All Projects → mgrankin → Over9000

mgrankin / Over9000

Licence: apache-2.0
Over9000 optimizer

Projects that are alternatives of or similar to Over9000

Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (-2.13%)
Mutual labels:  jupyter-notebook
Covid19pt Data
😷️🇵🇹 Dados relativos à pandemia COVID-19 em Portugal
Stars: ✭ 362 (-3.47%)
Mutual labels:  jupyter-notebook
Data Science
Collection of useful data science topics along with code and articles
Stars: ✭ 315 (-16%)
Mutual labels:  jupyter-notebook
Integrated Gradients
Attributing predictions made by the Inception network using the Integrated Gradients method
Stars: ✭ 365 (-2.67%)
Mutual labels:  jupyter-notebook
Fbrs interactive segmentation
[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331
Stars: ✭ 366 (-2.4%)
Mutual labels:  jupyter-notebook
Causal Inference Tutorial
Repository with code and slides for a tutorial on causal inference.
Stars: ✭ 368 (-1.87%)
Mutual labels:  jupyter-notebook
Intro programming
A set of IPython notebooks and learning resources for an Introduction to Programming class, focusing on Python.
Stars: ✭ 366 (-2.4%)
Mutual labels:  jupyter-notebook
Deep Learning
Repo for the Deep Learning Nanodegree Foundations program.
Stars: ✭ 3,782 (+908.53%)
Mutual labels:  jupyter-notebook
Handson Unsupervised Learning
Code for Hands-on Unsupervised Learning Using Python (O'Reilly Media)
Stars: ✭ 369 (-1.6%)
Mutual labels:  jupyter-notebook
Matlab kernel
Jupyter Kernel for Matlab
Stars: ✭ 373 (-0.53%)
Mutual labels:  jupyter-notebook
Audionotebooks
Collection of notebooks and scripts related to audio processing and machine learning.
Stars: ✭ 366 (-2.4%)
Mutual labels:  jupyter-notebook
D2l Pytorch
This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.
Stars: ✭ 3,810 (+916%)
Mutual labels:  jupyter-notebook
Python Course
Tutorial and introduction into programming with Python for the humanities and social sciences
Stars: ✭ 370 (-1.33%)
Mutual labels:  jupyter-notebook
Carnd Vehicle Detection
Vehicle detection using YOLO in Keras runs at 21FPS
Stars: ✭ 367 (-2.13%)
Mutual labels:  jupyter-notebook
Interesting Python
有趣的Python爬虫和Python数据分析小项目(Some interesting Python crawlers and data analysis projects)
Stars: ✭ 3,927 (+947.2%)
Mutual labels:  jupyter-notebook
Nerf pl
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
Stars: ✭ 362 (-3.47%)
Mutual labels:  jupyter-notebook
Tf 2.0 Hacks
Contains my explorations of TensorFlow 2.x
Stars: ✭ 369 (-1.6%)
Mutual labels:  jupyter-notebook
Data Analysis
Data Science Using Python
Stars: ✭ 4,080 (+988%)
Mutual labels:  jupyter-notebook
Learn Python3
Jupyter notebooks for teaching/learning Python 3
Stars: ✭ 4,418 (+1078.13%)
Mutual labels:  jupyter-notebook
Deep Learning Illustrated
Deep Learning Illustrated (2020)
Stars: ✭ 372 (-0.8%)
Mutual labels:  jupyter-notebook

Optimizers and tests

Every result is avg of 20 runs.

Dataset LR Schedule Imagenette size 128, 5 epoch Imagewoof size 128, 5 epoch
Adam - baseline OneCycle 0.8493 0.6125
RangerLars (RAdam + LARS + Lookahead) Flat and anneal 0.8732 0.6523
Ralamb (RAdam + LARS) Flat and anneal 0.8675 0.6367
Ranger (RAdam + Lookahead) Flat and anneal 0.8594 0.5946
Novograd Flat and anneal 0.8711 0.6126
Radam Flat and anneal 0.8444 0.537
Lookahead OneCycle 0.8578 0.6106
Lamb OneCycle 0.8400 0.5597
DiffGrad OneCycle 0.8527 0.5912
AdaMod OneCycle 0.8473 0.6132
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].