CANN for Edge AI Deployment Training Course
Huawei's Ascend CANN toolkit delivers powerful AI inference capabilities on edge devices such as the Ascend 310. CANN provides essential tools for compiling, optimising, and deploying models in environments where compute and memory resources are limited.
This instructor-led, live training (available online or on-site) is designed for intermediate-level AI developers and integrators who wish to deploy and optimise models on Ascend edge devices using the CANN toolchain.
By the end of this training, participants will be able to:
- Prepare and convert AI models for the Ascend 310 using CANN tools.
- Build lightweight inference pipelines using MindSpore Lite and AscendCL.
- Optimise model performance for constrained compute and memory environments.
- Deploy and monitor AI applications in real-world edge use cases.
Format of the Course
- Interactive lectures and live demonstrations.
- Hands-on laboratory work with edge-specific models and scenarios.
- Live deployment examples on virtual or physical edge hardware.
Course Customisation Options
- To request a customised training session for this course, please contact us to make arrangements.
Course Outline
Introduction to Edge AI and the Ascend 310
- Overview of Edge AI: trends, constraints, and applications
- Huawei Ascend 310 chip architecture and supported toolchain
- Positioning CANN within the edge AI deployment stack
Model Preparation and Conversion
- Exporting trained models from TensorFlow, PyTorch, and MindSpore
- Using ATC to convert models to OM format for Ascend devices
- Handling unsupported operators and lightweight conversion strategies
Developing Inference Pipelines with AscendCL
- Using the AscendCL API to run OM models on the Ascend 310
- Input/output preprocessing, memory handling, and device control
- Deploying within embedded containers or lightweight runtime environments
Optimisation for Edge Constraints
- Reducing model size and tuning precision (FP16, INT8)
- Using the CANN profiler to identify bottlenecks
- Managing memory layout and data streaming for optimal performance
Deploying with MindSpore Lite
- Using the MindSpore Lite runtime for mobile and embedded targets
- Comparing MindSpore Lite with a raw AscendCL pipeline
- Packaging inference models for device-specific deployment
Edge Deployment Scenarios and Case Studies
- Case study: smart camera with object detection model on the Ascend 310
- Case study: real-time classification in an IoT sensor hub
- Monitoring and updating deployed models at the edge
Summary and Next Steps
Requirements
- Experience with AI model development or deployment workflows
- Basic knowledge of embedded systems, Linux, and Python
- Familiarity with deep learning frameworks such as TensorFlow or PyTorch
Audience
- IoT solution developers
- Embedded AI engineers
- Edge system integrators and AI deployment specialists
Open Training Courses require 5+ participants.
CANN for Edge AI Deployment Training Course - Booking
CANN for Edge AI Deployment Training Course - Enquiry
CANN for Edge AI Deployment - Consultancy Enquiry
Testimonials (1)
That we can cover advance topic and work with real-life example
Ruben Khachaturyan - iris-GmbH infrared & intelligent sensors
Course - Advanced Edge AI Techniques
Provisional Upcoming Courses (Require 5+ participants)
Related Courses
5G and Edge AI: Enabling Ultra-Low Latency Applications
21 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at intermediate-level telecom professionals, AI engineers, and IoT specialists who wish to explore how 5G networks accelerate Edge AI applications.
By the end of this training, participants will be able to:
- Understand the fundamentals of 5G technology and its impact on Edge AI.
- Deploy AI models optimised for low-latency applications in 5G environments.
- Implement real-time decision-making systems using Edge AI and 5G connectivity.
- Optimise AI workloads for efficient performance on edge devices.
6G and the Intelligent Edge
21 Hours6G and the Intelligent Edge is a forward-looking course that explores the integration of 6G wireless technologies with edge computing, IoT ecosystems, and AI-driven data processing to support intelligent, low-latency, and adaptive infrastructures.
This instructor-led, live training (online or onsite) is aimed at intermediate-level IT architects who wish to understand and design next-generation distributed architectures leveraging the synergy of 6G connectivity and intelligent edge systems.
Upon completion of this course, participants will be able to:
- Understand how 6G will transform edge computing and IoT architectures.
- Design distributed systems for ultra-low latency, high bandwidth, and autonomous operations.
- Integrate AI and data analytics at the edge for intelligent decision-making.
- Plan scalable, secure, and resilient 6G-ready edge infrastructures.
- Evaluate business and operational models enabled by 6G-edge convergence.
Format of the Course
- Interactive lectures and discussions.
- Case studies and applied architecture design exercises.
- Hands-on simulation with optional edge or container tools.
Course Customization Options
- To request a customised training for this course, please contact us to arrange.
Advanced Edge AI Techniques
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at advanced-level AI practitioners, researchers, and developers who wish to master the latest advancements in Edge AI, optimise their AI models for edge deployment, and explore specialised applications across various industries.
By the end of this training, participants will be able to:
- Explore advanced techniques in Edge AI model development and optimisation.
- Implement cutting-edge strategies for deploying AI models on edge devices.
- Utilise specialised tools and frameworks for advanced Edge AI applications.
- Optimise the performance and efficiency of Edge AI solutions.
- Explore innovative use cases and emerging trends in Edge AI.
- Address advanced ethical and security considerations in Edge AI deployments.
Developing AI Applications with Huawei Ascend and CANN
21 HoursHuawei Ascend is a family of AI processors designed for high-performance inference and training.
This instructor-led, live training (online or onsite) is aimed at intermediate-level AI engineers and data scientists who wish to develop and optimise neural network models using Huawei's Ascend platform and the CANN toolkit.
By the end of this training, participants will be able to:
- Set up and configure the CANN development environment.
- Develop AI applications using MindSpore and CloudMatrix workflows.
- Optimise performance on Ascend NPUs using custom operators and tiling.
- Deploy models to edge or cloud environments.
Format of the Course
- Interactive lecture and discussion.
- Hands-on use of Huawei Ascend and CANN toolkit in sample applications.
- Guided exercises focused on model building, training, and deployment.
Course Customisation Options
- To request a customised training for this course based on your infrastructure or datasets, please contact us to arrange.
Deploying AI Models with CANN and Ascend AI Processors
14 HoursCANN (Compute Architecture for Neural Networks) is Huawei's AI compute stack for deploying and optimising AI models on Ascend AI processors.
This instructor-led, live training (online or on-site) is designed for intermediate-level AI developers and engineers who wish to deploy trained AI models efficiently to Huawei Ascend hardware using the CANN toolkit and tools such as MindSpore, TensorFlow, or PyTorch.
By the end of this training, participants will be able to:
- Understand the CANN architecture and its role in the AI deployment pipeline.
- Convert and adapt models from popular frameworks to Ascend-compatible formats.
- Use tools like ATC, OM model conversion, and MindSpore for edge and cloud inference.
- Diagnose deployment issues and optimise performance on Ascend hardware.
Format of the Course
- Interactive lecture and demonstration.
- Hands-on lab work using CANN tools and Ascend simulators or devices.
- Practical deployment scenarios based on real-world AI models.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Building AI Solutions on the Edge
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at intermediate-level developers, data scientists, and tech enthusiasts who wish to gain practical skills in deploying AI models on edge devices for various applications.
By the end of this training, participants will be able to:
- Understand the principles of Edge AI and its benefits.
- Set up and configure the edge computing environment.
- Develop, train, and optimise AI models for edge deployment.
- Implement practical AI solutions on edge devices.
- Evaluate and improve the performance of edge-deployed models.
- Address ethical and security considerations in Edge AI applications.
Building Secure and Resilient Edge AI Systems
21 HoursThis instructor-led, live training in New Zealand (available online or on-site) is designed for advanced-level cybersecurity professionals, AI engineers, and IoT developers who wish to implement robust security measures and resilience strategies for Edge AI systems.
By the end of this training, participants will be able to:
- Understand security risks and vulnerabilities in Edge AI deployments.
- Implement encryption and authentication techniques for data protection.
- Design resilient Edge AI architectures capable of withstanding cyber threats.
- Apply secure AI model deployment strategies in edge environments.
Cambricon MLU Development with BANGPy and Neuware
21 HoursCambricon MLUs (Machine Learning Units) are specialised AI chips optimised for inference and training in edge and datacentre scenarios.
This instructor-led, live training (online or on-site) is designed for intermediate-level developers who wish to build and deploy AI models using the BANGPy framework and Neuware SDK on Cambricon MLU hardware.
By the end of this training, participants will be able to:
- Set up and configure the BANGPy and Neuware development environments.
- Develop and optimise Python- and C++-based models for Cambricon MLUs.
- Deploy models to edge and datacentre devices running the Neuware runtime.
- Integrate ML workflows with MLU-specific acceleration features.
Course Format
- Interactive lectures and discussions.
- Hands-on application of BANGPy and Neuware for development and deployment.
- Guided exercises focused on optimisation, integration, and testing.
Course Customisation Options
- To request a customised training session for this course based on your Cambricon device model or specific use case, please contact us to make arrangements.
Introduction to CANN for AI Framework Developers
7 HoursCANN (Compute Architecture for Neural Networks) is Huawei's AI computing toolkit used to compile, optimise, and deploy AI models on Ascend AI processors.
This instructor-led, live training (online or on-site) is aimed at beginner-level AI developers who wish to understand how CANN fits into the model lifecycle from training to deployment, and how it works with frameworks such as MindSpore, TensorFlow, and PyTorch.
By the end of this training, participants will be able to:
- Understand the purpose and architecture of the CANN toolkit.
- Set up a development environment with CANN and MindSpore.
- Convert and deploy a simple AI model to Ascend hardware.
- Gain foundational knowledge for future CANN optimisation or integration projects.
Format of the Course
- Interactive lecture and discussion.
- Hands-on labs with simple model deployment.
- Step-by-step walkthrough of the CANN toolchain and integration points.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Understanding Huawei’s AI Compute Stack: From CANN to MindSpore
14 HoursHuawei's AI stack — spanning from the low-level CANN SDK to the high-level MindSpore framework — delivers a tightly integrated AI development and deployment environment optimised for Ascend hardware.
This instructor-led, live training (available online or on-site) is designed for beginner to intermediate-level technical professionals seeking to understand how CANN and MindSpore components work together to support AI lifecycle management and inform infrastructure decisions.
By the end of this training, participants will be able to:
- Understand the layered architecture of Huawei's AI compute stack.
- Identify how CANN supports model optimisation and hardware-level deployment.
- Evaluate the MindSpore framework and toolchain in relation to industry alternatives.
- Position Huawei's AI stack within enterprise or cloud/on-premises environments.
Course Format
- Interactive lecture and discussion.
- Live system demonstrations and case-based walkthroughs.
- Optional guided labs exploring model flow from MindSpore to CANN.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Optimizing Neural Network Performance with CANN SDK
14 HoursCANN SDK (Compute Architecture for Neural Networks) is Huawei's AI compute foundation that enables developers to fine-tune and optimise the performance of deployed neural networks on Ascend AI processors.
This instructor-led, live training (available online or on-site) is designed for advanced-level AI developers and system engineers who wish to enhance inference performance using CANN's advanced toolset, including the Graph Engine, TIK, and custom operator development.
By the end of this training, participants will be able to:
- Understand CANN's runtime architecture and performance lifecycle.
- Use profiling tools and the Graph Engine for performance analysis and optimisation.
- Create and optimise custom operators using TIK and TVM.
- Resolve memory bottlenecks and improve model throughput.
Course Format
- Interactive lectures and discussions.
- Hands-on labs featuring real-time profiling and operator tuning.
- Optimisation exercises using edge-case deployment scenarios.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
CANN SDK for Computer Vision and NLP Pipelines
14 HoursThe CANN SDK (Compute Architecture for Neural Networks) delivers powerful deployment and optimisation tools for real-time AI applications in computer vision and NLP, particularly on Huawei Ascend hardware.
This instructor-led, live training (online or on-site) is designed for intermediate-level AI practitioners who wish to build, deploy and optimise vision and language models using the CANN SDK for production use cases.
By the end of this training, participants will be able to:
- Deploy and optimise CV and NLP models using CANN and AscendCL.
- Use CANN tools to convert models and integrate them into live pipelines.
- Optimise inference performance for tasks such as detection, classification and sentiment analysis.
- Build real-time CV/NLP pipelines for edge or cloud-based deployment scenarios.
Course Format
- Interactive lecture and demonstration.
- Hands-on lab covering model deployment and performance profiling.
- Live pipeline design using real-world CV and NLP use cases.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Building Custom AI Operators with CANN TIK and TVM
14 HoursCANN TIK (Tensor Instruction Kernel) and Apache TVM enable advanced optimisation and customisation of AI model operators for Huawei Ascend hardware.
This instructor-led, live training (online or onsite) is aimed at advanced-level system developers who wish to build, deploy, and tune custom operators for AI models using CANN's TIK programming model and TVM compiler integration.
By the end of this training, participants will be able to:
- Write and test custom AI operators using the TIK DSL for Ascend processors.
- Integrate custom ops into the CANN runtime and execution graph.
- Use TVM for operator scheduling, auto-tuning, and benchmarking.
- Debug and optimise instruction-level performance for custom computation patterns.
Format of the Course
- Interactive lecture and demonstration.
- Hands-on coding of operators using TIK and TVM pipelines.
- Testing and tuning on Ascend hardware or simulators.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Edge AI for Agriculture: Smart Farming and Precision Monitoring
21 HoursThis instructor-led, live training in New Zealand (online or onsite) is aimed at beginner-level to intermediate-level agritech professionals, IoT specialists, and AI engineers who wish to develop and deploy Edge AI solutions for smart farming.
By the end of this training, participants will be able to:
- Understand the role of Edge AI in precision agriculture.
- Implement AI-driven crop and livestock monitoring systems.
- Develop automated irrigation and environmental sensing solutions.
- Optimise agricultural efficiency using real-time Edge AI analytics.
Edge AI in Autonomous Systems
14 HoursThis instructor-led, live training in New Zealand (online or onsite) is designed for intermediate-level robotics engineers, autonomous vehicle developers, and AI researchers who aim to leverage Edge AI to create innovative autonomous system solutions.
By the end of this training, participants will be able to:
- Understand the role and benefits of Edge AI in autonomous systems.
- Develop and deploy AI models for real-time processing on edge devices.
- Implement Edge AI solutions in autonomous vehicles, drones, and robotics.
- Design and optimise control systems using Edge AI.
- Address ethical and regulatory considerations in autonomous AI applications.
