{
  "id": 7168,
  "title": "Converting the images to Grayscale ?",
  "url": "/competitions/cifar-10/discussion/7168",
  "author_name": "aadesh neupane",
  "post_date": "2014-02-22T13:17:31.527000",
  "votes": 0,
  "comment_count": 3,
  "views": 3965,
  "content": "<p>All the images in the dataset are in color. Do we need to convert the images to grayscale. As most of the information is lost while converting to grayscale, how can we attain maximum accuracy.</p>",
  "messages": [
    {
      "id": 53288,
      "postDate": "2014-09-07T15:14:17.230Z",
      "content": "<p>hi guys !!&nbsp; converting to gray scale&nbsp; wouldn't help, in contrast it would penalize the result due to fact that for &quot;natural images&quot; ( as those in this data set )&nbsp; , the color is very&nbsp; important, take a look at this link to learn more further :&nbsp; http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial&nbsp;&nbsp;&nbsp; look at section : Preprocessing: PCA and Whitening !&nbsp;</p>",
      "votes": 4
    },
    {
      "id": 52114,
      "postDate": "2014-08-17T18:27:27.113Z",
      "content": "<p>If you do not want to utilize the color information in the images, yes you can convert to grayscale, which is nothing but simply averaging the RGB values for every pixel.&nbsp;</p>",
      "votes": 2
    },
    {
      "id": 39250,
      "postDate": "2014-02-22T13:17:31.527Z",
      "content": "<p>All the images in the dataset are in color. Do we need to convert the images to grayscale. As most of the information is lost while converting to grayscale, how can we attain maximum accuracy.</p>"
    },
    {
      "id": 643259,
      "postDate": "2019-10-07T10:38:29.460Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 53288,
      "author_name": "Junior Teudjio",
      "author_url": "",
      "post_date": "2014-09-07T15:14:17.230000",
      "content": "<p>hi guys !!&nbsp; converting to gray scale&nbsp; wouldn't help, in contrast it would penalize the result due to fact that for &quot;natural images&quot; ( as those in this data set )&nbsp; , the color is very&nbsp; important, take a look at this link to learn more further :&nbsp; http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial&nbsp;&nbsp;&nbsp; look at section : Preprocessing: PCA and Whitening !&nbsp;</p>",
      "votes": 4,
      "replies": []
    },
    {
      "id": 52114,
      "author_name": "Z.Z.",
      "author_url": "",
      "post_date": "2014-08-17T18:27:27.113000",
      "content": "<p>If you do not want to utilize the color information in the images, yes you can convert to grayscale, which is nothing but simply averaging the RGB values for every pixel.&nbsp;</p>",
      "votes": 2,
      "replies": []
    },
    {
      "id": 643259,
      "author_name": "",
      "author_url": "",
      "post_date": "2019-10-07T10:38:29.460000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "53288": "",
    "52114": "",
    "39250": "",
    "643259": ""
  }
}