Adan
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models (by sail-sg)
pytorch_resnet_cifar10
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper. (by akamaster)
| Adan | pytorch_resnet_cifar10 | |
|---|---|---|
| 1 | 1 | |
| 727 | 1,133 | |
| 1.2% | - | |
| 4.6 | 0.0 | |
| about 1 month ago | about 1 year ago | |
| Python | Python | |
| Apache License 2.0 | BSD 2-clause "Simplified" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
Adan
Posts with mentions or reviews of Adan.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-03-24.
-
Find Optimal Learning Rates for Stable Diffusion Fine-tunes (Link in Comments)
Adan https://github.com/sail-sg/Adan
pytorch_resnet_cifar10
Posts with mentions or reviews of pytorch_resnet_cifar10.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Trained a ResNet110 in Pytorch for multioutput classification, but the predicted values are out of range, what can be the reason?
I made some changes to this repo codes and trained a ResNet32 for 1 epoch to test if the script is working, then trained a ResNet110 for 200 epochs. the range of values for output A is [0,1] and output B is [0, 4] in the training dataset. The trained ResNet32 model predictions were within the proper range but the ResNet110 output range went negative or something like 15.324 (way beyond 4).
What are some alternatives?
When comparing Adan and pytorch_resnet_cifar10 you can also consider the following projects:
Sophia - Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
facenet-pytorch - Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
AdamP - AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
DeepFake-Detection - Towards deepfake detection that actually works
Adan-pytorch - Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch
dadaptation - D-Adaptation for SGD, Adam and AdaGrad
LaTeX-OCR - pix2tex: Using a ViT to convert images of equations into LaTeX code.