|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/yolo-masterclass-deep-learning-computer-vision-course/
课程评论：没有评论
**课程名称：YOLOv7、YOLOv8、YOLOv9、YOLOv10、YOLOv11 深度学习课程** **课程概述：** 本课程是一门集五大前沿目标检测模型（YOLOv7、YOLOv8、YOLOv9、YOLOv10、YOLOv11）于一体的深度学习课程。YOLO模型系列以其**速度快**和**高精度**而闻名，YOLOv11是最新版本，而YOLOv8是最受欢迎的版本。 **课程内容亮点：** 1. **快速实践：** 从零开始运行YOLOv7至YOLOv11模型，在10分钟内实现对80类物体的检测。 2. **YOLO演进：** 深入了解YOLO从v1到v8的发展历程。 3. **性能对比：** 通过实验验证YOLO与其他深度学习模型的实际性能差异。 4. **优势解析：** 阐述YOLO相较于其他深度学习模型的优势。 5. **版本更新：** 详细介绍YOLOv7和YOLOv8的新特性。 6. **基础知识：** 讲解人工神经网络（神经元、感知器、前馈网络、隐藏层、全连接层等）和卷积神经网络（卷积过程、池化层、展平操作等）的工作原理。 7. **激活函数：** 学习Sigmoid、tanh、ReLU、Leaky ReLU、Mish和SiLU等激活函数。 8. **计算机视觉任务：** 涵盖图像分类、目标定位、目标检测、实例分割和语义分割等多种计算机视觉问题。 9. **模型架构：** 详细解析YOLOv7、YOLOv8、YOLOv9、YOLOv10和YOLOv11的底层架构。 10. **数据集操作：** 包括数据集查找、使用LabelImg进行数据标注、数据集自动划分。 11. **模型安装与训练：** 提供YOLOv7至YOLOv11的详细安装步骤，并指导学员在自定义数据集上进行模型训练。 12. **结果可视化：** 利用Tensorboard可视化训练过程。 13. **模型测试：** 在图像、视频以及实时摄像头流上测试训练好的YOLO模型。 14. **高级功能：** * YOLOv7：姿态估计、实例分割。 * YOLOv8：实例分割、目标跟踪。 * YOLOv11：目标检测、目标跟踪、实例分割、图像分类。 15. **实战项目：** 涵盖多个真实世界应用项目，包括： * 基于YOLOv7和YOLOv8的鲁棒口罩检测器。 * YOLOv8天气分类应用。 * 咖啡叶病害分割应用。 * YOLOv7深蹲计数器。 * 基于YOLOv9 + Streamlit的车辆计数与速度估计Web应用。 * 基于YOLOv10 + Bytetrack的牛计数器。 * 基于YOLOv11 + Bytetrack的行人计数器。 * YOLOv11 X射线图像分类。 **学习目标：** 本课程旨在帮助学员掌握先进的目标检测技术，能够独立完成从数据准备到模型部署的整个流程，并能将YOLO模型应用于各种实际问题中。
Welcome to the YOLOv7, YOLOv8, YOLOv9, YOLOv10, & YOLOv11 Deep Learning Course, a 5 COURSES IN 1. YOLOv7, YOLOv8, YOLOv9, YOLOv10, and YOLOv11 are the current five best object detection deep learning models. They are fast and very accurate. YOLOv11 is the latest version of YOLO whereas YOLOv8 is the most popular YOLO version of all.What will you learn:1. How to run, from scratch, a YOLOv7, YOLOv8, YOLOv9, YOLOv10 & YOLO11 program to detect 80 types of objects in < 10 minutes.2. YOLO evolution from YOLO v1 to YOLO v83. What is the real performance comparison, based on our experiment4. What are the advantages of YOLO compares to other deep learning models5. What's new in YOLOv7 and YOLOv86. How artificial neural networks work (neuron, perceptron, feed-forward network, hidden layers, fully connected layers, etc)7. Different Activation functions and how they work (Sigmoid, tanh, ReLu, Leaky ReLu, Mish, and SiLU)8. How convolutional neural networks work (convolution process, pooling layer, flattening, etc)9. Different computer vision problems (image classification, object localization, object detection, instance segmentation, semantic segmentation)10. YOLOv7, YOLOv8, YOLOv9, YOLOv10, and YOLO11 architecture in detail11. How to find the dataset12. How to perform data annotation using LabelImg13. How to automatically split a dataset14. A detailed step-by-step YOLOv7, YOLOv8, YOLOv9, YOLOv10, and YOLOv11 installation15. Train YOLOv7, YOLOv8, YOLOv9, YOLOv10, and YOLO 11 on your own custom dataset16. Visualize your training result using Tensorboard17. Test the trained YOLOv7, YOLOv8, YOLOv9, YOLOv10, and YOLO11 models on image, video, and real-time using webcam.18. YOLOv7 New Features: Pose Estimation19. YOLOv7 New Features: Instance Segmentation20. YOLOv8 New Features: Instance Segmentation & Object Tracking21. YOLO11: Object Detection, Object Tracking, Instance Segmentation, & Image Classification22. Real World Project #1: Robust mask detector using YOLOv7 and YOLOv823. Real World Project #2: Weather YOLOv8 classification application24. Real World Project #3: Coffee Leaf Diseases Segmentation application25. Real World Project #4: YOLOv7 Squat Counter application26. Real World Project #5: Various Vehicle Counter and Speed Estimation Web App with Cool Dashboard using YOLOv9 + Streamlit 27. Real World Project #6: Cattle Counter using YOLOv10 + Bytetrack28. Real World Project #7: Person Counter using YOLOv11 + Bytetrack29. Real World Project #8: X-Ray Image Classification using YOLO11
