Get in Touch

Course Outline

Introduction to the Huawei Ascend Platform

  • Overview of the Ascend architecture and ecosystem
  • Insights into MindSpore and CANN
  • Relevant use cases and industry applications

Establishing the Development Environment

  • Installation of the CANN toolkit and MindSpore
  • Utilizing ModelArts and CloudMatrix for project orchestration
  • Verifying the environment using sample models

Model Development with MindSpore

  • Defining and training models within MindSpore
  • Managing data pipelines and dataset formatting
  • Exporting models to formats compatible with Ascend

Performance Optimization on Ascend

  • Operator fusion and custom kernel implementation
  • Tiling strategies and AI Core scheduling
  • Benchmarking and profiling utilities

Deployment Strategies

  • Evaluating tradeoffs between edge and cloud deployment
  • Employing the MindX SDK for deployment purposes
  • Integrating with CloudMatrix workflows

Debugging and Monitoring

  • Using Profiler and AiD for tracing
  • Resolving runtime failures
  • Tracking resource usage and throughput

Case Study and Lab Integration

  • Full pipeline development using MindSpore
  • Lab Exercise: Build, optimize, and deploy a model on Ascend
  • Performance comparison with other platforms

Summary and Next Steps

Requirements

  • A foundational understanding of neural networks and AI workflows
  • Practical experience with Python programming
  • Familiarity with pipelines for model training and deployment

Target Audience

  • AI engineers
  • Data scientists utilizing the Huawei AI stack
  • ML developers working with Ascend and MindSpore
 21 Hours

Testimonials (1)

Upcoming Courses

Related Categories