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
CANN and Ascend AI Processor Foundations
- Defining CANN and its function within Huawei’s AI compute stack.
- An overview of Ascend processor architectures (e.g., 310, 910).
- A summary of supported AI frameworks and the associated toolchain.
Model Conversion and Compilation
- Leveraging the ATC tool for converting models from TensorFlow, PyTorch, or ONNX.
- Generating and verifying OM model files.
- Addressing unsupported operators and resolving common conversion obstacles.
Deployment via MindSpore and Other Frameworks
- Implementing model deployment with MindSpore Lite.
- Integrating OM models using Python APIs or C++ SDKs.
- Utilizing the Ascend Model Manager.
Performance Optimization and Profiling
- Exploring AI Core, memory, and tiling optimizations.
- Analyzing model execution through CANN profiling tools.
- Applying best practices to enhance inference speed and resource efficiency.
Error Management and Debugging
- Identifying and resolving frequent deployment errors.
- Interpreting logs and utilizing error diagnosis utilities.
- Conducting unit testing and functional validation of deployed models.
Edge and Cloud Deployment Scenarios
- Deploying solutions to Ascend 310 for edge applications.
- Integrating with cloud-based APIs and microservices.
- Examining real-world case studies in computer vision and NLP.
Recap and Future Directions
Requirements
- Proficiency with Python-based deep learning frameworks like TensorFlow or PyTorch.
- A solid understanding of neural network architectures and model training workflows.
- Basic competence with the Linux command-line interface and scripting.
Target Audience
- AI engineers focused on model deployment.
- Machine learning practitioners aiming for hardware acceleration.
- Deep learning developers constructing inference solutions.
