Awesome-Incremental-Learning
avalanche
| Awesome-Incremental-Learning | avalanche | |
|---|---|---|
| 2 | 1 | |
| 3,482 | 1,674 | |
| - | 1.8% | |
| 7.6 | 9.4 | |
| 10 days ago | 9 days ago | |
| Python | ||
| - | 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.
Awesome-Incremental-Learning
-
[R] Single-task Continual/Incremental/Online/Life-Long learning.
For more reading, you (usually) can find a curated list of paper in those field, like xialeiliu/Awesome-Incremental-Learning
-
Best way to monthly add new classes to my trained model?
look for papers on class incremental learning, this might be a good start - https://github.com/xialeiliu/Awesome-Incremental-Learning
avalanche
-
[R] Single-task Continual/Incremental/Online/Life-Long learning.
Lastly, there are several github repo, but the most popular one is ContinualAI/avalanche, which already implement some of above algorithm, for the purpose of reproducibility i.e. can be applied to your task (probably)
What are some alternatives?
evaluate - 🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
torch-fidelity - High-fidelity performance metrics for generative models in PyTorch
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
pytorch-accelerated - A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases, and capable of utilizing different hardware options with no code changes required. Docs: https://pytorch-accelerated.readthedocs.io/en/latest/
rexmex - A general purpose recommender metrics library for fair evaluation.
trajectopy - Trajectopy - Trajectory Evaluation in Python
continuum - A clean and simple data loading library for Continual Learning
trajectopy-core - Trajectopy - Trajectory Evaluation in Python
Activeloop Hub - Data Lake for Deep Learning. Build, manage, query, version, & visualize datasets. Stream data real-time to PyTorch/TensorFlow. https://activeloop.ai [Moved to: https://github.com/activeloopai/deeplake]
simpleeval - Simple Safe Sandboxed Extensible Expression Evaluator for Python