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
- Insights into Edge AI: trends, limitations, and real-world applications
- Architecture of the Huawei Ascend 310 chip and its associated toolchain
- Understanding CANN’s role in the edge AI deployment ecosystem
Preparing and Converting Models
- Exporting trained models from TensorFlow, PyTorch, and MindSpore
- Utilizing ATC to transform models into OM format compatible with Ascend devices
- Strategies for handling unsupported operations and lightweight conversions
Creating Inference Pipelines with AscendCL
- Leveraging the AscendCL API to execute OM models on the Ascend 310
- Managing input/output preprocessing, memory allocation, and device control
- Implementing deployments within embedded containers or lightweight runtime settings
Optimizing for Edge Limitations
- Techniques for reducing model size and adjusting precision (FP16, INT8)
- Using the CANN profiler to pinpoint performance bottlenecks
- Controlling memory layout and data streams to boost performance
Deployment via MindSpore Lite
- Employing the MindSpore Lite runtime for mobile and embedded targets
- Analyzing MindSpore Lite against the native AscendCL pipeline
- Packaging inference models for specific device deployments
Edge Deployment Scenarios and Case Studies
- Case study: Implementing an object detection model on a smart camera with Ascend 310
- Case study: Real-time classification within an IoT sensor hub
- Monitoring and updating models once deployed at the edge
Recap and Future Directions
Requirements
- Hands-on experience with AI model creation or deployment processes
- Foundational understanding of embedded systems, Linux, and Python
- Proficiency with deep learning frameworks like TensorFlow or PyTorch
Target Audience
- Developers of IoT solutions
- Engineers specializing in embedded AI
- Edge system integrators and experts in AI deployment
Testimonials (1)
That we can cover advance topic and work with real-life example
