\u200E
  • 开始使用
  • 特性
  • 文档
    • API
    • 使用指南
  • 工具平台
    • 工具
      • AutoDL
      • PaddleHub
      • PARL
      • ERNIE
      • 全部
    • 平台
      • AI Studio
      • EasyDL
      • EasyEdge
  • 资源
    • 模型和数据集
    • 学习资料
    • 应用案例
  • 3.0
  • develop
  • 3.0-beta
  • 2.6
  • 2.5
  • 2.4
  • 2.3
  • 2.2
  • 2.1
  • 2.0
  • 1.8
  • 中文(简)
  • English(En)
  • Installation Guide
    • Install via pip
      • Install on Linux via PIP
      • Install on macOS via PIP
      • Install on Windows via PIP
    • Install via conda
      • Installation on Linux via Conda
      • Installation on macOS via Conda
      • Installation on Windows via Conda
    • Install via docker
      • Install on Linux via Docker
      • Install on macOS via Docker
      • Docker List
    • Compile From Source Code
      • Compile on Linux from Source Code
      • Compile on macOS from Source Code
      • Compile on Windows from Source Code
    • NVIDIA PaddlePaddle Container Installation Guide
    • Appendix
  • Guides
    • Model Development
      • Introduction to Tensor
    • More Uses for Model Development
      • Model Visualization
      • Introduction to models and layers
      • Gradient clip methods in Paddle
      • Introduction to Data Type Promotion
    • Dynamic to Static Graph
      • Supported Grammars
      • Error Debugging Experience
    • Deploy Inference Model
      • Model Compression
    • Distributed Training
      • Quick start for distributed training
    • Performance Improving
      • Automatic Mixed Precision Training (AMP)
      • Auto-tuning in Full-process Training (Beta)
    • Model Convert
      • Upgrade guide
    • FLAGS
      • cudnn
      • data processing
      • debug
        • check nan inf tool
      • device management
      • distributed
      • executor
      • memory management
      • ascend npu
      • others
  • API Reference
  • Contribution Guidelines
    • Kernel Primitive API
      • API Description
        • API Description - IO
        • API Description - Compute
        • API Description - OpFunc
      • API Examples
        • ElementwiseAdd
        • Reduce
        • Model
    • Custom Device Support
      • Custom Runtime
        • Data Type
        • Device APIs
        • Memory APIs
        • Stream APIs
        • Event APIs
      • Custom Kernel
        • Kernel Function Declaration
        • Kernel Implementation APIs
          • Context APIs
          • Tensor APIs
          • Exception API
        • Kernel Registration API
      • CustomDevice Example
  • 3.0 Release Note
  • Performance Improving
  • »
  • Guides »
  • Performance Improving
  • Edit on GitHub

Performance Improving¶

  • AMP

  • Auto-tuning in Full-process Training