9 个仓库
Tools for automated search, tuning, and pruning of neural network configurations to improve efficiency.
Distinct from Neural Network Optimizers: Focuses on structural hyperparameter tuning and pruning rather than gradient-based weight updates
Explore 9 awesome GitHub repositories matching artificial intelligence & ml · Hyperparameter Optimizers. Refine with filters or upvote what's useful.
Skorch 是一个深度学习工作流管理器和基于张量的模型接口。它为在标准机器学习工作流中训练和预测神经网络提供了统一的 API,充当用于寻找最佳网络配置的超参数优化器。 该库专门用于将 PyTorch 神经网络包装在 scikit-learn 兼容接口中。这允许在传统的机器学习流水线和网格搜索工具中使用基于张量的模型,包括将参数网格映射到模型配置。 该框架通过提前停止、检查点保存和学习率调度器涵盖了训练生命周期管理。它还包括通过层冻结、张量与 NumPy 数组之间的自动转换以及实时训练进度监控进行模型参数控制的能力。
Finds optimal network configurations using standard grid search and scoring functions.
Skorch 是一个将 PyTorch 神经网络包装在 scikit-learn 兼容接口中的库,允许在标准机器学习流水线和超参数优化工具中使用深度学习模型。它充当数据适配器、训练管理器和优化工具,弥合了深度学习模块与传统机器学习工作流之间的差距。 该项目通过提供用于自动化 PyTorch 训练生命周期的工具包而脱颖而出,包括集成的检查点保存、提前停止和学习率调度。它还通过用于冻结特定模型层和针对特定任务微调预训练权重的实用程序,实现了迁移学习。 能力面扩展到数据转换,包括将表格数据和数值数组转换为张量格式以及注册文本分词器。它还提供了用于硬件加速选择、即时模块编译以及用于不确定性量化的概率数据建模的工具。 该系统包括用于将超参数映射到命令行参数的实用程序,以确保实验的可重复性。
Automates the search for optimal neural network hyperparameters using grid search and cross-validation interfaces.
PufferLib is a reinforcement learning framework built around high-speed environment simulation and automatic hyperparameter optimization. It is designed to accelerate the entire RL training pipeline by running simulations at near-native speed and enabling the training of tiny models to super-human performance within seconds. The framework achieves its speed through a single-process training loop that eliminates inter-process communication overhead, vectorized batched simulation for parallel environment execution, and compiled C extensions that offload performance-critical computations. It als
Automatically searches for optimal training hyperparameters through in-process concurrent trials that share memory.
Cube Studio 是一个云原生 MLOps 平台和基于 Kubernetes 的 AI 编排器,专为机器学习全生命周期设计。它提供了一个用于大规模模型微调的分布式训练框架、用于硬件虚拟化的 GPU 资源管理器,以及一个使用可视化有向无环图(DAG)来管理端到端工作流的 ML 流水线编排器。 该平台的特色在于其专业的 LLM 推理服务器,支持检索增强生成(RAG)和私有知识库构建。它拥有专门用于大语言模型监督微调和强化学习的系统,并辅以可视化超参数搜索工具。 该系统涵盖了广泛的运营能力,包括多模态数据标注、分布式数据流水线和多集群工作负载调度。它还提供基于浏览器的交互式开发环境、容器镜像管理以及用于版本控制和部署可扩展推理 API(带流量拆分)的模型注册中心。 其基础设施包括集成的集群健康监控和支持单点登录(SSO)的基于角色的访问控制(RBAC)。
Automates the search for optimal model configurations to improve overall accuracy and performance.
PyTorch Forecasting is a deep learning framework designed for building and training neural network architectures specifically for time series forecasting. It serves as a comprehensive toolkit for implementing autoregressive models, multi-horizon forecasting, and probabilistic prediction intervals using PyTorch tensors. The library distinguishes itself through a probabilistic forecasting toolkit that generates prediction intervals and quantile forecasts using both parametric and non-parametric distributions. It further provides a neural network model optimizer for automated hyperparameter tuni
Offers an automated hyperparameter tuning and pruning framework to optimize deep learning architectures.
FLAML 是一个自动化机器学习框架、超参数优化工具和大型语言模型代理编排器。它提供了一个用于跨各种学习器和数据集进行模型选择和调优的系统,同时也提供了一个用于优化大型语言模型推理参数和微调设置的工具包。 该项目具有元学习调优系统,可分析历史任务数据以生成依赖于数据的默认配置,从而加速模型收敛。它进一步通过对话式工作流和事件驱动编排,支持协作式多代理系统的设计。 能力涵盖了针对机器学习模型和任意 Python 函数的资源高效超参数搜索,支持分层搜索空间和字典序目标优化。该框架还包括用于自动化模型选择、堆叠集成构建、零样本配置以及强制执行公平性约束的实用工具。 该系统支持分布式调优扩展和跨计算集群的并发试验执行,以缩短总搜索时长。
Implements search strategies that minimize total compute time and trial counts to find optimal configurations.
fast-reid 是一个基于 PyTorch 的计算机视觉框架,旨在构建、训练和部署用于基于身份的视觉任务的深度学习模型。它提供了一个用于行人重识别和车辆重识别的专用工具箱,能够跨非重叠的摄像机视图匹配个人和车辆。 该项目包括用于识别特定身体特征和属性的行人属性识别工具。它具有一个模块化模型库,允许交换和基准测试不同的重识别架构。 该框架涵盖了大规模开发基础设施,包括跨多个 GPU 的分布式训练、混合精度训练,以及将表示从复杂网络转移到较小学生模型的知识蒸馏。它还提供了一个超参数优化循环、多数据集评估引擎,以及用于将模型导出为行业标准格式以进行生产部署的管道。
Provides automated tools for tuning and searching optimal hyperparameter configurations.
PocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format optimization. It provides a system for reducing the size and complexity of neural networks to improve inference efficiency, featuring a dedicated engine for knowledge distillation and a mobile model optimizer. The framework differentiates itself through an automated hyperparameter tuning system that uses reinforcement learning and statistical models to determine optimal compression ratios and layer-wise bit allocation. It also includes a distributed training system that utilizes mu
Automatically searches for optimal compression ratios and bit-widths using reinforcement learning and statistical models.
This project is a collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3 and Gymnasium. It provides a framework for training agents to solve specific tasks, managing experiment reproducibility, and deploying pretrained models. The system includes a specialized benchmarking suite and optimization tools for tuning agent settings. It utilizes automated search spaces and distributed trials to maximize performance, while employing bootstrap sampling to generate statistically robust performance metrics and confidence intervals. Broad capabilities cov
Runs hyperparameter optimization trials across multiple distributed jobs using a shared database to accelerate search.