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 function within Huawei’s AI computing ecosystem
- Overview of Ascend processor architectures, including 310, 910, and other variants
- Survey of supported AI frameworks and the associated toolchain
Model Conversion and Compilation
- Utilizing the ATC tool for converting models from TensorFlow, PyTorch, and ONNX
- Generation and verification of OM model files
- Addressing unsupported operators and resolving frequent conversion challenges
Deployment via MindSpore and Other Frameworks
- Deploying models using MindSpore Lite
- Integrating OM models with Python APIs or C++ SDKs
- Utilizing the Ascend Model Manager
Performance Optimization and Profiling
- Analyzing AI Core, memory, and tiling optimization strategies
- Profiling model execution utilizing CANN-specific tools
- Best practices for enhancing inference speed and resource efficiency
Error Handling and Debugging
- Identifying common deployment errors and implementing solutions
- Interpreting logs and applying the error diagnosis tool
- Conducting unit tests and functional validation of deployed models
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for edge-based applications
- Integrating with cloud-based APIs and microservice architectures
- Real-world case studies in computer vision and NLP
Summary and Future Steps
Requirements
- Proficiency with Python-based deep learning frameworks, including TensorFlow or PyTorch
- A solid grasp of neural network architectures and model training processes
- Foundational knowledge of the Linux CLI and scripting basics
Target Audience
- AI engineers focused on model deployment tasks
- Machine learning specialists aiming for hardware acceleration
- Deep learning developers creating inference solutions
