pytorch-optimizer
RAdam
pytorch-optimizer | RAdam | |
---|---|---|
3 | 4 | |
2,946 | 2,520 | |
- | - | |
3.1 | 0.0 | |
about 1 month ago | almost 3 years ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch-optimizer
-
[D]: Implementation: Deconvolutional Paragraph Representation Learning
The specific implementation is from (here)[https://github.com/jettify/pytorch-optimizer] since pytorch doesn't have it directly.
- VQGAN+CLIP : "RAdam" from torch_optimizer could not be imported ?
- [R] AdasOptimizer Update: Cifar-100+MobileNetV2 Adas generalizes with Adas 15% better and 9x faster than Adam
RAdam
-
[D] Why does a sudden increase in accuracy at a specific epoch in these model
Code for https://arxiv.org/abs/1908.03265 found: https://github.com/LiyuanLucasLiu/RAdam
-
[D] How to pick a learning rate scheduler?
common practice is to include some type of annealing (cosine, linear, etc.), which makes intuitive sense. for adam/adamw, it's generally a good idea to include a warmup in the lr schedule, as the gradient distribution without the warmup can be distorted, leading to the optimizer being trapped in a bad local min. see this paper. there are also introduced in this paper and subsequent works (radam, ranger, and variants) that don't require a warmup stage to stabilize the gradients. i would say in general, if you're using adam/adamw, include a warmup and some annealing, either linear or cosine. if you're using radam/ranger/variants, you can skip the warmup. how many steps to use for warmup/annealing are probably problem specific, and require some hyperparam tuning to get optimimal results
- Why is my loss choppy?
What are some alternatives?
sam - SAM: Sharpness-Aware Minimization (PyTorch)
ML-Optimizers-JAX - Toy implementations of some popular ML optimizers using Python/JAX
DemonRangerOptimizer - Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay
AdaBound - An optimizer that trains as fast as Adam and as good as SGD.
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
pytorch_warmup - Learning Rate Warmup in PyTorch
imagenette - A smaller subset of 10 easily classified classes from Imagenet, and a little more French
simple-sam - Sharpness-Aware Minimization for Efficiently Improving Generalization
Best-Deep-Learning-Optimizers - Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable
PythonPID_Tuner - Python PID Tuner - Based on a FOPDT model obtained using a Open Loop Process Reaction Curve
deepnet - Educational deep learning library in plain Numpy.