Z-Ant开源程序是简化了微处理器上神经网络的部署和优化

📷 ImageToTensor Processing
📷 ImageToTensor 处理

🔧 Extensive ONNX Support
🔧 广泛的 ONNX 支持

Why Z-Ant? 为什么选择 Z-Ant？

Use Cases 使用案例

To establish Z-Ant as the premier tinyML inference engine, we are pursuing several key improvements:
为了将 Z-Ant 确立为首屈一指的 tinyML 推理引擎，我们正在寻求几项关键改进：

• Custom Memory Allocators: Zero-allocation inference with pre-allocated memory pools
  自定义内存分配器：使用预分配的内存池进行零分配推理
• In-Place Operations: Minimize memory copies through tensor operation fusion
  就地作：通过张量运算融合最大限度地减少内存副本
• SIMD Vectorization: ARM NEON, RISC-V Vector extensions, and x86 AVX optimizations
  SIMD 矢量化：ARM NEON、RISC-V 矢量扩展和 x86 AVX 优化
• Assembly Kernels: Hand-optimized assembly for critical operations (matrix multiplication, convolution)
  汇编内核：针对关键运算（矩阵乘法、卷积）的手动优化汇编
• Cache-Aware Algorithms: Memory access patterns optimized for L1/L2 cache efficiency
  高速缓存感知算法：针对 L1/L2 高速缓存效率优化的内存访问模式

• Dynamic Quantization: Runtime precision adjustment based on input characteristics
  动态量化：根据输入特性进行运行时精度调整
• Structured Pruning: Channel and block-level pruning for hardware-friendly sparsity
  结构化修剪：通道和块级修剪，实现硬件友好的稀疏性
• Knowledge Distillation: Automatic teacher-student model compression pipeline
  知识蒸馏：自动师生模型压缩管道
• Neural Architecture Search (NAS): Hardware-aware model architecture optimization
  神经架构搜索 （NAS）：硬件感知模型架构优化
• Binary/Ternary Networks: Extreme quantization for ultra-low power inference
  二进制/三元网络：用于超低功耗推理的极端量化

• DSP Instruction Utilization: Leverage ARM Cortex-M DSP instructions and RISC-V packed SIMD
  DSP 指令利用：利用 ARM Cortex-M DSP 指令和 RISC-V 封装的 SIMD
• DMA-Accelerated Operations: Offload data movement to DMA controllers
  DMA 加速作：将数据移动卸载到 DMA 控制器
• Flash Execution Strategies: XIP (Execute-in-Place) optimization for flash-resident models
  Flash 执行策略：针对 Flash 驻留模型的 XIP（就地执行）优化
• Low-Power Modes: Dynamic frequency scaling and sleep mode integration
  低功耗模式：动态频率调节和休眠模式集成
• Hardware Security Modules: Secure model storage and execution
  硬件安全模块：安全的模型存储和执行

• NPU Integration: Support for dedicated neural processing units (e.g., Arm Ethos, Intel Movidius)
  NPU 集成：支持专用神经处理单元（例如 Arm Ethos、Intel Movidius）
• FPGA Acceleration: Custom hardware generation for ultra-performance inference
  FPGA 加速：用于超高性能推理的定制硬件生成
• GPU Compute: OpenCL/CUDA kernels for edge GPU acceleration
  GPU 计算：用于边缘 GPU 加速的 OpenCL/CUDA 内核
• Neuromorphic Computing: Spike-based neural network execution
  Neuromorphic Computing：基于尖峰的神经网络执行

• Lottery Ticket Hypothesis: Sparse subnetwork discovery and training
  彩票假说：稀疏子网络发现和训练
• Progressive Quantization: Gradual precision reduction during training/deployment
  渐进式量化：训练/部署期间逐渐降低精度
• Magnitude-Based Pruning: Automatic weight importance analysis
  基于量级的修剪：自动权重重要性分析
• Channel Shuffling: Network reorganization for efficient inference
  通道改组：网络重组以实现高效推理
• Tensor Decomposition: Low-rank approximation for parameter reduction
  张量分解：用于参数缩减的低秩近似

• Early Exit Networks: Conditional computation based on input complexity
  Early Exit Networks：基于输入复杂度的条件计算
• Dynamic Model Selection: Runtime model switching based on resource availability
  动态模型选择：基于资源可用性的运行时模型切换
• Cascaded Inference: Multi-stage models with progressive complexity
  级联推理：具有渐进复杂性的多阶段模型
• Attention Mechanism Optimization: Efficient transformer and attention implementations
  注意力机制优化：高效的 transformer 和 attention 实现

• Hardware Performance Counters: Cycle-accurate performance measurement
  硬件性能计数器：周期精确的性能测量
• Energy Profiling: Power consumption analysis per operation
  能量分析：每个作的功耗分析
• Memory Footprint Analysis: Detailed RAM/Flash usage breakdown
  内存占用分析：详细的 RAM/Flash 使用情况明细
• Thermal Analysis: Temperature impact on inference performance
  热分析：温度对推理性能的影响
• Real-Time Visualization: Live performance monitoring dashboards
  实时可视化：实时性能监控仪表板

• AutoML Integration: Automated hyperparameter tuning for target hardware
  AutoML 集成：目标硬件的自动超参数调整
• Benchmark-Driven Optimization: Continuous performance regression testing
  基准测试驱动优化：持续性能回归测试
• Hardware-in-the-Loop Testing: Automated testing on real hardware platforms
  硬件在环测试：在真实硬件平台上进行自动化测试
• Model Validation: Accuracy preservation verification throughout optimization
  模型验证：在整个优化过程中保持精度验证
• Deploy-to-Production Pipeline: One-click deployment to embedded systems
  部署到生产管道：一键部署到嵌入式系统

• TensorFlow Lite Compatibility: Seamless migration from TFLite models
  TensorFlow Lite 兼容性：从 TFLite 模型无缝迁移
• PyTorch Mobile Integration: Direct PyTorch model deployment pipeline
  PyTorch 移动集成：直接 PyTorch 模型部署管道
• ONNX Runtime Parity: Feature-complete ONNX runtime alternative
  ONNX 运行时奇偶校验：功能齐全的 ONNX 运行时替代方案
• MLflow Integration: Model versioning and experiment tracking
  MLflow 集成：模型版本控制和实验跟踪
• Edge Impulse Compatibility: Integration with popular edge ML platforms
  Edge Impulse 兼容性：与流行的边缘 ML 平台集成

• OTA Model Updates: Over-the-air model deployment and versioning
  OTA 模型更新：无线模型部署和版本控制
• A/B Testing Framework: Safe model rollout with performance comparison
  A/B 测试框架：安全推出模型并进行性能比较
• Federated Learning Support: Distributed training on edge devices
  联邦学习支持：边缘设备上的分布式训练
• Model Encryption: Secure model storage and execution
  模型加密：安全的模型存储和执行
• Compliance Tools: GDPR, HIPAA, and safety-critical certifications
  合规性工具：GDPR、HIPAA 和安全关键认证

• MLPerf Tiny: Competitive performance on standard benchmarks
  MLPerf Tiny：在标准基准测试中具有竞争力的性能
• EEMBC MLMark: Energy efficiency measurements
  EEMBC MLMark：能效测量
• Custom TinyML Benchmarks: Domain-specific performance evaluation
  自定义 TinyML 基准测试：特定领域的性能评估
• Real-World Workload Testing: Production-representative model validation
  真实工作负载测试：具有生产代表性的模型验证
• Cross-Platform Consistency: Identical results across all supported hardware
  跨平台一致性：在所有支持的硬件上获得相同的结果

• Fuzzing Infrastructure: Automated testing with random inputs
  模糊测试基础设施：使用随机输入进行自动化测试
• Formal Verification: Mathematical proof of correctness for critical operations
  形式化验证：关键作正确性的数学证明
• Hardware Stress Testing: Extended operation under extreme conditions
  硬件压力测试：在极端条件下延长作时间
• Regression Test Suite: Comprehensive backward compatibility testing
  回归测试套件：全面的向后兼容性测试
• Performance Monitoring: Continuous integration with performance tracking
  性能监控：与性能跟踪持续集成

• Zig Compiler: Install the latest Zig compiler
  Zig 编译器：安装最新的 Zig 编译器
• Git: For version control and collaboration
  Git：用于版本控制和协作
• Basic Zig Knowledge: Improve Zig proficiency via Ziglings
  Zig 基础知识：通过 Ziglings 提高 Zig 熟练度

1. Clone the repository: 克隆存储库：

   git clone https://github.com/ZIGTinyBook/Z-Ant.git
   cd Z-Ant

2. Run tests to verify setup:
   运行测试以验证设置：

   zig build test --summary all

3. Generate code for a model:
   为模型生成代码：

   zig build codegen -Dmodel=mnist-1

Start here if you're new to Z-Ant:
如果您是 Z-Ant 的新用户，请从这里开始：

1. Run existing tests: Use zig build test --summary all to understand the codebase
   运行现有测试：用于 zig build test --summary all 了解代码库
2. Try code generation: Use zig build codegen -Dmodel=mnist-1 to see the workflow
   尝试代码生成：用于 zig build codegen -Dmodel=mnist-1 查看工作流程
3. Read the documentation: Check /docs/ folder for detailed guides
   阅读文档：检查 /docs/ 文件夹以获取详细指南
4. Review the Hackathon Guide: For specific guidance on the rendering and lowering pipeline, refer to the HackathonGuide.md.
   查看 Hackathon 指南：有关渲染和降低管道的具体指导，请参阅 HackathonGuide.md。

<span style="background-color:var(--bgColor-muted, var(--color-canvas-subtle))"><span style="color:#1f2328"><span style="color:var(--fgColor-default, var(--color-fg-default))"><span style="background-color:var(--bgColor-muted, var(--color-canvas-subtle))"><code>Z-Ant/
├── src/                    # Core source code
│   ├── Core/              # Neural network core functionality
│   ├── CodeGen/           # Code generation engine
│   ├── ImageToTensor/     # Image preprocessing pipeline
│   ├── onnx/              # ONNX model parsing
│   └── Utils/             # Utilities and helpers
├── tests/                 # Comprehensive test suite
├── datasets/              # Sample models and test data
├── generated/             # Generated code output
├── examples/              # Arduino and microcontroller examples
└── docs/                  # Documentation and guides
</code></span></span></span></span>

# Run comprehensive tests
zig build test --summary all# Generate code for a specific model
zig build codegen -Dmodel=mnist-1# Test generated code
zig build test-codegen -Dmodel=mnist-1# Compile static library for deployment
zig build lib -Dmodel=mnist-1 -Dtarget=thumb-freestanding -Dcpu=cortex_m33

We follow a structured branching strategy to ensure code quality and smooth collaboration:
我们遵循结构化的分支策略来确保代码质量和顺利协作：

• main: Stable, production-ready code for releases
  main ：用于发布的稳定、生产就绪代码
• feature/<feature-name>: New features under development
  feature/<feature-name> ：正在开发的新功能
• fix/<issue-description>: Bug fixes and patches
  fix/<issue-description> ：错误修复和补丁
• docs/<documentation-topic>: Documentation improvements
  docs/<documentation-topic> ： 文档改进
• test/<test-improvements>: Test suite enhancements
  test/<test-improvements> ：测试套件增强功能

• Test Before Committing: Run zig build test --summary all before every commit
  Test Before Committing：在每次提交之前运行 zig build test --summary all
• Document Your Code: Follow Zig's doc-comments standard
  记录您的代码：遵循 Zig 的文档注释标准
• Small, Focused PRs: Keep pull requests small and focused on a single feature/fix
  小型、专注的 PR：保持拉取请求较小并专注于单个功能/修复
• Use Conventional Commits: Follow commit message conventions (feat:, fix:, docs:, etc.)
  使用常规提交：遵循提交消息约定（feat：、fix：、docs： 等）

Using Z-Ant 🔧 使用 Z-Ant

Development Requirements 开发要求

Running Tests 运行测试

Generating Code for Models
为模型生成代码

zig build codegen -Dmodel=model_name [-Dlog -Duser_tests=user_tests.json]

<span style="background-color:var(--bgColor-muted, var(--color-canvas-subtle))"><span style="color:#1f2328"><span style="color:var(--fgColor-default, var(--color-fg-default))"><span style="background-color:var(--bgColor-muted, var(--color-canvas-subtle))"><code>generated/model_name/
├── lib_{model_name}.zig
├── test_{model_name}.zig
└── user_tests.json
</code></span></span></span></span>

Testing Generated Models 测试生成的模型

zig build test-codegen -Dmodel=model_name

Integrating into Your Project
集成到您的项目中

zig build lib -Dmodel=model_name -Dtarget={arch} -Dcpu={cpu}

target_link_libraries(your_project PUBLIC path/to/libzant.a)

Logging (Optional) 日志记录（可选）

extern void setLogFunction(void (*log_function)(uint8_t *string));

🏗️ Build System (build.zig)
🏗️ 构建系统 （ build.zig ）

Available Build Commands 可用的构建命令

Core Commands 核心命令

Testing Commands 测试命令

Profiling & Performance 分析和性能

Command-Line Options 命令行选项

Target & Architecture Options
目标和架构选项

Model & Path Options 模型和路径选项

Code Generation Options 代码生成选项

Testing Options 测试选项

Debug & Profiling Options
调试和分析选项

Common Usage Examples 常见使用示例

# Generate code for MNIST model with logging
zig build codegen -Dmodel=mnist-1 -Dlog=true# Build static library for ARM Cortex-M33
zig build lib -Dmodel=mnist-1 -Dtarget=thumb-freestanding -Dcpu=cortex_m33# Test with heavy computational tests enabled
zig build test -Dheavy=true --summary all# Generate code with custom paths and comments
zig build codegen -Dmodel=custom_model -Dmodel_path=my_models/custom.onnx -Dgenerated_path=output/ -Dcomm=true# Build library with custom output location
zig build lib -Dmodel=mnist-1 -Doutput_path=/path/to/deployment/# Run specific test
zig build test -Dtest_name=tensor_math_test# Build profiling executable for performance analysis
zig build build-main -Dmodel=mnist-1 -Dtarget=native