Yonghongwei / Gradient-Centralization
A New Optimization Technique for Deep Neural Networks
☆533Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Gradient-Centralization
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆588Updated 4 years ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆334Updated 5 years ago
- Standardizing weights to accelerate micro-batch training☆546Updated 2 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆417Updated 6 months ago
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.☆693Updated 2 years ago
- Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)☆471Updated this week
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆309Updated 4 years ago
- PyTorch DataLoaders implemented with DALI for accelerating image preprocessing☆880Updated 4 years ago
- Stochastic Weight Averaging in PyTorch☆966Updated 3 years ago
- torchsummaryX: Improved visualization tool of torchsummary☆301Updated 2 years ago
- Scaling and Benchmarking Self-Supervised Visual Representation Learning☆587Updated 3 years ago
- Code for paper☆563Updated 3 years ago
- The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition☆661Updated last year
- My best practice of training large dataset using PyTorch.☆1,086Updated 6 months ago
- Implementation of the mixup training method☆465Updated 6 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆160Updated 4 years ago
- Pytorch implementation of newly added convolution☆583Updated 5 years ago
- Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'☆332Updated 3 years ago
- Over9000 optimizer☆425Updated last year
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,194Updated 10 months ago
- Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' pap…☆397Updated 6 years ago
- Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10…☆867Updated 4 years ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆785Updated 9 months ago
- Implementing Stand-Alone Self-Attention in Vision Models using Pytorch☆454Updated 4 years ago
- An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.☆583Updated 3 years ago
- Implementing Attention Augmented Convolutional Networks using Pytorch☆641Updated 2 years ago
- PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models☆291Updated 4 years ago
- Implementations of ideas from recent papers☆391Updated 3 years ago
- a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results☆860Updated 3 years ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆407Updated 3 months ago