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
Introduction to Edge AI and the Ascend 310
- Edge AI landscape: exploring trends, limitations, and real-world applications
- Architecture of the Huawei Ascend 310 chip and its supported toolchain
- The role of CANN within the broader edge AI deployment ecosystem
Model Preparation and Transformation
- Exporting trained models from TensorFlow, PyTorch, and MindSpore
- Utilizing ATC to convert models into OM format for Ascend compatibility
- Addressing unsupported operators and implementing lightweight conversion techniques
Building Inference Pipelines with AscendCL
- Executing OM models on Ascend 310 via the AscendCL API
- Managing input/output preprocessing, memory allocation, and device control
- Integration within embedded containers or lightweight runtime environments
Optimization for Edge Limitations
- Minimizing model size and adjusting precision (FP16, INT8)
- Identifying performance bottlenecks using the CANN profiler
- Optimizing memory layout and data streaming for enhanced performance
Deployment via MindSpore Lite
- Leveraging the MindSpore Lite runtime for mobile and embedded targets
- Evaluating MindSpore Lite against the native AscendCL pipeline
- Packaging inference models tailored for specific device deployments
Edge Deployment Scenarios and Case Studies
- Case study: Implementing object detection on a smart camera with Ascend 310
- Case study: Real-time classification within an IoT sensor hub
- Strategies for monitoring and updating models deployed at the edge
Conclusion and Future Directions
Requirements
- Practical experience in AI model development or deployment processes
- Foundational understanding of embedded systems, Linux, and Python
- Proficiency with deep learning frameworks such as TensorFlow or PyTorch
Target Audience
- IoT solution architects
- Embedded AI engineers
- Edge system integrators and AI deployment experts
Testimonials (1)
That we can cover advance topic and work with real-life example
