课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

时间:2023-06-09 11:21:56

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

【解释】

tree的两个bounding boxes 都要保留,因为交并比小于0.5;car 0.73保留;pedestrain 0.98保留;motorcycle 0.58保留。一共5个。

课程四(Convolutional Neural Networks),第三 周(Object detection) —— 1.Practice questions:Detection algorithms

【解释】

5个anchor box, 一个anchor box 对应(1+4+20)个标签,所以output volume 是 19*19*5*25