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 its position within Huawei’s AI compute stack
- Insight into Ascend processor architecture (310, 910, etc.)
- Review of supported AI frameworks and the toolchain
Model Conversion and Compilation
- Employing the ATC tool for converting models from TensorFlow, PyTorch, and ONNX
- Generating and verifying OM model files
- Addressing unsupported operators and typical conversion pitfalls
Deployment using MindSpore and Other Frameworks
- Deploying models via MindSpore Lite
- Integrating OM models through Python APIs or C++ SDKs
- Interfacing with the Ascend Model Manager
Performance Optimization and Profiling
- Grasping AI Core, memory, and tiling optimization strategies
- Analyzing model execution using CANN profiling tools
- Best practices for boosting inference speed and reducing resource consumption
Error Management and Debugging
- Identifying and resolving frequent deployment errors
- Interpreting logs and utilizing the error diagnosis utility
- Conducting unit tests and functional verification of deployed models
Edge and Cloud Deployment Contexts
- Implementing deployment on Ascend 310 for edge applications
- Connecting with cloud-based APIs and microservices
- Real-world case studies covering computer vision and NLP
Conclusion and Recommended Next Steps
Requirements
- Proficiency with Python-based deep learning frameworks like TensorFlow or PyTorch
- Knowledge of neural network architectures and model training workflows
- Foundational understanding of Linux CLI and scripting
Target Audience
- AI engineers engaged in model deployment
- Machine learning specialists focusing on hardware acceleration
- Deep learning developers creating inference solutions
14 Hours
