|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/advanced-computer-vision-transfer-learning-with-tensorflow/
课程评论：没有评论
课程名称：深度学习：高级计算机视觉（目标检测及更多！） 课程概述：本课程将教授如何使用预训练模型以及如何在Google Colab上使用自定义数据集自行训练模型。课程是设置TensorFlow目标检测API、迁移学习等内容的完整指南。与之前的课程相比，本课程涵盖的材料更加丰富多样。我们将从Colab入手，这将帮助我们利用Google提供的免费GPU来训练模型。 我们将从基础的卷积神经网络（CNN）架构逐步过渡到现代的、创新的架构，例如ResNet和Inception。课程将详细了解使用TensorFlow目标检测API和YOLO算法的目标检测模块。此外，我们还将研究一个最先进的算法，即RESNET和MobileNetV2，这些算法比其前身更快、更准确。 课程的亮点包括： - 提供在Colab GPU上训练模型的全动手实践经验。 - 课程内容将重点关注高层次的构建模块，而非详尽探讨CNN的内部运作，几乎没有数学内容。 - 大部分代码将使用Keras编写，以简化繁琐的操作，虽然对高级学生可能会提供一些可选的复杂低层代码练习。 建议先决条件： - 了解如何使用某个库（最好是Python）构建、训练和使用CNN。 - 理解卷积和神经网络背后的基本理论概念。 - 拥有一定的数据科学和Numpy堆栈的Python编程技能。 适合人群： - 希望将计算机视觉和深度学习知识提升到新水平的学生和专业人士。 - 想学习如SSD和YOLO等目标检测算法的人士。 - 希望学习如何编写神经风格迁移代码的人。 - 希望利用迁移学习缩短训练时间、快速构建最先进计算机视觉网络的人。 - 对计算机视觉感兴趣的初学者。 希望大家都能在课堂上收获满满，期待与你们的见面！
Latest update: I will show you both how to use a pretrained model and how to train one yourself with a custom dataset on Google Colab.This course is a complete guide for setting up TensorFlow object detection api, Transfer learning and a lot moreI think what you'll find is that, this course is so entirely different from the previous one, you will be impressed at just how much material we have to cover.Here is the details about the project.Here we will star from colab understating because that will help to use free GPU provided by google to train up our model.We're going to bridge the gap between the basic CNN architecture you already know and love, to modern, novel architectures such as ResNet, and Inception.We will understand object detection modules in detail using both tensorflow object detection api as well as YOLO algorithms.We'll be looking at a state-of-the-art algorithm called RESNET and MobileNetV2 which is both faster and more accurate than its predecessors.One best thing is you will understand the core basics of CNN and how it converts to object detection slowly.I hope you're excited to learn about these advanced applications of CNNs Yolo and Tensorflow, I'll see you in class!AMAGING FACTS:· This course give's you full hand's on experience of training models in colab GPU.· Instead of focusing on the detailed inner workings of CNNs (which we've already done), we'll focus on high-level building blocks. The result? Almost zero math.· Another result? No complicated low-level code such as that written in Tensorflow, Theano,YOLO, or PyTorch (although some optional exercises may contain them for the very advanced students). Most of the course will be in Keras which means a lot of the tedious, repetitive stuff is written for you.Suggested Prerequisites:· Know how to build, train, and use a CNN using some library (preferably in Python)· Understand basic theoretical concepts behind convolution and neural networks· Decent Python coding skills, preferably in data science and the Numpy StackWho this course is for:· Students and professionals who want to take their knowledge of computer vision and deep learning to the next level· Anyone who wants to learn about object detection algorithms like SSD and YOLO· Anyone who wants to learn how to write code for neural style transfer· Anyone who wants to use transfer learning· Anyone who wants to shorten training time and build state-of-the-art computer vision nets fast· Anyone who is starting with computer vison
