Gradient-Centralization-TensorFlow
DemonRangerOptimizer
Gradient-Centralization-TensorFlow | DemonRangerOptimizer | |
---|---|---|
5 | 1 | |
105 | 23 | |
- | - | |
0.0 | 0.0 | |
about 2 years ago | over 3 years ago | |
Python | Python | |
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.
Gradient-Centralization-TensorFlow
- How many epochs of constant loss (e.g. 0.6933) will cause you to try something else?
- A Python package to boost your ML training performance
- A Python package to sizably boost your ML performance
-
[P] I made gctf: a package to sizeably improve your performance (link in comments)
GitHub repo: https://github.com/Rishit-dagli/Gradient-Centralization-TensorFlow
- A Python package to sizably increase your ML Training performance
DemonRangerOptimizer
-
[R] AdasOptimizer Update: Cifar-100+MobileNetV2 Adas generalizes with Adas 15% better and 9x faster than Adam
The results are interesting, but in terms of novelty of the main theory - isn't it almost identical to Baydin et al.? https://arxiv.org/pdf/1703.04782.pdf It seems the difference may be in some implementation details, like using a running average for the past gradient. If it's useful, I implemented a bunch of optimizers with options to synergize different techniques (https://github.com/JRC1995/DemonRangerOptimizer) including hypergradient updates for stuffs (and taking into account decorrelated weight decay and per-parameter lrs for hypergradient lr) when I was bored before practically abandoning it all together. I didn't really run any experiments with it though, but some people tried although they may not have got any particularly striking results.
What are some alternatives?
guesslang - Detect the programming language of a source code
pytorch-optimizer - torch-optimizer -- collection of optimizers for Pytorch
EasyMSE - A Python package for generating custom Magic The Gathering cards
ML-Optimizers-JAX - Toy implementations of some popular ML optimizers using Python/JAX
Im2txt - Image captioning ready-to-go inference: show and tell model compatible with Tensorflow r1.9
AdasOptimizer - ADAS is short for Adaptive Step Size, it's an optimizer that unlike other optimizers that just normalize the derivative, it fine-tunes the step size, truly making step size scheduling obsolete, achieving state-of-the-art training performance
neural-network-scratch - build a neural network to show as a demonstration on inner workings of a neural network
imagenette - A smaller subset of 10 easily classified classes from Imagenet, and a little more French
yolo-tf2 - yolo(all versions) implementation in keras and tensorflow 2.x
RAdam - On the Variance of the Adaptive Learning Rate and Beyond
Machine-Learning-Collection - A resource for learning about Machine learning & Deep Learning
You-Python - A python library for you.com and all of its apps.