# coursera-斯坦福-机器学习-吴恩达-第11周笔记-ORC系统

## 1图像ORC

### 1.1问题描述

1. 第一 我想向你展示 一个复杂的机器学习系统 是如何被组合起来的
2. 第二 我想介绍一下 机器学习流水线（machine learning pipeline）的有关概念， 以及在决定下一步做什么时， 如何分配资源。
3. 最后,通过介绍照片OCR问题 的机会来告诉你， 机器学习的诸多 有意思的想法和理念 。其中之一是如何将机器学习 应用到计算机视觉问题中， 第二是有关 人工数据合成（artificial data synthesis）的概念。

OCR技术 主要解决的问题是让计算机 读出照片中拍到的文字信息。

OCR pipeline的意思主要是把一个ML系统分割为几个连续的部分，如下图：

### 1.2 滑动窗(sliding windows)

1. 第一步通过滑动窗在图像中找出有字母的部分，然后把他变白方便下一步提取。

1. 分割字母，使用滑动窗在上一部提取的像素中提取分割的部分。

—–>
3. 第三步，字母分类。

### 1.3获取大量的图片

Getting Lots of Data and Artificial Data获取大量数据和人工合成数据。

idea2: take an existing example and and introducing distortions通过引入扭曲合成数据

### 1.4分析

Ceiling Analysis：What Part of the Pipeline to Work on Next 上限分析-接下来工作重心应放在pipeline哪个部分。

## 2复习 quiz

1. 第 1 个问题
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?答案：B

• 1,000,000
• 500,000
• 100,000
• 250,000
2. 第 2 个问题 Suppose that you just joined a product team that has been developing a machine learning application, using m=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?答案：D •$600
• $250 •$10,000
• \$400
3. 第 3 个问题What are the benefits of performing a ceiling analysis? Check all that apply. 答案：AB

• It can help indicate that certain components of a system might not be worth a significant amount of work improving, because even if it had perfect performance its impact on the overall system may be small.
• It helps us decide on allocation of resources in terms of which component in a machine learning pipeline to spend more effort on.
• It is a way of providing additional training data to the algorithm.
• If we have a low-performing component, the ceiling analysis can tell us if that component has a high bias problem or a high variance problem.
4. Suppose you are building an object classifier, that takes as input an image, and recognizes that image as either containing a car (y=1) or not (y=0). For example, here are a positive example and a negative example: After carefully analyzing the performance of your algorithm, you conclude that you need more positive (y=1) training examples. Which of the following might be a good way to get additional positive examples?答案：A

• Apply translations, distortions, and rotations to the images already in your training set.
• Select two car images and average them to make a third example.
• Take a few images from your training set, and add random, gaussian noise to every pixel.
• Make two copies of each image in the training set; this immediately doubles your training set size.
5. Suppose you have a PhotoOCR system, where you have the following pipeline:
You have decided to perform a ceiling analysis on this system, and find the following:Which of the following statements are true?答案：

• If the text detection system was trained using gradient descent, running gradient descent for more iterations is unlikely to help much.
• If we conclude that the character recognition’s errors are mostly due to the character recognition system having high variance, then it may be worth significant effort obtaining additional training data for character recognition.
• We should dedicate significant effort to collecting additional training data for the text detection system.
• The least promising component to work on is the character recognition system, since it is already obtaining 100% accuracy.

03-22 1633
07-04 1036
02-19 70万+
01-11
05-23
06-09