timgaripov / swaLinks
Stochastic Weight Averaging in PyTorch
☆975Updated 4 years ago
Alternatives and similar repositories for swa
Users that are interested in swa are comparing it to the libraries listed below
Sorting:
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆338Updated 6 years ago
- mixup: Beyond Empirical Risk Minimization☆1,197Updated 4 years ago
- Implementations of ideas from recent papers☆392Updated 5 years ago
- 2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552☆555Updated 5 years ago
- Efficient Learning of Augmentation Policy Schedules☆508Updated 6 years ago
- Official Implementation of 'Fast AutoAugment' in PyTorch.☆1,613Updated 4 years ago
- Over9000 optimizer☆424Updated 3 years ago
- Code snippets created for the PyTorch discussion board☆570Updated 4 years ago
- ☆1,145Updated 2 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆987Updated 6 months ago
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆596Updated 5 years ago
- Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow☆1,494Updated 2 years ago
- Standardizing weights to accelerate micro-batch training☆549Updated 3 years ago
- A New Optimization Technique for Deep Neural Networks☆540Updated 3 years ago
- Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)☆867Updated 3 years ago
- Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019☆615Updated 4 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆314Updated 6 years ago
- Fine-tune pretrained Convolutional Neural Networks with PyTorch☆724Updated last year
- ☆535Updated 3 years ago
- Weakly Supervised Learning On Images☆602Updated 4 years ago
- Code for reproducing Manifold Mixup results (ICML 2019)☆495Updated last year
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆805Updated last year
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆992Updated last year
- Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10…☆870Updated 5 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆420Updated last year
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,208Updated 2 years ago
- Code for Noisy Student Training. https://arxiv.org/abs/1911.04252☆764Updated 4 years ago
- PyTorch Boilerplate For Research☆608Updated 3 years ago
- My best practice of training large dataset using PyTorch.☆1,106Updated last year
- Implementation of the mixup training method☆471Updated 7 years ago