Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week3-编程作业

最新推荐文章于 2021-08-10 23:33:02 发布

原创

最新推荐文章于 2021-08-10 23:33:02 发布 · 601 阅读

1 ·

CC 4.0 BY-SA版权

本文介绍了Coursera上吴恩达深度学习课程中关于卷积神经网络的第三周内容——目标检测，特别是使用YOLO算法进行汽车检测。YOLO通过一次前向传播即可做出预测，输出包含边界框和识别类别的列表。文章详细讲解了模型细节、阈值过滤和非极大值抑制等步骤，帮助理解YOLO如何从(19, 19, 5, 85)维度的输出中筛选出准确的检测结果。" 28598401,2276703,Unity 3D教程：ScrollView控件详解,"['Unity', '游戏开发', 'UI设计', '脚本', '互联网']

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

本文章内容：

Coursera吴恩达深度学习课程，

第四课：卷积神经网络（Convolutional Neural Networks）

第三周：目标检测（Object detection）

编程作业

Autonomous driving - Car detection

learn to:

Use object detection on a car detection dataset
Deal with bounding boxes

1 - Problem Statement

You've gathered all these images into a folder and have labelled them by drawing bounding boxes around every car you found.

If you have 80 classes that you want YOLO to recognize, you can represent the class label cc either as an integer from 1 to 80, or as an 80-dimensional vector (with 80 numbers) one component of which is 1 and the rest of which are 0.

2 - YOLO

YOLO ("you only look once") is a popular algoritm because it achieves high accuracy while also being able to run in real-time. This algorithm "only looks once" at the image in the sense that it requires only one forward propagation pass through the network to make predictions.

After non-max suppression, it then outputs recognized objects together with the boundi