alphadl / Lookahead.pytorch
Licence: mit
lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch
Stars: ✭ 279
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Lookahead.pytorch
portfolio-optimizer
A library for portfolio optimization algorithms with python interface.
Stars: ✭ 19 (-93.19%)
Mutual labels: optimizer
sam.pytorch
A PyTorch implementation of Sharpness-Aware Minimization for Efficiently Improving Generalization
Stars: ✭ 96 (-65.59%)
Mutual labels: optimizer
Post-Tweaks
A post-installation batch script for Windows
Stars: ✭ 136 (-51.25%)
Mutual labels: optimizer
lookahead tensorflow
Lookahead optimizer ("Lookahead Optimizer: k steps forward, 1 step back") for tensorflow
Stars: ✭ 25 (-91.04%)
Mutual labels: optimizer
falcon
A WordPress cleanup and performance optimization plugin.
Stars: ✭ 17 (-93.91%)
Mutual labels: optimizer
Cleaner
The only storage saving app that actually works! :D
Stars: ✭ 27 (-90.32%)
Mutual labels: optimizer
simplu3D
A library to generate buildings from local urban regulations.
Stars: ✭ 18 (-93.55%)
Mutual labels: optimizer
postcss-clean
PostCss plugin to minify your CSS with clean-css
Stars: ✭ 41 (-85.3%)
Mutual labels: optimizer
rethinking-bnn-optimization
Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"
Stars: ✭ 62 (-77.78%)
Mutual labels: optimizer
AdaBound-tensorflow
An optimizer that trains as fast as Adam and as good as SGD in Tensorflow
Stars: ✭ 44 (-84.23%)
Mutual labels: optimizer
goga
Go evolutionary algorithm is a computer library for developing evolutionary and genetic algorithms to solve optimisation problems with (or not) many constraints and many objectives. Also, a goal is to handle mixed-type representations (reals and integers).
Stars: ✭ 39 (-86.02%)
Mutual labels: optimizer
adamwr
Implements https://arxiv.org/abs/1711.05101 AdamW optimizer, cosine learning rate scheduler and "Cyclical Learning Rates for Training Neural Networks" https://arxiv.org/abs/1506.01186 for PyTorch framework
Stars: ✭ 130 (-53.41%)
Mutual labels: optimizer
EAGO.jl
A development environment for robust and global optimization
Stars: ✭ 106 (-62.01%)
Mutual labels: optimizer
Windows11-Optimization
Community repository, to improve security and performance of Windows 10 and windows 11 with tweaks, commands, scripts, registry keys, configuration, tutorials and more
Stars: ✭ 17 (-93.91%)
Mutual labels: optimizer
pigosat
Go (golang) bindings for Picosat, the satisfiability solver
Stars: ✭ 15 (-94.62%)
Mutual labels: optimizer
lookahead optimizer for pytorch
PyTorch implement of Lookahead Optimizer: k steps forward, 1 step back
Usage:
base_opt = torch.optim.Adam(model.parameters(), lr=1e-3, betas=(0.9, 0.999)) # Any optimizer
lookahead = Lookahead(base_opt, k=5, alpha=0.5) # Initialize Lookahead
lookahead.zero_grad()
loss_function(model(input), target).backward() # Self-defined loss function
lookahead.step()
lookahead优化器的PyTorch实现
论文《Lookahead Optimizer: k steps forward, 1 step back》的PyTorch实现。
用法：
base_opt = torch.optim.Adam(model.parameters(), lr=1e-3, betas=(0.9, 0.999)) # 用你想用的优化器
lookahead = Lookahead(base_opt, k=5, alpha=0.5) # 初始化Lookahead
lookahead.zero_grad()
loss_function(model(input), target).backward() # 自定义的损失函数
lookahead.step()
中文介绍：https://mp.weixin.qq.com/s/3J-28xd0pyToSy8zzKs1RA
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].