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: key trends, hardware constraints, and practical applications
- Ascend 310 chip architecture and its compatible toolchain
- The role of CANN in the broader edge AI deployment stack
Model Preparation and Conversion
- Exporting trained models from TensorFlow, PyTorch, and MindSpore
- Utilizing the ATC tool to convert models into OM format for Ascend hardware
- Addressing unsupported operators and applying lightweight conversion techniques
Building Inference Pipelines with AscendCL
- Executing OM models on the Ascend 310 via the AscendCL API
- Managing input/output preprocessing, memory allocation, and device control
- Implementation within embedded containers or lightweight runtime environments
Optimizing for Edge Constraints
- Minimizing model size and tuning precision (FP16, INT8)
- Leveraging the CANN profiler to pinpoint performance bottlenecks
- Optimizing memory layout and data streaming for improved throughput
Deployment with MindSpore Lite
- Utilizing the MindSpore Lite runtime for mobile and embedded targets
- Comparative analysis of MindSpore Lite versus raw AscendCL pipelines
- Packaging inference models for device-specific deployment scenarios
Edge Deployment Scenarios and Case Studies
- Case study: Object detection model implementation 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 with AI model development or deployment workflows
- Foundational understanding of embedded systems, Linux, and Python
- Familiarity with deep learning frameworks such as TensorFlow or PyTorch
Target 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
