alphadl / lookahead.pytorchLinks
lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch
☆337Updated 5 years ago
Alternatives and similar repositories for lookahead.pytorch
Users that are interested in lookahead.pytorch are comparing it to the libraries listed below
Sorting:
- pytorch implement of Lookahead Optimizer☆191Updated 3 years ago
- A New Optimization Technique for Deep Neural Networks☆537Updated 3 years ago
- Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"☆409Updated 11 months ago
- Implementation and experiments for AdamW on Pytorch☆94Updated 5 years ago
- Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neu…☆149Updated 6 years ago
- A PyTorch implementation of " EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."☆313Updated 5 years ago
- Stochastic Weight Averaging in PyTorch☆973Updated 3 years ago
- 🛠 Toolbox to extend PyTorch functionalities☆421Updated last year
- Over9000 optimizer☆426Updated 2 years ago
- torchsummaryX: Improved visualization tool of torchsummary☆303Updated 3 years ago
- Debug PyTorch code using PySnooper☆798Updated 4 years ago
- Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase☆1,201Updated last year
- A large scale study of Knowledge Distillation.☆220Updated 5 years ago
- Implementations of ideas from recent papers☆392Updated 4 years ago
- Deep Learning Experiment Management☆639Updated 2 years ago
- Implementation of the mixup training method☆466Updated 7 years ago
- Mish Deep Learning Activation Function for PyTorch / FastAI☆161Updated 5 years ago
- Experimental ground for optimizing memory of pytorch models☆366Updated 7 years ago
- Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.☆596Updated 4 years ago
- Standardizing weights to accelerate micro-batch training☆549Updated 3 years ago
- Accelerate training by storing parameters in one contiguous chunk of memory.☆291Updated 4 years ago
- ☆261Updated 5 years ago
- Useful PyTorch functions and modules that are not implemented in PyTorch by default☆188Updated last year
- Implementation of https://arxiv.org/abs/1904.00962☆376Updated 4 years ago
- Sublinear memory optimization for deep learning. https://arxiv.org/abs/1604.06174☆598Updated 5 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆989Updated 9 months ago
- PyTorch Implementation of Focal Loss and Lovasz-Softmax Loss☆333Updated 3 years ago
- A simpler version of the self-attention layer from SAGAN, and some image classification results.☆212Updated 5 years ago
- Library for faster pinned CPU <-> GPU transfer in Pytorch☆685Updated 5 years ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆800Updated last year