pytorch-optimizer
simple-sam
| pytorch-optimizer | simple-sam | |
|---|---|---|
| 3 | 1 | |
| 2,946 | 40 | |
| - | - | |
| 3.1 | 0.0 | |
| about 1 month ago | about 2 years ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
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
simple-sam
-
[R] When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations
Which implementation(s) have you been using? I've been eyeing this one for use in a Keras project of mine, so I'm curious what others are using.
What are some alternatives?
sam - SAM: Sharpness-Aware Minimization (PyTorch)
DemonRangerOptimizer - Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
imagenette - A smaller subset of 10 easily classified classes from Imagenet, and a little more French
RAdam - On the Variance of the Adaptive Learning Rate and Beyond
PythonPID_Tuner - Python PID Tuner - Based on a FOPDT model obtained using a Open Loop Process Reaction Curve
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