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 Edge AI and the Ascend 310
- Edge AI Overview: trends, constraints, and key applications.
- Architecture of the Huawei Ascend 310 chip and its supported toolchain.
- The role of CANN within the edge AI deployment stack.
Model Preparation and Conversion
- Exporting trained models from TensorFlow, PyTorch, and MindSpore.
- Utilizing ATC to convert models into the OM format for Ascend devices.
- Managing unsupported operations and applying lightweight conversion strategies.
Building Inference Pipelines with AscendCL
- Executing OM models on the Ascend 310 using the AscendCL API.
- Input/output preprocessing, memory management, and device control.
- Deploying within embedded containers or lightweight runtime environments.
Optimizing for Edge Constraints
- Reducing model size and tuning precision (FP16, INT8).
- Employing the CANN profiler to pinpoint performance bottlenecks.
- Managing memory layout and data streaming to boost performance.
Deployment using MindSpore Lite
- Leveraging the MindSpore Lite runtime for mobile and embedded targets.
- Comparing MindSpore Lite against the raw AscendCL pipeline.
- Packaging inference models for specific device deployments.
Edge Deployment Scenarios and Case Studies
- Case study: Object detection model on a smart camera using Ascend 310.
- Case study: Real-time classification within an IoT sensor hub.
- Monitoring and updating deployed models at the edge.
Summary and Next Steps
Requirements
- Prior experience with AI model development or deployment workflows.
- Fundamental 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.
14 Hours
Testimonials (1)
That we can cover advance topic and work with real-life example
