Course Code: cannsdkcv
Duration: 14 hours
Prerequisites:
  • Familiarity with deep learning for computer vision or NLP
  • Experience with Python and AI frameworks such as TensorFlow, PyTorch, or MindSpore
  • Basic understanding of model deployment or inference workflows

Audience

  • Computer vision and NLP practitioners using Huawei’s Ascend platform
  • Data scientists and AI engineers developing real-time perception models
  • Developers integrating CANN pipelines in manufacturing, surveillance, or media analytics
Overview:

The CANN SDK (Compute Architecture for Neural Networks) provides powerful deployment and optimization tools for real-time AI applications in computer vision and NLP, especially on Huawei Ascend hardware.

This instructor-led, live training (online or onsite) is aimed at intermediate-level AI practitioners who wish to build, deploy, and optimize vision and language models using the CANN SDK for production use cases.

By the end of this training, participants will be able to:

  • Deploy and optimize CV and NLP models using CANN and AscendCL.
  • Use CANN tools to convert models and integrate them into live pipelines.
  • Optimize inference performance for tasks like detection, classification, and sentiment analysis.
  • Build real-time CV/NLP pipelines for edge or cloud-based deployment scenarios.

Format of the Course

  • Interactive lecture and demonstration.
  • Hands-on lab with model deployment and performance profiling.
  • Live pipeline design using real CV and NLP use cases.

Course Customization Options

  • To request a customized training for this course, please contact us to arrange.
Course Outline:

Introduction to CV/NLP Deployment with CANN

  • AI model lifecycle from training to deployment
  • Key performance considerations for real-time CV and NLP
  • Overview of CANN SDK tools and their role in model integration

Preparing CV and NLP Models

  • Exporting models from PyTorch, TensorFlow, and MindSpore
  • Handling model inputs/outputs for image and text tasks
  • Using ATC to convert models to OM format

Deploying Inference Pipelines with AscendCL

  • Running CV/NLP inference using the AscendCL API
  • Preprocessing pipelines: image resizing, tokenization, normalization
  • Postprocessing: bounding boxes, classification scores, text output

Performance Optimization Techniques

  • Profiling CV and NLP models using CANN tools
  • Reducing latency with mixed-precision and batch tuning
  • Managing memory and compute for streaming tasks

Computer Vision Use Cases

  • Case study: object detection for smart surveillance
  • Case study: visual quality inspection in manufacturing
  • Building 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

Sites Published:

United Arab Emirates - CANN SDK for Computer Vision and NLP Pipelines

Qatar - CANN SDK for Computer Vision and NLP Pipelines

Egypt - CANN SDK for Computer Vision and NLP Pipelines

Saudi Arabia - CANN SDK for Computer Vision and NLP Pipelines

South Africa - CANN SDK for Computer Vision and NLP Pipelines

Brasil - CANN SDK for Computer Vision and NLP Pipelines

Canada - CANN SDK for Computer Vision and NLP Pipelines

中国 - CANN SDK for Computer Vision and NLP Pipelines

香港 - CANN SDK for Computer Vision and NLP Pipelines

澳門 - CANN SDK for Computer Vision and NLP Pipelines

台灣 - CANN SDK for Computer Vision and NLP Pipelines

USA - CANN SDK for Computer Vision and NLP Pipelines

Österreich - CANN SDK for Computer Vision and NLP Pipelines

Schweiz - CANN SDK for Computer Vision and NLP Pipelines

Deutschland - CANN SDK for Computer Vision and NLP Pipelines

Czech Republic - CANN SDK for Computer Vision and NLP Pipelines

Denmark - CANN SDK for Computer Vision and NLP Pipelines

Estonia - CANN SDK for Computer Vision and NLP Pipelines

Finland - CANN SDK for Computer Vision and NLP Pipelines

Greece - CANN SDK for Computer Vision and NLP Pipelines

Magyarország - CANN SDK for Computer Vision and NLP Pipelines

Ireland - CANN SDK for Computer Vision and NLP Pipelines

Luxembourg - CANN SDK for Computer Vision and NLP Pipelines

Latvia - CANN SDK for Computer Vision and NLP Pipelines

España - CANN SDK for Computer Vision and NLP Pipelines

Italia - CANN SDK for Computer Vision and NLP Pipelines

Lithuania - CANN SDK for Computer Vision and NLP Pipelines

Nederland - CANN SDK for Computer Vision and NLP Pipelines

Norway - CANN SDK for Computer Vision and NLP Pipelines

Portugal - CANN SDK for Computer Vision and NLP Pipelines

România - CANN SDK for Computer Vision and NLP Pipelines

Sverige - CANN SDK for Computer Vision and NLP Pipelines

Türkiye - CANN SDK for Computer Vision and NLP Pipelines

Malta - CANN SDK for Computer Vision and NLP Pipelines

Belgique - CANN SDK for Computer Vision and NLP Pipelines

France - CANN SDK for Computer Vision and NLP Pipelines

日本 - CANN SDK for Computer Vision and NLP Pipelines

Australia - CANN SDK for Computer Vision and NLP Pipelines

Malaysia - CANN SDK for Computer Vision and NLP Pipelines

New Zealand - CANN SDK for Computer Vision and NLP Pipelines

Philippines - CANN SDK for Computer Vision and NLP Pipelines

Singapore - CANN SDK for Computer Vision and NLP Pipelines

Thailand - CANN SDK for Computer Vision and NLP Pipelines

Vietnam - CANN SDK for Computer Vision and NLP Pipelines

India - CANN SDK for Computer Vision and NLP Pipelines

Argentina - CANN SDK for Computer Vision and NLP Pipelines

Chile - CANN SDK for Computer Vision and NLP Pipelines

Costa Rica - CANN SDK for Computer Vision and NLP Pipelines

Ecuador - CANN SDK for Computer Vision and NLP Pipelines

Guatemala - CANN SDK for Computer Vision and NLP Pipelines

Colombia - CANN SDK for Computer Vision and NLP Pipelines

México - CANN SDK for Computer Vision and NLP Pipelines

Panama - CANN SDK for Computer Vision and NLP Pipelines

Peru - CANN SDK for Computer Vision and NLP Pipelines

Uruguay - CANN SDK for Computer Vision and NLP Pipelines

Venezuela - CANN SDK for Computer Vision and NLP Pipelines

Polska - CANN SDK for Computer Vision and NLP Pipelines

United Kingdom - CANN SDK for Computer Vision and NLP Pipelines

South Korea - CANN SDK for Computer Vision and NLP Pipelines

Pakistan - CANN SDK for Computer Vision and NLP Pipelines

Sri Lanka - CANN SDK for Computer Vision and NLP Pipelines

Bulgaria - CANN SDK for Computer Vision and NLP Pipelines

Bolivia - CANN SDK for Computer Vision and NLP Pipelines

Indonesia - CANN SDK for Computer Vision and NLP Pipelines

Kazakhstan - CANN SDK for Computer Vision and NLP Pipelines

Moldova - CANN SDK for Computer Vision and NLP Pipelines

Morocco - CANN SDK for Computer Vision and NLP Pipelines

Tunisia - CANN SDK for Computer Vision and NLP Pipelines

Kuwait - CANN SDK for Computer Vision and NLP Pipelines

Oman - CANN SDK for Computer Vision and NLP Pipelines

Slovakia - CANN SDK for Computer Vision and NLP Pipelines

Kenya - CANN SDK for Computer Vision and NLP Pipelines

Nigeria - CANN SDK for Computer Vision and NLP Pipelines

Botswana - CANN SDK for Computer Vision and NLP Pipelines

Slovenia - CANN SDK for Computer Vision and NLP Pipelines

Croatia - CANN SDK for Computer Vision and NLP Pipelines

Serbia - CANN SDK for Computer Vision and NLP Pipelines

Bhutan - CANN SDK for Computer Vision and NLP Pipelines

Nepal - CANN SDK for Computer Vision and NLP Pipelines

Uzbekistan - CANN SDK for Computer Vision and NLP Pipelines