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.
Course Outline
Introduction to Huawei’s AI Ecosystem
- Ascend AI hardware: Overview of 310, 910, and 910B chips.
- MindSpore, CANN, and associated supporting tools.
- The AI development workflow, spanning from model training to deployment.
Understanding the CANN Toolkit
- Defining CANN and its significance in the industry.
- Overview of core components, including ATC, AscendCL, and operator libraries.
- The role CANN plays within AI inference pipelines.
Getting Started with MindSpore and CANN
- Setting up the development environment (MindSpore + CANN + Python).
- Training a basic model using MindSpore.
- Exporting and converting the model using the ATC tool.
Running Inference on Ascend Devices
- Utilizing the OM model with AscendCL or Python APIs.
- Performing basic input and output preprocessing.
- Validating model outputs for accuracy.
Working with Other Frameworks
- Overview of support for TensorFlow, PyTorch, and ONNX.
- Supported operators and known limitations.
- Simple model conversion demonstration (e.g., converting from ONNX to OM format).
Exploring the CANN and MindSpore Developer Ecosystem
- Key resources: documentation, GitHub repositories, and sample code.
- Overview of the MindSpore Hub and model zoo.
- Community forums, events, and available support channels.
Summary and Next Steps
Requirements
- Fundamental understanding of machine learning and deep learning principles.
- Some prior programming experience in Python.
- No previous exposure to CANN or Ascend hardware is required.
Target Audience
- Machine learning developers interested in exploring deployment workflows.
- Students or researchers newly entering Huawei's AI ecosystem.
- AI framework contributors and enthusiasts eager to learn about model acceleration.
7 Hours
