2 个仓库
A deep learning framework implemented entirely in header files with no external dependencies, supporting feedforward networks and CPU training.
Distinct from Deep Learning Framework Implementations: Distinct from Deep Learning Framework Implementations: focuses specifically on header-only implementations rather than general deep learning framework implementations.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Header-Only Implementations. Refine with filters or upvote what's useful.
tiny-dnn is a header-only C++14 deep learning framework for building, training, and running inference on neural networks. It constructs static computational graphs at compile time using template-based layer composition, with a gradient-based backpropagation engine and minibatch stochastic gradient descent for training, all without external dependencies beyond the C++14 standard library. The framework supports importing pre-trained models from the Caffe framework directly, parsing its binary serialization format without requiring external protocol buffer libraries. It provides CPU-optimized te
Provides a header-only C++14 deep learning framework with no external dependencies.
Chips 是一个模块化的、仅头文件的 C 语言库框架,专为构建周期精确的硬件模拟器和复制历史上的八位计算架构而设计。它提供了通过集成单个模拟微处理器和外围芯片来构建完整复古系统所需的基础组件。 该框架通过组件化架构脱颖而出,其中硬件模块实现为可以连接在一起形成复杂系统的独立头文件。它在底层建模硬件交互,利用引脚级信号模拟和内存映射总线通信来确保确定性行为。开发者可以将模拟器的整个内部状态捕获到内存缓冲区中,从而实现持久化快照和精确的状态恢复。 该项目包括一套全面的诊断和开发工具,例如即时模式调试可视化以及对系统寄存器和帧缓冲区的实时监控。它还提供命令行实用程序来自动化硬件组件定义和源代码的生成,促进自定义嵌入式环境的构建。
Implements hardware modules as standalone C headers that can be wired together to form complex system architectures.