All Projects → ContinualAI → Avalanche

ContinualAI / Avalanche

Licence: mit
Avalanche: a End-to-End Library for Continual Learning.

Programming Languages

139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Avalanche

Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.
Stars: ✭ 295 (+95.36%)
Mutual labels:  artificial-intelligence, framework, neural-networks
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: ✭ 38 (-74.83%)
Mutual labels:  artificial-intelligence, training, library
☁️ 🚀 📊 📈 Evaluating state of the art in AI
Stars: ✭ 1,087 (+619.87%)
Mutual labels:  artificial-intelligence, evaluation, reproducible-research
Telegram MTProto API Client Library and Framework in Pure Python for Users and Bots
Stars: ✭ 2,252 (+1391.39%)
Mutual labels:  framework, library
Declarative framework for interactive CLI applications
Stars: ✭ 126 (-16.56%)
Mutual labels:  framework, library
Unity Raymarching Framework
A framework to easy implement raymarching in unity. Include lots of hash,noise,fbm,SDF,rotate functions
Stars: ✭ 129 (-14.57%)
Mutual labels:  framework, library
Reproducible Image Denoising State Of The Art
Collection of popular and reproducible image denoising works.
Stars: ✭ 1,776 (+1076.16%)
Mutual labels:  reproducible-research, benchmarking
Microbenchmarking for Modern C++
Stars: ✭ 140 (-7.28%)
Mutual labels:  library, benchmarking
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+1070.2%)
Mutual labels:  artificial-intelligence, neural-networks
My journey to learn and grow in the domain of Machine Learning and Artificial Intelligence by performing the #100DaysofMLCode Challenge.
Stars: ✭ 146 (-3.31%)
Mutual labels:  artificial-intelligence, neural-networks
Hands On Machine Learning With Scikit Learn Keras And Tensorflow
Notes & exercise solutions of Part I from the book: "Hands-On ML with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems" by Aurelien Geron
Stars: ✭ 151 (+0%)
Mutual labels:  artificial-intelligence, neural-networks
Machine Learning Flappy Bird
Machine Learning for Flappy Bird using Neural Network and Genetic Algorithm
Stars: ✭ 1,683 (+1014.57%)
Mutual labels:  artificial-intelligence, neural-networks
Round Anything
A set of OpenSCAD utilities for adding radii and fillets, that embodies a robust approach to developing OpenSCAD parts.
Stars: ✭ 122 (-19.21%)
Mutual labels:  framework, library
A tool for automatic phoneme transcription
Stars: ✭ 130 (-13.91%)
Mutual labels:  artificial-intelligence, neural-networks
Stars: ✭ 121 (-19.87%)
Mutual labels:  framework, training
INGInious is a secure and automated exercises assessment platform using your own tests, also providing a pluggable interface with your existing LMS.
Stars: ✭ 138 (-8.61%)
Mutual labels:  training, evaluation
Web Components to turn your web app into a fake operating system
Stars: ✭ 151 (+0%)
Mutual labels:  framework, library
100 Lines Of Code Challenge Js
Write Everything in JavaScript under 100 Lines!!!😈
Stars: ✭ 157 (+3.97%)
Mutual labels:  framework, library
Hyperion Ios
In-app design review tool to inspect measurements, attributes, and animations.
Stars: ✭ 1,964 (+1200.66%)
Mutual labels:  framework, library
A modern, light CSS UI framework by Shakr
Stars: ✭ 113 (-25.17%)
Mutual labels:  framework, library

Avalanche: an End-to-End Library for Continual Learning

Avalanche Website | Getting Started | Examples | Tutorial | API Doc

unit test syntax checking pep8 checking docstring coverage test coverage

Avalanche is an end-to-end Continual Learning library based on Pytorch, born within ContinualAI with the unique goal of providing a shared and collaborative open-source (MIT licensed) codebase for fast prototyping, training and reproducible evaluation of continual learning algorithms. Avalanche can help Continual Learning researchers in several ways:

  • Write less code, prototype faster & reduce errors
  • Improve reproducibility
  • Improve modularity and reusability
  • Increase code efficiency, scalability & portability
  • Augment impact and usability of your research products

The library is organized in four main modules:

  • Benchmarks: This module maintains a uniform API for data handling: mostly generating a stream of data from one or more datasets. It contains all the major CL benchmarks (similar to what has been done for torchvision).
  • Training: This module provides all the necessary utilities concerning model training. This includes simple and efficient ways of implement new continual learning strategies as well as a set pre-implemented CL baselines and state-of-the-art algorithms you will be able to use for comparison!
  • Evaluation: This modules provides all the utilities and metrics that can help evaluate a CL algorithm with respect to all the factors we believe to be important for a continually learning system. It also includes advanced logging and plotting features, including native Tensorboard support.
  • Extras: In the extras module you'll be able to find several useful utilities and building blocks that will help you create your continual learning experiments with ease. This includes configuration files for quick reproducibility and model building functions for example.
  • Models: In this module you'll be able to find several model architectures and pre-trained models that can be used for your continual learning experiment (similar to what has been done in torchvision.models).
  • Logging: It includes advanced logging and plotting features, including native stdout, file and TensorBoard support (How cool it is to have a complete, interactive dashboard, tracking your experiment metrics in real-time with a single line of code?)

Avalanche the first experiment of a End-to-end Library for reproducible continual learning research & development where you can find benchmarks, algorithms, evaluation metrics and much more, in the same place.

Let's make it together :people_holding_hands: a wonderful ride! 🎈

Check out below how you can start using Avalanche! 👇

Quick Example

import torch
from torch.nn import CrossEntropyLoss
from torch.optim import SGD

from avalanche.benchmarks.classic import PermutedMNIST
from avalanche.models import SimpleMLP
from import Naive

# Config
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# model
model = SimpleMLP(num_classes=10)

# CL Benchmark Creation
perm_mnist = PermutedMNIST(n_experiences=3)
train_stream = perm_mnist.train_stream
test_stream = perm_mnist.test_stream

# Prepare for training & testing
optimizer = SGD(model.parameters(), lr=0.001, momentum=0.9)
criterion = CrossEntropyLoss()

# Continual learning strategy
cl_strategy = Naive(
    model, optimizer, criterion, train_mb_size=32, train_epochs=2,
    eval_mb_size=32, device=device)

# train and test loop
results = []
for train_task in train_stream:
    cl_strategy.train(train_task, num_workers=4)

Current Release

Avalanche is a framework in constant development. Thanks to the support of the ContinualAI community and its active members we are quickly extending its features and improve its usability based on the demands of our research community!

A the moment, Avalanche is in Alpha v0.0.1, but we already support a number of Benchmarks, Strategies and Metrics, that makes it, we believe, the best tool out there for your continual learning research! 💪

Please note that, at the moment, we do not support stable releases and packaged versions of the library. We do this intentionally as in this early phase we would like to stimulate contributions only from experienced CL researchers and coders.

Getting Started

We know that learning a new tool may be tough at first. This is why we made Avalanche as easy as possible to learn with a set of resources that will help you along the way. For example, you may start with our 5-minutes guide that will let you acquire the basics about Avalanche and how you can use it in your research project:

We have also prepared for you a large set of examples & snippets you can plug-in directly into your code and play with:

Having completed these two sections, you will already feel with superpowers ⚡, this is why we have also created an in-depth tutorial that will cover all the aspect of Avalanche in details and make you a true Continual Learner! 👩‍🎓

Cite Avalanche

If you used Avalanche in your research project, please remember to cite our white paper. This will help us make Avalanche better known in the machine learning community, ultimately making a better tool for everyone:

   title = {Avalanche: an End-to-End Library for Continual Learning},
   author = {...},
   journal = {Arxiv preprint arXiv:xxxx.xxxx},
   year = {2021}

Maintained by ContinualAI Lab

Avalanche is the flagship open-source collaborative project of ContinualAI: a non profit research organization and the largest open community on Continual Learning for AI.

Do you have a question, do you want to report an issue or simply ask for a new feature? Check out the Questions & Issues center. Do you want to improve Avalanche yourself? Follow these simple rules on How to Contribute.

The Avalanche project is maintained by the collaborative research team ContinualAI Lab and used extensively by the Units of the ContinualAI Research (CLAIR) consortium, a research network of the major continual learning stakeholders around the world.

We are always looking for new awesome members willing to join the ContinualAI Lab, so check out our official website if you want to learn more about us and our activities, or contact us.

Learn more about the Avalanche team and all the people who made it great!

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].