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 lifecycle of AI models from training through to deployment.
- Critical performance metrics 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 transform models into OM format.
Deploying Inference Pipelines with AscendCL
- Executing CV/NLP inference via the AscendCL API.
- Preprocessing workflows: image resizing, tokenization, and normalization.
- Postprocessing: handling bounding boxes, classification scores, and text outputs.
Performance Optimization Techniques
- Profiling CV and NLP models with CANN utilities.
- Minimizing latency through mixed-precision and batch tuning.
- Managing memory and compute resources for streaming tasks.
Computer Vision Use Cases
- Case study: object detection for intelligent surveillance.
- Case study: visual quality inspection within manufacturing.
- 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
- A solid grasp of deep learning concepts in computer vision or NLP.
- Proficiency with Python and AI frameworks like TensorFlow, PyTorch, or MindSpore.
- Foundational knowledge of model deployment or inference workflows.
Target Audience
- Computer vision and NLP practitioners utilizing Huawei’s Ascend platform.
- Data scientists and AI engineers creating real-time perception models.
- Developers integrating CANN pipelines within manufacturing, surveillance, or media analytics sectors.
