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 14 hours
Course Outline
Foundations of Edge AI and the Ascend 310
- Introduction to Edge AI: market trends, hardware constraints, and use cases
- Architecture of the Huawei Ascend 310 chip and its supported toolchain
- Understanding CANN’s role within the edge AI deployment ecosystem
Preparing and Converting Models
- Exporting trained models from TensorFlow, PyTorch, and MindSpore
- Utilising ATC to transform models into OM format compatible with Ascend devices
- Strategies for handling unsupported operations and lightweight conversion techniques
Creating Inference Pipelines with AscendCL
- Executing OM models on the Ascend 310 via the AscendCL API
- Managing input/output preprocessing, memory allocation, and device control
- Integration within embedded containers or lightweight runtime environments
Optimising for Edge Limitations
- Reducing model footprint and adjusting precision (FP16, INT8)
- Leveraging the CANN profiler to pinpoint performance bottlenecks
- Optimising memory layout and data streaming for enhanced performance
Deployment with MindSpore Lite
- Employing the MindSpore Lite runtime for mobile and embedded applications
- Comparing MindSpore Lite against the native AscendCL pipeline
- Packaging inference models for specific device deployment
Edge Deployment Scenarios and Practical Examples
- Case study: implementing object detection on a smart camera using Ascend 310
- Case study: real-time classification within an IoT sensor hub
- Strategies for monitoring and updating models deployed at the edge
Recap and Future Directions
Requirements
- Prior experience in AI model development or deployment processes
- Foundational understanding of embedded systems, Linux, and Python
- Working knowledge of deep learning frameworks like TensorFlow or PyTorch
Intended Audience
- IoT solution developers
- Embedded AI engineers
- Edge system integrators and AI deployment specialists
Testimonials (1)
That we can cover advance topic and work with real-life example
