|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/build-face-recognition-app-using-machine-learning-in-flask/
课程评论：没有评论
课程名称：机器学习面部识别与Flask应用部署 课程概述： 本课程旨在教授如何使用机器学习技术开发和部署基于面部识别的Web应用。仅掌握机器学习或深度学习的知识远不足以满足在Web上开发和部署应用的需求，您还需了解流水线架构的创建、客户端的调用、HTTP请求等内容。在开发过程中，您可能会遇到许多挑战。本课程的结构使您能够从零开始开发面部识别的Web应用。 您将学习到： - Python编程 - 使用OpenCV进行图像处理 - 图像数据预处理 - 图像数据分析 - 使用主成分分析（PCA）提取特征（如Eigenfaces） - 基于支持向量机的面部识别分类模型 - 流水线模型的构建 - Flask框架的使用（包括Jinja模板、HTML、CSS和HTTP方法） - 开发面部识别Web应用 - 将Flask应用部署到云平台（如Heroku） 在课程中，您将学习图像处理技术及其背后的概念，并进行必要的图像分析与预处理步骤。我们将从预处理的图像中提取特征，即通过主成分分析计算的特征图像。通过这些特征图像，我们将训练机器学习模型，并在部署之前对模型进行测试。在此过程中，我们将通过网格搜索方法调优超参数，以获得最佳结果。 当机器学习模型准备就绪后，我们将学习并开发一个Flask Web服务器接口，前端使用HTML、CSS和Bootstrap进行渲染，后端用Python编写。最后，我们将完成面部识别项目，将机器学习模型整合到Flask应用中。
MLOPs: AI based Face Recognition Web App in Flask & DeployFace recognition is one of the most widely used in my application. If at all you want to develop and deploy the application on the web only knowledge of machine learning or deep learning is not enough. You also need to know the creation of pipeline architecture and call it from the client-side, HTTP request, and many more. While doing so you might face many challenges while developing the app. This course is structured in such a way that you can able to develop the face recognition based web app from scratch.What you will learn?PythonImage Processing with OpenCVImage Data PreprocessingImage Data AnalysisEigenfaces with PCAFace Recognition Classification Model with Support Vector MachinesPipeline ModelFlask (Jinja Template, HTML, CSS, HTTP Methods)Develop Face Recognition WebDeploy Flask App in Cloud (Heroku)You will learn image processing techniques in OpenCV and the concepts behind the images. We will also do the necessary image analysis and required preprocessing steps for images. For the preprocess images, we will extract features from the images, ie. computing Eigen images using principal component analysis. With Eigen images, we will train the Machine learning model and also learn to test our model before deploying, to get the best results from the model we will tune with the Grid search method for the best hyperparameters.Once our machine learning model is ready, will we learn and develop a web server gateway interphase in flask by rendering HTML CSS and bootstrap in the frontend and in the backend written in Python. Finally, we will create the project on the Face Recognition project by integrating the machine learning model to Flask App.
