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 AI model lifecycle from training through to deployment.
- Critical performance considerations for real-time CV and NLP applications.
- An overview of CANN SDK tools and their function in model integration.
Preparing CV and NLP Models
- Exporting models from PyTorch, TensorFlow, and MindSpore.
- Managing model inputs and outputs for image and text tasks.
- Utilizing ATC to convert models into OM format.
Deploying Inference Pipelines with AscendCL
- Executing CV/NLP inference via the AscendCL API.
- Preprocessing workflows: including image resizing, tokenization, and normalization.
- Postprocessing tasks: handling bounding boxes, classification scores, and text output.
Performance Optimization Techniques
- Profiling CV and NLP models using CANN tools.
- Reducing latency through mixed-precision and batch tuning.
- Managing memory and compute resources for streaming tasks.
Computer Vision Use Cases
- Case study: Object detection for smart surveillance systems.
- Case study: Visual quality inspection in manufacturing settings.
- Constructing live video analytics pipelines on Ascend 310.
NLP Use Cases
- Case study: Sentiment analysis and intent detection.
- Case study: Document classification and summarization.
- Real-time NLP integration with REST APIs and messaging systems.
Summary and Next Steps
Requirements
- Proficiency in deep learning concepts for computer vision or NLP.
- Practical experience with Python and AI frameworks like TensorFlow, PyTorch, or MindSpore.
- A foundational grasp of model deployment and inference workflows.
Audience
- Computer vision and NLP practitioners working with Huawei’s Ascend platform.
- Data scientists and AI engineers developing real-time perception models.
- Developers integrating CANN pipelines in sectors such as manufacturing, surveillance, or media analytics.
