CANN SDK for Computer Vision and NLP Pipelines Training Course

Introduction to CV and NLP Deployment with CANN

• Understanding the AI model lifecycle from training through to deployment
• Critical performance metrics for real-time CV and NLP applications
• An overview of CANN SDK tools and their significance in model integration

Preparing CV and NLP Models

• Techniques for exporting models from PyTorch, TensorFlow, and MindSpore
• Managing model inputs and outputs specific to image and text processing tasks
• Utilizing ATC to transform models into the OM format

Deploying Inference Pipelines with AscendCL

• Executing CV and NLP inference tasks via the AscendCL API
• Implementing preprocessing pipelines such as image resizing, tokenization, and normalization
• Applying postprocessing techniques for bounding boxes, classification scores, and text generation

Performance Optimization Techniques

• Profiling CV and NLP models using dedicated CANN tools
• Strategies to reduce latency through mixed-precision computing and batch size tuning
• Efficient memory and compute resource management for streaming workloads

Computer Vision Use Cases

• Case study: Implementing object detection for intelligent surveillance systems
• Case study: Applying visual quality inspection in manufacturing processes
• Developing live video analytics pipelines on Ascend 310 hardware

NLP Use Cases

• Case study: Performing sentiment analysis and intent detection
• Case study: Automating document classification and content summarization
• Integrating real-time NLP capabilities with REST APIs and messaging platforms

Summary and Next Steps