CANN SDK for Computer Vision and NLP Pipelines Training Course
The CANN SDK (Compute Architecture for Neural Networks) offers robust deployment and optimization capabilities for real-time AI applications in computer vision and NLP, particularly when targeting Huawei Ascend hardware.
Designed as an instructor-led, live training experience available online or onsite, this course is tailored for intermediate-level AI practitioners looking to build, deploy, and optimize vision and language models for production environments using the CANN SDK.
Upon completing this training, participants will be equipped to:
- Deploy and fine-tune CV and NLP models leveraging CANN and AscendCL.
- Utilize CANN tools to convert models and seamlessly integrate them into live pipelines.
- Enhance inference performance for tasks such as object detection, classification, and sentiment analysis.
- Construct real-time CV/NLP pipelines suitable for edge or cloud-based deployment scenarios.
Course Format
- Engaging lectures paired with live demonstrations.
- Practical hands-on labs focused on model deployment and performance profiling.
- Designing live pipelines using authentic CV and NLP use cases.
Customization Options
- To arrange a customized version of this training, please get in touch with our team.
Course Outline
Introduction to CV/NLP Deployment with CANN
- The AI model lifecycle, from training through to deployment.
- Critical performance factors for real-time CV and NLP applications.
- An overview of CANN SDK tools and their significance in model integration.
Preparing CV and NLP Models
- Exporting models from PyTorch, TensorFlow, and MindSpore.
- Managing model inputs and outputs for image and text processing tasks.
- Converting models to OM format using ATC.
Deploying Inference Pipelines with AscendCL
- Executing CV/NLP inference via the AscendCL API.
- Implementing preprocessing steps, including image resizing, tokenization, and normalization.
- Handling postprocessing outputs such as bounding boxes, classification scores, and generated text.
Performance Optimization Techniques
- Profiling CV and NLP models using CANN tools.
- Minimizing latency through mixed-precision and batch tuning strategies.
- Efficiently 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 environments.
- Constructing live video analytics pipelines on Ascend 310.
NLP Use Cases
- Case study: Sentiment analysis and intent detection.
- Case study: Document classification and summarization.
- Integrating real-time NLP 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.
- Foundational knowledge 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.
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 powerful framework for constructing stateful, multi-actor LLM applications. It enables the creation of composable graphs with persistent state, granting precise control over execution flows.
This instructor-led, live training—available both online and onsite—is designed specifically for advanced AI platform engineers, DevOps specialists in AI, and ML architects. The goal is to equip professionals with the skills to optimize, debug, monitor, and operate production-grade LangGraph systems.
Upon completing this training, participants will possess the ability to:
- Design and optimize complex LangGraph topologies to enhance speed, reduce costs, and improve scalability.
- Build robust reliability mechanisms by implementing retries, timeouts, idempotency, and checkpoint-based recovery.
- Systematically debug and trace graph executions, inspect state variables, and reliably reproduce production issues.
- Instrument graphs with comprehensive logs, metrics, and traces, deploy them to production, and effectively monitor SLAs and operational costs.
Course Format
- Engaging interactive lectures and open discussions.
- Extensive exercises and practical applications.
- Hands-on implementation within a live-lab environment.
Customization Options
- For tailored training solutions, please reach out to us to discuss your specific requirements.
Building Coding Agents with Devstral: From Agent Design to Tooling
14 HoursDevstral is an open-source framework designed to facilitate the creation and execution of coding agents. These agents can engage with codebases, developer tools, and APIs to boost engineering productivity.
This live, instructor-led training, available online or onsite, is tailored for intermediate to advanced ML engineers, developer-tooling teams, and SREs who aim to design, implement, and optimize coding agents using Devstral.
Upon completion of this training, participants will be equipped to:
- Configure and set up Devstral for coding agent development.
- Create agentic workflows for exploring and modifying codebases.
- Connect 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 application.
- Hands-on implementation within a live-lab environment.
Course Customization Options
- To request a customized version of this training, please reach out to us for arrangements.
Open-Source Model Ops: Self-Hosting, Fine-Tuning and Governance with Devstral & Mistral Models
14 HoursDevstral and Mistral models represent open-source AI technologies engineered for flexible deployment, precise fine-tuning, and scalable integration.
This instructor-led, live training—available online or on-site—is tailored for intermediate to advanced machine learning engineers, platform teams, and research engineers seeking to self-host, fine-tune, and govern Mistral and Devstral models within production environments.
Upon completing this training, participants will be equipped to:
- Establish and configure self-hosted environments for Mistral and Devstral models.
- Implement fine-tuning techniques to enhance domain-specific performance.
- Deploy versioning, monitoring, and lifecycle governance frameworks.
- Safeguard security, compliance, and the responsible utilization of open-source models.
Course Format
- Interactive lectures and discussions.
- Practical exercises focused on self-hosting and fine-tuning.
- Live-lab implementation of governance and monitoring pipelines.
Customization Options
- Interested in tailoring this course to your specific needs? Please reach out to us to discuss customization arrangements.
AI Facial Recognition Development for Law Enforcement
21 HoursThis live, instructor-led training held in Thailand (either online or on-site) is tailored for entry-level law enforcement officers seeking to move beyond manual facial sketching and embrace AI tools for developing facial recognition systems.
By the conclusion of this program, participants will be able to:
- Comprehend the foundational principles of Artificial Intelligence and Machine Learning.
- Understand the basics of digital image processing and its application in facial recognition.
- Build skills in deploying AI tools and frameworks to construct facial recognition models.
- Accumulate hands-on experience in building, training, and evaluating facial recognition systems.
- Address ethical considerations and adhere to best practices in the deployment of facial recognition technology.
Fiji: Image Processing for Biotechnology and Toxicology
14 HoursThis practical training program on Thailand delves into the fundamentals of Fiji and ImageJ for biological research. Participants will develop practical competencies in image preprocessing, quantitative analysis, and macro automation, enabling them to streamline workflows for histological tissues, cells, and other samples while ensuring reproducible results.
LangGraph Applications in Finance
35 HoursLangGraph Foundations: Graph-Based LLM Prompting and Chaining
14 HoursLangGraph serves as a robust framework for engineering graph-structured LLM applications, facilitating complex capabilities such as planning, conditional branching, tool utilization, memory retention, and controlled execution flows.
This instructor-led session, available online or onsite, is tailored for beginner-level developers, prompt engineers, and data professionals seeking to construct dependable, multi-stage LLM workflows with LangGraph.
Upon completion of this program, participants will be equipped to:
- Articulate fundamental LangGraph components, including nodes, edges, and state, and identify optimal use cases for each.
- Construct prompt chains that dynamically branch, invoke external tools, and retain contextual memory.
- Seamlessly integrate retrieval mechanisms and external APIs into graph-based workflows.
- Implement rigorous testing, debugging, and evaluation protocols to ensure application reliability and safety.
Delivery Methodology
- Engaging lectures complemented by facilitated group discussions.
- Supervised laboratories and detailed code reviews within a secure sandbox environment.
- Practical, scenario-driven exercises focused on architecture design, testing, and performance evaluation.
Tailored Training Options
- For specific customization requests regarding this curriculum, please reach out to our team to discuss arrangements.
LangGraph in Healthcare: Workflow Orchestration for Regulated Environments
35 HoursLangGraph for Legal Applications
35 HoursBuilding Dynamic Workflows with LangGraph and LLM Agents
14 HoursLangGraph for Marketing Automation
14 HoursLangGraph serves as a graph-based orchestration framework designed to facilitate conditional, multi-step workflows involving LLMs and various tools. This makes it an excellent choice for streamlining and tailoring content pipelines.
Delivered as a live, instructor-led session (either online or onsite), this training is tailored for intermediate-level marketers, content strategists, and automation developers looking to deploy dynamic, branching email campaigns and content generation pipelines using LangGraph.
Upon completing this training, participants will gain the ability to:
- Construct graph-structured workflows for content and email that incorporate conditional logic.
- Seamlessly integrate LLMs, APIs, and diverse data sources to drive automated personalization.
- Effectively manage state, memory, and context across complex, multi-step campaigns.
- Assess, monitor, and refine workflow performance to enhance delivery outcomes.
Course Format
- Engaging interactive lectures complemented by group discussions.
- Practical hands-on labs focused on implementing email workflows and content pipelines.
- Scenario-based exercises covering personalization, segmentation, and branching logic.
Customization Options
- Interested in a tailored training experience? Please contact us to discuss custom arrangements for this course.
Le Chat Enterprise: Private ChatOps, Integrations & Admin Controls
14 HoursLe Chat Enterprise is a secure, private ChatOps platform that delivers governed and customizable conversational AI capabilities for organizations. It supports essential 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 both online and onsite, is designed for intermediate-level product managers, IT leads, solution engineers, and security/compliance professionals. The course focuses on deploying, configuring, and governing Le Chat Enterprise within enterprise environments.
Upon completing this training, participants will be equipped to:
- Configure and deploy Le Chat Enterprise securely.
- Implement RBAC, SSO, and compliance-centric controls.
- Connect Le Chat with enterprise applications and data repositories.
- Create and execute governance and administrative playbooks for ChatOps.
Course Structure
- Engaging lectures paired with open discussions.
- Extensive practical exercises and practice sessions.
- Hands-on implementation within a live laboratory environment.
Tailored Training Options
- For customized training requirements, please reach out to us to discuss arrangements.
Cost-Effective LLM Architectures: Mistral at Scale (Performance / Cost Engineering)
14 HoursProductizing Conversational Assistants with Mistral Connectors & Integrations
14 HoursMistral AI provides an open-source platform designed to help organizations develop and embed conversational assistants into both enterprise operations and customer-facing interactions.
Delivered as a live, instructor-led session (available online or onsite), this program targets product managers, full-stack developers, and integration engineers with beginner to intermediate experience. The focus is on designing, integrating, and scaling conversational assistants by leveraging Mistral’s ecosystem of connectors and integrations.
Upon completion, participants will be equipped to:
- Connect Mistral’s conversational models with enterprise systems and SaaS applications.
- Apply retrieval-augmented generation (RAG) to ensure accurate, context-grounded responses.
- Develop effective UX patterns for chat assistants used internally and externally.
- Integrate these assistants into live product workflows for practical, real-world scenarios.
Course Format
- Interactive lectures and guided discussions.
- Practical, hands-on integration exercises.
- Live lab sessions dedicated to building conversational assistants.
Customization Options
- For tailored training requirements, please contact us to discuss bespoke arrangements.
Vision Builder for Automated Inspection
35 HoursThis live, instructor-led training is conducted in Thailand (either online or onsite) and is designed for intermediate-level professionals seeking to utilize Vision Builder AI to design, build, and optimize automated inspection systems for SMT (Surface-Mount Technology) operations.
By the end of the program, learners will be equipped to:
- Set up and configure automated inspection tasks via Vision Builder AI.
- Acquire and preprocess high-quality images for analytical purposes.
- Implement logic-driven decisions for identifying defects and verifying process integrity.
- Generate comprehensive inspection reports and enhance system efficiency.