PistonY / torch-toolbox
🛠 Toolbox to extend PyTorch functionalities
☆419Updated 9 months ago
Alternatives and similar repositories for torch-toolbox:
Users that are interested in torch-toolbox are comparing it to the libraries listed below
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆592Updated 4 years ago
- Official implementation of 'FMix: Enhancing Mixed Sample Data Augmentation'☆333Updated 3 years ago
- Unofficial PyTorch Reimplementation of RandAugment.☆631Updated last year
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.☆696Updated 3 years ago
- Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)☆472Updated 2 months ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆790Updated last year
- Compute CNN receptive field size in pytorch in one line☆357Updated 9 months ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆309Updated 5 years ago
- PyTorch implementation of AutoAugment.☆158Updated 4 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆986Updated 4 months ago
- Official Pytorch implementation of CutMix regularizer☆1,226Updated 4 years ago
- Standardizing weights to accelerate micro-batch training☆547Updated 2 years ago
- Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)☆415Updated 4 years ago
- Image Test Time Augmentation with PyTorch!☆992Updated last year
- PyTorch DataLoaders implemented with DALI for accelerating image preprocessing☆881Updated 4 years ago
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty☆982Updated 6 months ago
- mixup: Beyond Empirical Risk Minimization☆1,172Updated 3 years ago
- A New Optimization Technique for Deep Neural Networks☆535Updated 3 years ago
- a Ready-to-use PyTorch Extension of Unofficial CutMix Implementations with more improved performance.