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.
- An overview of Ascend processor architectures, including models 310, 910, and others.
- A summary of supported AI frameworks and the associated toolchain.
Model Conversion and Compilation
- Applying the ATC tool for model conversion from TensorFlow, PyTorch, and ONNX.
- The process of creating and validating OM model files.
- Managing unsupported operators and addressing frequent conversion challenges.
Deployment via MindSpore and Other Frameworks
- Deploying models effectively using MindSpore Lite.
- Integrating OM models with Python APIs or C++ SDKs.
- Utilising the Ascend Model Manager for streamlined operations.
Performance Optimisation and Profiling
- Explaining AI Core, memory management, and tiling optimisation strategies.
- Profiling model execution using native CANN tools.
- Industry best practices for enhancing inference speed and resource efficiency.
Error Handling and Debugging
- Identifying common deployment errors and their effective resolution.
- Interpreting logs and utilising error diagnosis tools for troubleshooting.
- Conducting unit tests and functional validation of deployed models.
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for targeted edge applications.
- Integrating solutions with cloud-based APIs and microservices.
- Examining real-world case studies in computer vision and NLP.
Summary and Next Steps
Requirements
- Proficiency with Python-based deep learning frameworks, including TensorFlow or PyTorch.
- A solid grasp of neural network architectures and standard model training workflows.
- Fundamental familiarity with Linux CLI commands and scripting.
Target Audience
- AI engineers focused on model deployment strategies.
- Machine learning practitioners seeking to leverage hardware acceleration.
- Deep learning developers constructing robust inference solutions.
14 Hours
Custom Corporate Training
Training solutions designed exclusively for businesses.
- Customized Content: We adapt the syllabus and practical exercises to the real goals and needs of your project.
- Flexible Schedule: Dates and times adapted to your team's agenda.
- Format: Online (live), In-company (at your offices), or Hybrid.
Price per private group, online live training, starting from 2600 € + VAT*
Contact us for an exact quote and to hear our latest promotions
