Awesome GitHub RepositoriesTensor Computation Graphs

Llama is a computational framework and runtime environment designed for executing transformer-based neural networks locally. It functions as a generative AI inference engine, enabling the processing of input sequences through pre-trained model weights to produce text completions and structured data outputs directly on your own hardware. The system distinguishes itself through specialized memory and computation management techniques, including memory-mapped weight loading and quantization-aware inference, which allow for efficient execution on standard consumer hardware. It utilizes a stateles

Detectron2 is a PyTorch computer vision framework and visual recognition platform designed for training and deploying models for object detection, image segmentation, and visual recognition. It provides a research-oriented environment for training complex vision models with multi-GPU acceleration. The project includes a specialized object detection library for identifying and locating multiple objects via bounding boxes, as well as an image segmentation toolkit for creating pixel-level masks through instance, semantic, and panoptic segmentation. Additionally, it features a human pose estimati

This project is a structured educational resource and training platform designed for mastering deep learning development. It provides a comprehensive curriculum focused on building, evaluating, and refining predictive models through hands-on coding exercises and standard industry workflows. The curriculum emphasizes practical implementation, guiding users through the construction of neural network architectures and the application of transfer learning to adapt pretrained models for custom tasks. It includes methodologies for tracking and comparing model experiment results, allowing for the sy

This project is an open source deep learning textbook and educational resource. It provides a structured curriculum of theory and practical examples designed for mastering the training of regression, classification, and generative models using the TensorFlow framework. The repository functions as a machine learning code collection, utilizing interactive notebooks and source code to demonstrate neural network implementation and tensor operations. It covers the development of deep learning models and the study of reinforcement learning. The material employs a case-study driven pedagogy, combin

ConvNetJS is a JavaScript deep learning library and neural network training engine designed for client-side machine learning. It functions as a framework for building, training, and running convolutional neural networks directly within a web browser without the need for a backend server. The library specializes in image recognition and pattern analysis using convolutional and pooling layers. It enables the creation of models for classification and regression tasks, as well as the development of reinforcement learning agents that optimize behavior through trial and error in simulated environme

Sonnet is a modular machine learning framework and TensorFlow library used for building, training, and managing deep learning models. It functions as a system for composing neural networks from reusable modules and layers that encapsulate their own parameters and internal states. The project provides specialized tools for distributed model training, enabling the synchronization of gradients across multiple hardware devices. It also serves as a model state management system, allowing for the persistence of neural network weights and the export of portable models that separate the computation g

torchdiffeq 是一个 PyTorch ODE（常微分方程）求解器库，专为解决初值问题和构建神经 ODE 框架而设计。它提供了一个可微分的 ODE 积分器，允许深度学习模型通过随时间积分动力学函数来模拟连续深度。 该库具有用于内存高效反向传播的伴随法梯度计算器。通过在时间上反向求解增广伴随系统，它可以在不存储每个中间求解器状态的情况下计算参数梯度。 该项目涵盖了具有自适应和固定步长求解器的数值积分，并结合了误差控制和多项式状态插值。它还支持可微分事件管理，以便在特定标量函数触发时终止求解器，并沿事件时间传播梯度。 该框架常用于连续归一化流以及通过学习连续时间常微分方程进行概率分布转换等应用。

这是一个教育性 Jupyter Notebook 合集，提供了使用 TensorFlow 框架构建神经网络和进行张量运算的教程。它作为机器学习教育仓库和深度学习学生的实现指南。 该套件专注于特定的高级架构，包括用于图像分类的卷积神经网络、用于训练稳定性的残差网络（带跳跃连接），以及用于生成建模和数据合成的变分自编码器。它还包含构建去噪和深度自编码器以进行特征提取和降维的指南。 该仓库涵盖了更广泛的预测建模领域，实现了用于预测连续值和二元结果的线性、多项式和逻辑回归。 内容组织为交互式 Notebook，允许用户执行数学运算并修改机器学习实验。

Cactus 是一个端侧 AI 推理引擎，专为在移动和可穿戴硬件上执行大语言模型、视觉模型和语音转文字系统而设计。它提供了一个用于定义矩阵运算和激活函数序列的可编程张量计算图，以及一个利用本地文本文件为模型响应提供依据的本地检索增强生成（RAG）框架。 该项目具有一个多平台 SDK，包含用于将 AI 功能集成到移动应用程序中的语言绑定，以及一个将外部模型格式转换为优化本地执行的模型转换系统。它利用混合路由系统，根据硬件容量在端侧执行和云端提供商之间重定向工作负载。 该引擎涵盖了广泛的功能面，包括用于语音活动检测和转录的端侧音频处理、用于相似性搜索的向量嵌入生成，以及用于将模型输出解析为外部函数调用的工具集成。这些过程由针对移动硬件低延迟性能优化的原生内核提供支持。

Caffe is a high-performance deep learning framework and convolutional neural network library designed for training and deploying neural networks. It functions as a GPU-accelerated machine learning engine with a core implemented in C++ to enable high-throughput tensor operations. The project utilizes a declarative configuration system where model architectures and hyperparameters are defined in external text files, separating the network design from the execution code. It includes a model serialization system to export trained weights and topologies into binary files for efficient deployment a

oneDNN 是一个深度学习加速库，为神经网络训练和推理提供优化的构建块。它管理跨 CPU 和 GPU 硬件的张量计算，支持执行用于模型训练和神经网络推理优化的高性能原语。 该项目通过硬件特定的内核优化和使用即时编译来针对特定处理器指令集脱颖而出。它支持使用静态和动态量化来执行量化神经网络，以减少内存使用并提高吞吐量。 该库涵盖了广泛的功能，包括卷积、矩阵乘法和循环神经网络执行等深度学习原语。它实现了先进的性能优化，包括操作融合、计算图优化和内存格式管理。通过稳定的 C ABI 和 C++ 包装器提供集成，并支持 SYCL、OpenCL 和外部线性代数库。 该系统包括用于硬件性能分析、原语基准测试和详细执行日志记录的观测工具。

PyTorchZeroToAll 是一个教育资源和教程合集，专注于深度学习和 PyTorch 框架。它为实现神经网络架构提供了一条结构化的学习路径，范围从基础语言语法和原理到复杂的模型设计。 该项目作为一个实现指南，用于构建各种网络类型，包括线性、逻辑、卷积和循环网络。它专门涵盖了通过使用注意力机制和字符级网络进行序列建模的工作流。 该资源还涵盖机器学习数据准备，包括使用自定义数据集加载器、文本处理工具以及将原始源文件转换为张量以用于训练流水线。

This is a TensorFlow-based framework for implementing and training capsule networks designed for image classification. It utilizes a tensor graph neural network model to build architectures that preserve spatial relationships and pose parameters through vector-based neuron groupings. The project implements a dynamic routing mechanism to establish hierarchical relationships between input features and output capsules. To handle complex architectures, it includes a distributed deep learning toolset that enables training across multiple graphics processing units. The framework covers the full ma

Taco is a sparse tensor algebra compiler that translates high-level tensor index expressions into optimized machine code. It functions as a numerical code generator, producing specialized C kernels designed to execute complex multidimensional array operations efficiently on both CPU and GPU hardware. The project distinguishes itself by allowing users to define custom tensor storage layouts by composing dimension-level formats, such as dense or compressed structures, to match the specific sparsity patterns of their datasets. By analyzing the mathematical structure of tensor operations at compi

This project provides a clean implementation of the latent diffusion model architecture using the PyTorch framework. It functions as a generative machine learning pipeline designed to synthesize images from text prompts by loading pre-trained model weights into a modular neural network structure. The implementation focuses on the mechanics of image generation, utilizing a tensor-based computational graph to execute the complex linear algebra required for inference. It incorporates transformer-based text encoding to map natural language into vector embeddings, which are then integrated into th