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 related supporting tools.
- AI development workflow: from training to deployment.
Understanding the CANN Toolkit
- Definition of CANN and its significance.
- Overview of core components (ATC, AscendCL, operator libraries).
- The role of CANN in AI inference pipelines.
Getting Started with MindSpore and CANN
- Environment setup (MindSpore + CANN + Python).
- Training a basic model in MindSpore.
- Exporting and converting the model using ATC.
Running Inference on Ascend Devices
- Utilizing the OM model with AscendCL or Python APIs.
- Basic input/output preprocessing.
- Validating model outputs.
Working with Other Frameworks
- Support overview for TensorFlow, PyTorch, and ONNX.
- Supported operators and associated limitations.
- Simple model conversion demonstration (e.g., from ONNX to OM).
Exploring the CANN and MindSpore Developer Ecosystem
- Key resources: documentation, GitHub repositories, and 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 concepts.
- Programming experience with Python.
- No prior experience with CANN or Ascend hardware is necessary.
Audience
- Machine learning developers exploring deployment workflows.
- Students or researchers new to Huawei's AI ecosystem.
- AI framework contributors and hobbyists interested in model acceleration.
