Yonghongwei / Gradient-CentralizationLinks
A New Optimization Technique for Deep Neural Networks
☆540Updated 4 years ago
Alternatives and similar repositories for Gradient-Centralization
Users that are interested in Gradient-Centralization are comparing it to the libraries listed below
Sorting:
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.☆701Updated 4 years ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆338Updated 6 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆421Updated last year
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆594Updated 5 years ago
- Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)☆478Updated last year
- Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'☆339Updated 4 years ago
- Standardizing weights to accelerate micro-batch training☆550Updated 3 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆315Updated 6 years ago
- PyTorch implementation of AutoAugment.☆161Updated 5 years ago
- Stochastic Weight Averaging in PyTorch☆976Updated 4 years ago
- Code for Noisy Student Training. https://arxiv.org/abs/1911.04252☆763Updated 4 years ago
- Code for paper☆560Updated 4 years ago
- This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423☆1,044Updated 4 years ago
- torchsummaryX: Improved visualization tool of torchsummary☆302Updated 3 years ago
- Weakly Supervised Learning On Images☆603Updated 4 years ago
- Pytorch implementation of newly added convolution☆585Updated 6 years ago
- Pytorch implementation of network design paradigm described in the paper "Designing Network Design Spaces"☆184Updated last year
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,532Updated 5 years ago
- Efficient Learning of Augmentation Policy Schedules☆508Updated 6 years ago
- PyTorch DataLoaders implemented with DALI for accelerating image preprocessing☆884Updated 5 years ago
- Implementing Attention Augmented Convolutional Networks using Pytorch☆657Updated 4 years ago
- Compute CNN receptive field size in pytorch in one line☆367Updated last year
- Implementation of the mixup training method☆472Updated 7 years ago
- PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models☆293Updated 5 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆989Updated 8 months ago
- Implementing Stand-Alone Self-Attention in Vision Models using Pytorch☆455Updated 5 years ago
- Example code showing how to use Nvidia DALI in pytorch, with fallback to torchvision. Contains a few differences to the official Nvidia …☆197Updated 6 years ago
- ☆405Updated 3 years ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆805Updated last year
- Deep Learning Experiment Management☆642Updated last month