Get in Touch

Course Outline

Introduction to the Huawei Ascend Platform

  • Overview of Ascend architecture and ecosystem
  • MindSpore and CANN overview
  • Use cases and industry relevance

Configuring the Development Environment

  • Installing MindSpore and the CANN toolkit
  • Testing the environment using sample models
  • Utilizing CloudMatrix and ModelArts for project orchestration

Developing Models with MindSpore

  • Model definition and training within MindSpore
  • Exporting models to Ascend-compatible formats
  • Data pipelines and dataset formatting

Optimizing Performance on Ascend

  • Operator fusion and custom kernels
  • AI Core scheduling and tiling strategies
  • Profiling and benchmarking tools

Deployment Strategies

  • Utilizing the MindX SDK for deployment
  • Edge versus cloud deployment tradeoffs
  • Integration with CloudMatrix workflows

Debugging and Monitoring

  • Tracing using Profiler and AiD
  • Debugging runtime failures
  • Monitoring resource usage and throughput

Case Study and Lab Integration

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

Summary and Next Steps

Requirements

  • Proficiency in AI workflows and neural networks
  • Hands-on experience with Python programming
  • Understanding of deployment pipelines and model training

Audience

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

Number of participants


Price per participant

Testimonials (1)

Upcoming Courses

Related Categories