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 CANN and Ascend AI Processors
- Defining CANN and exploring its function within Huawei’s AI compute stack
- A review of Ascend processor architectures, including models like 310 and 910
- An overview of supported AI frameworks and the associated toolchain
Model Conversion and Compilation
- Employing the ATC tool to convert models from TensorFlow, PyTorch, and ONNX
- Generating and validating OM model files
- Addressing unsupported operators and resolving typical conversion hurdles
Deploying with MindSpore and Other Frameworks
- Implementing model deployment using MindSpore Lite
- Integrating OM models via Python APIs or C++ SDKs
- Managing deployments with the Ascend Model Manager
Performance Optimization and Profiling
- Gaining insight into AI Core, memory management, and tiling optimizations
- Analyzing model execution profiles using CANN tools
- Adopting best practices to enhance inference speed and resource efficiency
Error Handling and Debugging
- Identifying common deployment errors and their solutions
- Interpreting logs and utilizing error diagnosis utilities
- Performing unit testing and functional validation for deployed models
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for edge-based applications
- Seamlessly integrating with cloud-based APIs and microservices
- Examining real-world case studies in computer vision and NLP
Summary and Next Steps
Requirements
- Proficiency in 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 practices
Target Audience
- AI engineers focused on model deployment strategies
- Machine learning specialists aiming for hardware acceleration
- Deep learning developers constructing inference solutions
14 Hours
