CANN SDK for Computer Vision and NLP Pipelines Training Course
The CANN SDK (Compute Architecture for Neural Networks) offers robust deployment and optimization tools for real-time AI applications in computer vision and NLP, particularly on Huawei Ascend hardware.
This instructor-led, live training (available online or onsite) is designed for intermediate-level AI practitioners looking to build, deploy, and optimize vision and language models using the CANN SDK for production environments.
Upon completing this training, participants will be able to:
- Deploy and optimize CV and NLP models using CANN and AscendCL.
- Utilize CANN tools to convert models and integrate them into live pipelines.
- Optimize inference performance for tasks such as detection, classification, and sentiment analysis.
- Construct real-time CV/NLP pipelines suitable for edge or cloud-based deployment scenarios.
Format of the Course
- Interactive lecture and demonstration.
- Hands-on lab involving model deployment and performance profiling.
- Live pipeline design utilizing real-world CV and NLP use cases.
Course Customization Options
- To request 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
Requirements
- 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
Open Training Courses require 5+ participants.
CANN SDK for Computer Vision and NLP Pipelines Training Course - Booking
CANN SDK for Computer Vision and NLP Pipelines Training Course - Enquiry
CANN SDK for Computer Vision and NLP Pipelines - Consultancy Enquiry
Upcoming Courses
Related Courses
Advanced LangGraph: Optimization, Debugging, and Monitoring Complex Graphs
35 HoursLangGraph serves as a framework for constructing stateful, multi-agent LLM applications as composable graphs, featuring persistent state and precise control over execution.
This instructor-led live training, available online or onsite, targets advanced AI platform engineers, AI DevOps specialists, and ML architects who aim to optimize, debug, monitor, and manage production-grade LangGraph systems.
Upon completing this training, participants will be able to:
- Design and optimize complex LangGraph topologies for enhanced speed, cost-efficiency, and scalability.
- Ensure reliability through retries, timeouts, idempotency, and checkpoint-based recovery mechanisms.
- Debug and trace graph executions, inspect state, and systematically reproduce production issues.
- Instrument graphs with logs, metrics, and traces, deploy them to production, and monitor SLAs and costs.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practice sessions.
- Hands-on implementation within a live lab environment.
Course Customization Options
- To request customized training for this course, please contact us to make arrangements.
Building Coding Agents with Devstral: From Agent Design to Tooling
14 HoursDevstral serves as an open-source framework engineered for the creation and execution of coding agents capable of engaging with codebases, developer utilities, and APIs to elevate engineering efficiency.
This instructor-led, live training session (available online or onsite) targets intermediate to advanced ML engineers, developer-tooling teams, and SREs aiming to design, implement, and refine coding agents utilizing Devstral.
Upon completing this training, participants will possess the ability to:
- Establish and configure Devstral for coding agent development.
- Design agentic workflows tailored for codebase exploration and modification.
- Seamlessly integrate coding agents with developer tools and APIs.
- Apply best practices for secure and efficient agent deployment.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical applications.
- Hands-on implementation within a live-lab environment.
Customization Options
- To arrange customized training for this course, please contact us directly.
Open-Source Model Ops: Self-Hosting, Fine-Tuning and Governance with Devstral & Mistral Models
14 HoursDevstral and Mistral models are open-source AI technologies engineered for flexible deployment, fine-tuning, and scalable integration.
This instructor-led, live training (available online or onsite) is tailored for intermediate to advanced-level ML engineers, platform teams, and research engineers who wish to self-host, fine-tune, and govern Mistral and Devstral models in production environments.
Upon completion of this training, participants will be able to:
- Set up and configure self-hosted environments for Mistral and Devstral models.
- Apply fine-tuning techniques to optimize performance for specific domains.
- Implement versioning, monitoring, and lifecycle governance.
- Ensure security, compliance, and responsible usage of open-source models.
Course Format
- Interactive lectures and discussions.
- Hands-on exercises focused on self-hosting and fine-tuning.
- Live-lab implementation of governance and monitoring pipelines.
Course Customization Options
- To request customized training for this course, please contact us to arrange.
AI Facial Recognition Development for Law Enforcement
21 HoursThis instructor-led, live training in Taiwan (online or onsite) is designed for beginner-level law enforcement personnel seeking to transition from manual facial sketching to utilizing AI tools for building facial recognition systems.
Upon completion of this training, participants will be able to:
- Grasp the fundamental concepts of Artificial Intelligence and Machine Learning.
- Learn the core principles of digital image processing and their application in facial recognition.
- Acquire skills in using AI tools and frameworks to construct facial recognition models.
- Gain practical experience in creating, training, and testing facial recognition systems.
- Understand the ethical considerations and best practices associated with the use of facial recognition technology.
Fiji: Introduction to Scientific Image Processing
21 HoursFiji is a powerful open-source image processing package that bundles ImageJ (a program designed for scientific multidimensional images) along with a comprehensive suite of plugins for scientific image analysis.
In this instructor-led, live training, participants will learn how to leverage the Fiji distribution and its underlying ImageJ program to create robust image analysis applications.
By the end of this training, participants will be able to:
- Use Fiji's advanced programming features and software components to extend ImageJ capabilities
- Stitch large 3D images from overlapping tiles
- Automate the update of a Fiji installation on startup using the integrated update system
- Select from a broad selection of scripting languages to build custom image analysis solutions
- Utilize Fiji's powerful libraries, such as ImgLib, to process large bioimage datasets efficiently
- Deploy applications and collaborate effectively with other scientists on similar projects
Format of the Course
- Interactive lecture and discussion
- Extensive exercises and practical application
- Hands-on implementation in a live-lab environment
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Fiji: Image Processing for Biotechnology and Toxicology
14 HoursThis instructor-led, live training in Taiwan (online or onsite) is aimed at beginner-level to intermediate-level researchers and laboratory professionals who wish to process and analyze images related to histological tissues, blood cells, algae, and other biological samples.
By the end of this training, participants will be able to:
- Navigate the Fiji interface and utilize ImageJ’s core functions.
- Preprocess and enhance scientific images for better analysis.
- Analyze images quantitatively, including cell counting and area measurement.
- Automate repetitive tasks using macros and plugins.
- Customize workflows for specific image analysis needs in biological research.
LangGraph Applications in Finance
35 HoursLangGraph serves as a framework for developing stateful, multi-agent LLM applications through composable graphs that maintain persistent state and provide precise control over execution flow.
This instructor-led, live training (available online or on-site) is designed for intermediate to advanced professionals seeking to design, implement, and operate LangGraph-based financial solutions with robust governance, observability, and compliance.
Upon completion of this training, participants will be capable of:
- Designing finance-specific LangGraph workflows that align with regulatory and audit requirements.
- Integrating financial data standards and ontologies into graph state and tooling.
- Implementing reliability, safety, and human-in-the-loop controls for critical processes.
- Deploying, monitoring, and optimizing LangGraph systems to meet performance, cost, and SLA objectives.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and practical application.
- Hands-on implementation within a live laboratory environment.
Course Customization Options
- To request a customized training session for this course, please contact us to make arrangements.
LangGraph Foundations: Graph-Based LLM Prompting and Chaining
14 HoursLangGraph is a framework designed for constructing graph-structured LLM applications that enable planning, branching, tool integration, memory management, and controllable execution.
This instructor-led, live training (available online or onsite) targets beginner-level developers, prompt engineers, and data practitioners seeking to design and build reliable, multi-step LLM workflows using LangGraph.
By the end of this training, participants will be able to:
- Explain core LangGraph concepts (nodes, edges, state) and determine when to apply them.
- Create prompt chains that branch, invoke tools, and maintain memory.
- Integrate retrieval mechanisms and external APIs into graph workflows.
- Test, debug, and evaluate LangGraph applications for reliability and safety.
Format of the Course
- Interactive lectures and facilitated discussions.
- Guided labs and code walkthroughs conducted in a sandbox environment.
- Scenario-based exercises focused on design, testing, and evaluation.
Course Customization Options
- To request customized training for this course, please contact us to make arrangements.
LangGraph in Healthcare: Workflow Orchestration for Regulated Environments
35 HoursLangGraph facilitates stateful, multi-agent workflows driven by LLMs, offering precise control over execution paths and state persistence. In the healthcare sector, these capabilities are vital for ensuring compliance, interoperability, and the development of decision-support systems that align with clinical workflows.
This instructor-led live training, available online or onsite, targets intermediate to advanced professionals looking to design, implement, and manage LangGraph-based healthcare solutions while navigating regulatory, ethical, and operational challenges.
Upon completion of this training, participants will be able to:
- Design healthcare-specific LangGraph workflows with compliance and auditability in mind.
- Integrate LangGraph applications with medical ontologies and standards (FHIR, SNOMED CT, ICD).
- Apply best practices for reliability, traceability, and explainability in sensitive environments.
- Deploy, monitor, and validate LangGraph applications in healthcare production settings.
Course Format
- Interactive lectures and discussions.
- Hands-on exercises utilizing real-world case studies.
- Implementation practice within a live laboratory environment.
Course Customization Options
- To request customized training for this course, please contact us to arrange it.
LangGraph for Legal Applications
35 HoursLangGraph is a framework designed for constructing stateful, multi-actor LLM applications as composable graphs, featuring persistent state and precise execution control.
This instructor-led, live training (available online or onsite) targets intermediate to advanced professionals seeking to design, implement, and operate LangGraph-based legal solutions with robust compliance, traceability, and governance controls.
Upon completing this training, participants will be able to:
- Design legal-specific LangGraph workflows that preserve auditability and compliance.
- Integrate legal ontologies and document standards into graph state and processing.
- Implement guardrails, human-in-the-loop approvals, and traceable decision paths.
- Deploy, monitor, and maintain LangGraph services in production with observability and cost controls.
Course Format
- Interactive lecture and discussion.
- Extensive exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request customized training for this course, please contact us to make arrangements.
Building Dynamic Workflows with LangGraph and LLM Agents
14 HoursLangGraph is a framework designed for composing graph-structured LLM workflows that support branching, tool use, memory, and controllable execution.
This instructor-led, live training (online or onsite) targets intermediate-level engineers and product teams seeking to combine LangGraph’s graph logic with LLM agent loops to build dynamic, context-aware applications such as customer support agents, decision trees, and information retrieval systems.
By the end of this training, participants will be able to:
- Design graph-based workflows that coordinate LLM agents, tools, and memory.
- Implement conditional routing, retries, and fallbacks for robust execution.
- Integrate retrieval, APIs, and structured outputs into agent loops.
- Evaluate, monitor, and harden agent behavior for reliability and safety.
Course Format
- Interactive lecture and facilitated discussion.
- Guided labs and code walkthroughs in a sandbox environment.
- Scenario-based design exercises and peer reviews.
Customization Options
- To request customized training for this course, please contact us to arrange.
LangGraph for Marketing Automation
14 HoursLangGraph is a graph-based orchestration framework designed to facilitate conditional, multi-step workflows involving large language models (LLMs) and tools, making it an excellent choice for automating and personalizing content pipelines.
This instructor-led live training, available either online or onsite, targets intermediate-level marketers, content strategists, and automation developers who aim to implement dynamic, branching email campaigns and content generation pipelines using LangGraph.
Upon completion of this training, participants will be able to:
- Design graph-structured content and email workflows incorporating conditional logic.
- Integrate LLMs, APIs, and data sources to enable automated personalization.
- Manage state, memory, and context across multi-step campaigns.
- Evaluate, monitor, and optimize workflow performance and delivery outcomes.
Course Format
- Interactive lectures accompanied by group discussions.
- Hands-on labs focused on implementing email workflows and content pipelines.
- Scenario-based exercises covering personalization, segmentation, and branching logic.
Course Customization Options
- To request customized training for this course, please contact us to make arrangements.
Le Chat Enterprise: Private ChatOps, Integrations & Admin Controls
14 HoursLe Chat Enterprise offers a secure, private ChatOps solution that delivers governed and customizable conversational AI capabilities tailored for organizational needs. It supports key enterprise features such as Role-Based Access Control (RBAC), Single Sign-On (SSO), connectors, and integration with enterprise applications.
This instructor-led live training (available online or onsite) is designed for intermediate-level product managers, IT leads, solution engineers, and security/compliance professionals who aim to deploy, configure, and govern Le Chat Enterprise within enterprise settings.
Upon completion of this training, participants will be able to:
- Deploy and configure Le Chat Enterprise securely.
- Implement RBAC, SSO, and compliance-driven controls.
- Integrate Le Chat with enterprise applications and data stores.
- Develop and execute governance and administration playbooks for ChatOps.
Course Format
- Interactive lectures and discussions.
- Extensive hands-on exercises and practice sessions.
- Live-lab implementation for practical learning.
Customization Options
- For customized training arrangements, please contact us to discuss your specific requirements.
Python and Deep Learning with OpenCV 4
14 HoursThis instructor-led, live training in Taiwan (online or onsite) is aimed at software engineers who wish to program in Python with OpenCV 4 for deep learning.
By the end of this training, participants will be able to:
- View, load, and classify images and videos using OpenCV 4.
- Implement deep learning in OpenCV 4 with TensorFlow and Keras.
- Run deep learning models and generate impactful reports from images and videos.
Vision Builder for Automated Inspection
35 HoursThis instructor-led, live training in Taiwan (online or onsite) targets intermediate-level professionals who wish to use Vision Builder AI to design, implement, and optimize automated inspection systems for SMT (Surface-Mount Technology) processes.
By the end of this training, participants will be able to:
- Set up and configure automated inspections using Vision Builder AI.
- Acquire and preprocess high-quality images for analysis.
- Implement logic-based decisions for defect detection and process validation.
- Generate inspection reports and optimize system performance.
