{
  "id": 8274,
  "title": "Extracting pixel data from images",
  "url": "/competitions/cifar-10/discussion/8274",
  "author_name": "Christopher Beckham",
  "post_date": "2014-05-25T04:03:57.373000",
  "votes": 1,
  "comment_count": 5,
  "views": 5869,
  "content": "<p>I just put this repo up, potentially to help newcomers.</p>\n<p>http://github.com/chrispy645/kaggle-cifar10-extract</p>\n<p>It's a Python script that will automatically extract RGB pixel features from all the images in the training set. The script can easily be modified so that you extract greyscale pixels instead or apply it to the test set as well.</p>\n<p>If there any bugs let me know. Works perfect for me. :)</p>\n<p>Cheers</p>",
  "messages": [
    {
      "id": 46193,
      "postDate": "2014-05-25T04:03:57.373Z",
      "content": "<p>I just put this repo up, potentially to help newcomers.</p>\n<p>http://github.com/chrispy645/kaggle-cifar10-extract</p>\n<p>It's a Python script that will automatically extract RGB pixel features from all the images in the training set. The script can easily be modified so that you extract greyscale pixels instead or apply it to the test set as well.</p>\n<p>If there any bugs let me know. Works perfect for me. :)</p>\n<p>Cheers</p>",
      "votes": 1
    },
    {
      "id": 86384,
      "postDate": "2015-07-21T21:40:41.490Z",
      "content": "<p>Is there any way to have the pixel data be outputed in a csv file like this?</p>",
      "rawMarkdown": "Is there any way to have the pixel data be outputed in a csv file like this?"
    },
    {
      "id": 50915,
      "postDate": "2014-07-20T07:05:47.513Z",
      "content": "<p>It's been a long while but I did use a neural network. I'm not sure if performance was that great... yes you may have to derive other features to get better accuracy. The script I've put up is pretty barebones, it's simply for deriving pixel data from the images but there are a ton of other things you could do in addition to that.</p>"
    },
    {
      "id": 50897,
      "postDate": "2014-07-19T16:55:32.923Z",
      "content": "<p>i guess you use a neural network for your object detection? does object detection on pixel level work with good performance? why not using any other features than pixel features?</p>"
    },
    {
      "id": 136756,
      "postDate": "2016-09-24T20:06:38.810Z",
      "rawMarkdown": "",
      "isDeleted": true,
      "replies": [
        {
          "id": 268792,
          "postDate": "2018-01-15T16:46:22.960Z",
          "content": "<p>Hi Matt, \nI really appreciate you taking time to write a Code in R for Cifar 10 dataset. I am having some problems in converting your files to CSV for both training and test datasets. Could you be kind enough to provide me with a code to save testing and training datasets in CSV format  in R to be further used to develop CNN model.</p>\n\n<p>Thanks\nVijay</p>",
          "rawMarkdown": "Hi Matt, \nI really appreciate you taking time to write a Code in R for Cifar 10 dataset. I am having some problems in converting your files to CSV for both training and test datasets. Could you be kind enough to provide me with a code to save testing and training datasets in CSV format  in R to be further used to develop CNN model.\n\nThanks\nVijay"
        }
      ]
    }
  ],
  "comments": [
    {
      "id": 86384,
      "author_name": "abqader",
      "author_url": "",
      "post_date": "2015-07-21T21:40:41.490000",
      "content": "<p>Is there any way to have the pixel data be outputed in a csv file like this?</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 50915,
      "author_name": "Christopher Beckham",
      "author_url": "",
      "post_date": "2014-07-20T07:05:47.513000",
      "content": "<p>It's been a long while but I did use a neural network. I'm not sure if performance was that great... yes you may have to derive other features to get better accuracy. The script I've put up is pretty barebones, it's simply for deriving pixel data from the images but there are a ton of other things you could do in addition to that.</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 50897,
      "author_name": "Gerald Stan",
      "author_url": "",
      "post_date": "2014-07-19T16:55:32.923000",
      "content": "<p>i guess you use a neural network for your object detection? does object detection on pixel level work with good performance? why not using any other features than pixel features?</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 136756,
      "author_name": "",
      "author_url": "",
      "post_date": "2016-09-24T20:06:38.810000",
      "content": "",
      "votes": 0,
      "replies": [
        {
          "id": 268792,
          "author_name": "VijayZutshi",
          "author_url": "",
          "post_date": "2018-01-15T16:46:22.960000",
          "content": "<p>Hi Matt, \nI really appreciate you taking time to write a Code in R for Cifar 10 dataset. I am having some problems in converting your files to CSV for both training and test datasets. Could you be kind enough to provide me with a code to save testing and training datasets in CSV format  in R to be further used to develop CNN model.</p>\n\n<p>Thanks\nVijay</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "46193": "",
    "86384": "Is there any way to have the pixel data be outputed in a csv file like this?",
    "50915": "",
    "50897": "",
    "136756": ""
  }
}