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 CV/NLP Deployment with CANN
- The end-to-end AI model lifecycle, from training to production deployment.
- Critical performance factors for real-time CV and NLP applications.
- An overview of CANN SDK tools and their role in model integration.
Preparing CV and NLP Models
- Exporting models from frameworks such as PyTorch, TensorFlow, and MindSpore.
- Managing model inputs and outputs for image and text-based tasks.
- Utilizing ATC to convert models into the OM format.
Deploying Inference Pipelines with AscendCL
- Executing CV/NLP inference via the AscendCL API.
- Implementing preprocessing steps, including image resizing, tokenization, and normalization.
- Handling postprocessing tasks such as bounding boxes, classification scores, and text generation.
Performance Optimization Techniques
- Profiling CV and NLP models using specialized CANN tools.
- Reducing latency through mixed-precision inference and batch size tuning.
- Managing memory and compute resources for streaming workloads.
Computer Vision Use Cases
- Case study: Object detection for intelligent surveillance systems.
- Case study: Visual quality inspection in manufacturing environments.
- Developing live video analytics pipelines on the Ascend 310.
NLP Use Cases
- Case study: Sentiment analysis and intent detection.
- Case study: Document classification and automated summarization.
- Integrating real-time NLP with REST APIs and messaging systems.
Summary and Next Steps
Requirements
- Solid familiarity with deep learning concepts in computer vision or NLP.
- Practical experience with Python and major AI frameworks, including TensorFlow, PyTorch, or MindSpore.
- A foundational grasp of model deployment and inference workflows.
Target Audience
- Computer vision and NLP specialists working with Huawei’s Ascend platform.
- Data scientists and AI engineers focused on developing real-time perception models.
- Developers integrating CANN pipelines into sectors such as manufacturing, surveillance, or media analytics.
