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
- Definition of CANN and its role in Huawei’s AI compute stack.
- Overview of Ascend processor architecture (including models like 310, 910, etc.).
- Supported AI frameworks and an overview of the toolchain.
Model Conversion and Compilation
- Utilizing the ATC tool for model conversion (covering TensorFlow, PyTorch, ONNX).
- Creating and validating OM model files.
- Addressing unsupported operators and common conversion issues.
Deployment with MindSpore and Other Frameworks
- Deploying models using MindSpore Lite.
- Integrating OM models with Python APIs or C++ SDKs.
- Working with Ascend Model Manager.
Performance Optimization and Profiling
- Understanding AI Core, memory, and tiling optimizations.
- Profiling model execution using CANN tools.
- Best practices for enhancing inference speed and resource utilization.
Error Handling and Debugging
- Identifying common deployment errors and their resolutions.
- Reading logs and utilizing the error diagnosis tool.
- Unit testing and functional validation of deployed models.
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for edge applications.
- Integration with cloud-based APIs and microservices.
- Real-world case studies in computer vision and NLP.
Summary and Next Steps
Requirements
- Experience with Python-based deep learning frameworks such as TensorFlow or PyTorch.
- Understanding of neural network architectures and model training workflows.
- Basic familiarity with Linux CLI and scripting.
Target Audience
- AI engineers involved in model deployment.
- Machine learning practitioners focusing on hardware acceleration.
- Deep learning developers constructing inference solutions.
14 Hours
