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
Introduction to CANN and Ascend AI Processors
- Understanding CANN and its position within Huawei’s AI compute ecosystem.
- An overview of Ascend processor architectures, including the 310 and 910 series.
- A summary of supported AI frameworks and the associated toolchain.
Model Conversion and Compilation
- Utilizing the ATC tool for converting models from TensorFlow, PyTorch, and ONNX.
- Generating and validating OM model files.
- Addressing unsupported operators and resolving typical conversion challenges.
Deployment using MindSpore and Other Frameworks
- Deploying models via MindSpore Lite.
- Integrating OM models with Python APIs or C++ SDKs.
- Utilizing the Ascend Model Manager for workflow management.
Performance Optimization and Profiling
- Insights into AI Core, memory, and tiling optimization strategies.
- Profiling model execution processes using CANN-specific tools.
- Best practices for enhancing inference speed and managing resource utilization.
Error Handling and Debugging
- Identifying and resolving common deployment errors.
- Analyzing logs and utilizing error diagnosis tools.
- Conducting unit testing and functional validation of deployed models.
Edge and Cloud Deployment Scenarios
- Deploying to Ascend 310 for edge-side applications.
- Integrating with cloud-based APIs and microservice architectures.
- Examining real-world case studies in computer vision and NLP.
Summary and Next Steps
Requirements
- Proficiency with Python-based deep learning frameworks like TensorFlow or PyTorch.
- A solid grasp of neural network architectures and model training workflows.
- Foundational knowledge of the Linux command line interface and scripting.
Target Audience
- AI engineers focused on model deployment.
- Machine learning practitioners seeking to leverage hardware acceleration.
- Deep learning developers creating inference solutions.
