Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 7 hours
Course Outline
Introduction to Huawei’s AI Ecosystem
- Ascend AI hardware: 310, 910, and 910B chips
- MindSpore, CANN, and auxiliary tools
- AI development workflow: from training through to deployment
Understanding the CANN Toolkit
- Definition of CANN and its significance
- Overview of core components (ATC, AscendCL, operator libraries)
- The function of CANN within AI inference pipelines
Getting Started with MindSpore and CANN
- Configuring the environment (MindSpore + CANN + Python)
- Training a basic model using MindSpore
- Exporting and converting the model via ATC
Running Inference on Ascend Devices
- Utilizing OM models through AscendCL or Python APIs
- Fundamental input/output preprocessing
- Verifying model outputs
Working with Other Frameworks
- Summary of support for TensorFlow, PyTorch, and ONNX
- Compatible operators and existing limitations
- Demonstration of a simple model conversion (e.g., from ONNX to OM)
Exploring the CANN and MindSpore Developer Ecosystem
- Essential resources: documentation, GitHub repositories, sample code
- Overview of MindSpore Hub and the model zoo
- Community forums, events, and support channels
Summary and Next Steps
Requirements
- Fundamental understanding of machine learning and deep learning principles
- Some programming proficiency in Python
- No prior experience with CANN or Ascend hardware is necessary
Audience
- Machine learning developers investigating deployment processes
- Students or researchers unfamiliar with Huawei’s AI ecosystem
- AI framework contributors and enthusiasts interested in model acceleration
