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 CANN and Ascend AI Processors
- Defining CANN and its role within Huawei’s AI compute stack
- An overview of Ascend processor architectures, including models 310, 910, and others
- A summary of supported AI frameworks and the associated toolchain
Model Conversion and Compilation
- Utilizing the ATC tool for converting models from TensorFlow, PyTorch, and ONNX
- The process of generating and validating OM model files
- Managing unsupported operators and addressing common conversion challenges
Deployment via MindSpore and Other Frameworks
- Deploying models using MindSpore Lite
- Integrating OM models through Python APIs or C++ SDKs
- Interfacing with the Ascend Model Manager
Performance Optimization and Profiling
- Insights into AI Core, memory management, and tiling optimizations
- Profiling model execution using CANN diagnostic tools
- Best practices for enhancing inference speed and resource efficiency
Error Handling and Debugging
- Identifying common deployment errors and their solutions
- Interpreting logs and utilizing error diagnosis tools
- Conducting unit tests and functional validation of deployed models
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for edge application use cases
- Integrating with cloud-based APIs and microservices
- Examining real-world case studies in computer vision and NLP
Summary and Future Directions
Requirements
- Practical experience with Python-based deep learning frameworks, including TensorFlow or PyTorch
- A solid grasp of neural network architectures and model training workflows
- Fundamental knowledge of Linux CLI and scripting capabilities
Target Audience
- AI engineers focused on model deployment strategies
- Machine learning specialists aiming for hardware acceleration solutions
- Deep learning developers constructing inference systems
