|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/ai-4-everyone-dive-into-modern-ai-with-llama-31-and-gemini/
课程评论：没有评论
课程名称：人人皆可AI：构建生成式AI与计算机视觉应用 课程概述： 欢迎参加“人人皆可AI：构建生成式AI与计算机视觉应用”课程。本课程旨在帮助所有希望释放AI潜力的人，无论你是非技术专业人士还是有志的AI开发者。在这个课程中，您将学习如何自动化任务、创建强大应用程序，并与AI模型互动，无需深入的编程知识。即便是初学者，这门课程也将指导您构建实用的AI工具，简化日常工作。 您将学习的内容： 1. **使用AI自动化任务**：掌握如何撰写专业邮件、总结YouTube视频、创造令人惊叹的图像和解释复杂图表，所有这些都无需编写一行代码。 2. **开发AI驱动的应用程序**：使用Python和Streamlit创建现实世界的应用程序，例如： - 根据需求生成食谱的食谱生成器。 - 根据营养需求组织餐食的AI膳食规划器。 - 将视频转换为博客文章的YouTube视频到博客转换器。 - 高效组织和分类文档的PDF整理工具。 3. **文档和数据库交互**：探索如何与文档聊天并提取信息，包括： - 查询SQL数据库的文本到SQL LLM应用。 - 提取多语言发票文字的多语言发票提取器。 - 无需训练或微调大型语言模型即可与PDF文件进行互动和管理的PDF问答与整理。 - 学习使用LangChain代理与CSV和JSON文件进行问答的高级AI技术。 4. **提示工程**：学习如何有效地与AI模型（如Llama 3.1和Gemini）沟通，掌握提示工程技巧，以便为各种任务提供准确的输出。 5. **OpenCV功能**：学习如何读取图像、视频和实时网络摄像头视频流，探索各种OpenCV功能，包括： - 将图像转换为灰度 - 模糊图像 - 检测图像中的边缘 - 对图像进行膨胀和侵蚀 - 裁剪和调整图像大小 - 在图像上绘制形状（线条、矩形、圆形）并添加文字 - 透视扭曲 - 检测轮廓和形状 - 使用OpenCV创建文档扫描仪等AI应用。 6. **利用AI进行手势数学**：使用手势生成绘画，该绘画将被AI模型处理以解决数学问题。您还可以向AI模型询问与绘画相关的问题。 7. **实时手势控制转盘**：学习如何使用OpenCV和MediaPipe库创建一个实时手势控制的转盘。 通过本课程，您将获得实用的技能，以便在各个领域中实施AI解决方案。
Welcome to "AI 4 Everyone: Build Generative AI & Computer Vision Apps"-a comprehensive course designed for anyone looking to unlock the power of AI, whether you are a non-technical professional, or an aspiring AI developer.In this course, you'll learn how to automate tasks, create powerful applications, and interact with AI models without needing extensive coding knowledge. Even if you're a beginner, this course will guide you through building practical AI tools that simplify your day-to-day work.What You Will Learn:Automating Tasks with AI: Learn how to write professional emails, summarize YouTube videos, create stunning images, and explain complex graphs-all without writing a single line of code.Developing AI-Powered Applications: Using Python and Streamlit, you'll create real-world applications like:A Recipe Generator that creates recipes based on your requests.An AI Meal Planner that organizes your meals based on nutritional needs.A YouTube Video to Blog Converter that transforms videos into blog posts.A PDF Sorter to efficiently organize and categorize documents.Document & Database Interactions: Discover how to chat with and extract information from documents, including:Text-to-SQL LLM Applications that query SQL databases.Multi-language Invoice Extractor that extracts text from invoices in various languages.PDF Q & A and sorting: Interact with your PDF files and manage them without the need for training or fine-tuning Large Language Models.LangChain Agents for CSV & JSON: Learn advanced AI techniques, like using LangChain agents to interact with CSV and JSON files for Q & A purposes.Prompt Engineering: Learn how to effectively communicate with AI models like Llama 3.1 and Gemini by learning prompt engineering techniques that give precise outputs for a variety of tasks.OpenCV Functions:Learn how to read images, videos, and live webcam feeds using OpenCV. Explore various OpenCV functions, including:Converting an image to grayscaleBlurring an imageDetecting edges in an imagePerforming dilation and erosion on imagesCropping and resizing imagesDrawing shapes on images (lines, rectangles, circles) and adding textWarping perspectiveDetecting contours and shapesAdditionally, create AI applications with OpenCV, such as a Document Scanner.Math with Gesture Using AI: Use your hand to create a drawing, which will be processed by an AI model to solve math problem. You can also ask the AI model questions about the drawing.Real-Time Gesture-Controlled Spin Wheel with OpenCV & MediaPipe: Learn how to create a real-time hand gesture-controlled spin wheel using the OpenCV and MediaPipe libraries.
