Homework_Week11_Coursera【Machine Learning】AndrewNg、Application: Photo OCR

1 题目Suppose you are running a sliding window detector to find text in images. Your input images are 1000x1000 pixels. You will run your sliding windows detector at two scales, 10x10 and 20x20 (i.e., you will run your classifier on lots of 10x10 patches to decide if they contain text or not; and also on lots of 20x20 patches), and you will “step” your detector by 2 pixels each time. About how many times will you end up running your classifier on a single 1000x1000 test set image？

解析

做了一个滑动窗口检测器来找出图片中的文本。你的输入图片是10001000像素的。两种款式的检测器，1010和2020。步长为2像素。你的分类器多少次能跑完10001000的测试图片？
500500=250000这是1010，步长为2走过的。
在此基础上double应该选d 500000

答案

D

2 题目 Suppose that you just joined a product team that has been developing a machine learning application, using m = 1,000m=1,000 training examples. You discover that you have the option of hiring additional personnel to help collect and label data. You estimate that you would have to pay each of the labellers $10 per hour, and that each labeller can label 4 examples per minute. About how much will it cost to hire labellers to label 10,000 new training examples?

解析

训练样本m=1000，让人标签收集数据。每个标签工人一小时10元，每个标签工人每分钟标记4个样本。一小时可以标记240个样本
所以标记10000个新训练样本的话。就需要10000/240=41.6约等于42个小时大概就是400了

答案

A

3 题目 What are the benefits of performing a ceiling analysis? Check all that apply.

解析

做ceiling 分析有什么益处呢
B它会给我们关于哪一个组件的信息。如果改进了，是最有可能对最终系统的表现有一个非常大的影响，这个完全正确。选择
The ceiling analysis gives us this information by comparing the baseline overall system performance with ground truth results from each component of the pipeline
C能帮助我们知名 确切的系统组件可能不会值得很多工作区改进，因为它占比重很小，正确。选择
An unpromising component will have little effect on overall performance when it is replaced with ground truth.
D 这个分析不会告诉我们哪个是最有希望的算法，应该时只能知道这个组件所占的比重

答案

BC

4 题目Suppose you are building an object classifier, that takes as input an image, and recognizes that image as either containing a car (y=1y=1) or not (y=0y=0). For example, here are a positive example and a negative example

解析

正例是汽车的图片，结果也是需要更多的正例
A运用各种图像处理方法来扩充训练集可以
These geometric distortions are likely to occur in real-world images, so they are a good way to generate additional data.
其余从应用场景来看意义不大

答案

A

5 题目Suppose you have a PhotoOCR system, where you have the following pipeline

解析

A 文字识别部分可以带来的提升最大
没有错
B 天花板分析，都需要各个部件的最好情况，环环相扣，对
C 错，最后一part是最重要，最关键的，提升最多打的
D 错，不是72就是有最大的潜力空间，而是要看他提升百分之2的效果，而最后一part和倒数第二part差值更大

答案

AB