4 个仓库
Awesome GitHub RepositoriesMeta Learning Libraries
Software libraries providing primitives and tools for building meta-learning models.
Explore 4 awesome GitHub repositories matching part of an awesome list · Meta Learning Libraries. Refine with filters or upvote what's useful.
Awesome Meta Learning Libraries GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- google-deepmind/learning-to-learn
google-deepmind/learning-to-learn
4,068在 GitHub 上查看本项目是一个 TensorFlow 元学习框架和研究工具包，旨在实现和训练学习到的优化器。它提供了一套用于开发学习如何优化其他模型的神经网络的工具，取代了传统的基于梯度的优化算法。 该框架包括一个问题集成管理器，允许将多个不同的优化任务组合成单个加权损失函数进行同步训练。它使用工厂模式进行网络实例化，并支持定义自定义目标函数和损失图作为学习算法的目标。 该工具包涵盖了广泛的功能，包括基于梯度的元优化、模型基准测试以及具有可配置展开长度的训练循环执行。它还提供了用于梯度预处理、序列化状态持久化以及报告实验统计数据（如平均最终误差和 epoch 持续时间）的工具。
Provides a toolkit for developing and training neural networks that learn how to optimize other models.
Pythonartificial-intelligencedeep-learningmachine-learning - learnables/learn2learn
learnables/learn2learn
2,886在 GitHub 上查看A PyTorch Library for Meta-learning Research
Unified library for meta-learning research and experimentation.
Python - tristandeleu/pytorch-meta
tristandeleu/pytorch-meta
2,058在 GitHub 上查看A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Collection of meta-learning algorithms and datasets for PyTorch.
Python - facebookresearch/higher
facebookresearch/higher
1,627在 GitHub 上查看higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
PyTorch library for higher-order gradient optimization in meta-learning.
Python
