Yonghongwei / Gradient-Centralization
A New Optimization Technique for Deep Neural Networks
☆535Updated 3 years ago
Alternatives and similar repositories for Gradient-Centralization:
Users that are interested in Gradient-Centralization are comparing it to the libraries listed below
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.☆698Updated 3 years ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆334Updated 5 years ago
- Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)☆473Updated 3 months ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆310Updated 5 years ago
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆593Updated 4 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆418Updated 10 months ago
- Implementation of the mixup training method☆466Updated 6 years ago
- Standardizing weights to accelerate micro-batch training☆547Updated 3 years ago
- PyTorch DataLoaders implemented with DALI for accelerating image preprocessing☆880Updated 4 years ago
- Pytorch implementation of newly added convolution☆587Updated 5 years ago
- PyTorch implementation of AutoAugment.☆159Updated 4 years ago
- Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'☆334Updated 3 years ago
- Efficient Learning of Augmentation Policy Schedules☆505Updated 5 years ago
- PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models☆293Updated 4 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆585Updated 3 years ago
- Code for paper☆560Updated 3 years ago
- Stochastic Weight Averaging in PyTorch☆969Updated 3 years ago
- torchsummaryX: Improved visualization tool of torchsummary☆304Updated 3 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆161Updated 4 years ago
- Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019☆609Updated 3 years ago
- Over9000 optimizer☆427Updated 2 years ago
- Search for RegNet using PyTorch☆316Updated 4 years ago
- My best practice of training large dataset using PyTorch.☆1,092Updated 10 months ago
- Deep Learning Experiment Management☆640Updated 2 years ago
- High-level batteries-included neural network training library for Pytorch☆397Updated 3 years ago
- Implementing Attention Augmented Convolutional Networks using Pytorch☆649Updated 3 years ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆792Updated last year
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆984Updated this week
- Implementations of ideas from recent papers☆392Updated 4 years ago
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,197Updated last year