled Weight Decay Regularization (ICLR 2019)
☆262Updated 5 years ago
Related projects: ⓘ
- Implementations of ideas from recent papers☆391Updated 3 years ago
- ☆250Updated 7 years ago
- Code for experiments regarding importance sampling for training neural networks☆320Updated 2 years ago
- Implementation for the Lookahead Optimizer.☆236Updated 2 years ago
- Totally Versatile Miscellanea for Pytorch☆461Updated 2 years ago
- Stochastic Weight Averaging in PyTorch☆959Updated 3 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆212Updated 6 years ago
- Robust Bi-Tempered Logistic Loss Based on Bregman Divergences. https://arxiv.org/pdf/1906.03361.pdf☆146Updated 2 years ago
- Wide Residual Networks (WideResNets) in PyTorch☆331Updated 3 years ago
- Experimental ground for optimizing memory of pytorch models☆356Updated 6 years ago
- pytorch implement of Lookahead Optimizer☆188Updated 2 years ago
- Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…☆148Updated 5 years ago
- A drop-in replacement for CIFAR-10.☆234Updated 3 years ago
- Code to reproduce some of the figures in the paper "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima"☆137Updated 7 years ago
- Efficient PyTorch Hessian eigendecomposition tools!☆355Updated 6 months ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆333Updated 5 years ago
- Experiments with Adam/AdamW/amsgrad☆194Updated 6 years ago
- A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.☆238Updated 3 years ago
- Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch☆457Updated 4 years ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆405Updated last month
- Snapshot Ensembles in Torch (Snapshot Ensembles: Train 1, Get M for Free)☆190Updated 7 years ago
- Code for reproducing Manifold Mixup results (ICML 2019)☆482Updated 5 months ago
- A PyTorch implementation of Learning to learn by gradient descent by gradient descent☆309Updated 6 years ago
- hessian in pytorch☆185Updated 3 years ago
- 2.86% and 15.85% on CIFAR-10 and CIFAR-100☆295Updated 5 years ago
- Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"☆458Updated 5 years ago
- Implementation and experiments for AdamW on Pytorch☆93Updated 4 years ago
- Public repo for Augmented Multiscale Deep InfoMax representation learning☆396Updated 4 years ago
- A large scale study of Knowledge Distillation.☆217Updated 4 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆542Updated 4 years ago