{
  "id": 31048,
  "title": "Rules clarification",
  "url": "/competitions/noaa-fisheries-steller-sea-lion-population-count/discussion/31048",
  "author_name": "",
  "post_date": "2017-04-03T09:52:07.841794400Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>This is the first image based competition I am working on. I have a few questions about the rules, I am not sure what is and what is not permitted. </p>\n\n<ol>\n<li><p>Can I manually change the train images in any way? For example 338.jpg dotted has some red lines at the bottom of the image, that throws away my dot parser, can I black out that part manually? </p></li>\n<li><p>I want to create a training set of 32x32 images of the sea lions. Can I manually delete some of these images? or do I have to be able to generate the training set by running a script? </p></li>\n<li><p>In general, what can we do and what we cannot manually do to the training set?</p></li>\n</ol>",
  "messages": [
    {
      "id": "172322",
      "postDate": "04/03/2017 09:52:07",
      "content": "<p>This is the first image based competition I am working on. I have a few questions about the rules, I am not sure what is and what is not permitted. </p>\n\n<ol>\n<li><p>Can I manually change the train images in any way? For example 338.jpg dotted has some red lines at the bottom of the image, that throws away my dot parser, can I black out that part manually? </p></li>\n<li><p>I want to create a training set of 32x32 images of the sea lions. Can I manually delete some of these images? or do I have to be able to generate the training set by running a script? </p></li>\n<li><p>In general, what can we do and what we cannot manually do to the training set?</p></li>\n</ol>",
      "rawMarkdown": "This is the first image based competition I am working on. I have a few questions about the rules, I am not sure what is and what is not permitted. \n \n1. Can I manually change the train images in any way? For example 338.jpg dotted has some red lines at the bottom of the image, that throws away my dot parser, can I black out that part manually? \n \n2. I want to create a training set of 32x32 images of the sea lions. Can I manually delete some of these images? or do I have to be able to generate the training set by running a script? \n \n3. In general, what can we do and what we cannot manually do to the training set?",
      "votes": null
    },
    {
      "id": "172500",
      "postDate": "04/03/2017 21:55:03",
      "content": "<p>Take my words with a grain of salt, as I am not the organizer of this contest. That said, in the past contests you could all sorts of manual processing of the training set, as long as your method processed the test set automatically.</p>",
      "rawMarkdown": "Take my words with a grain of salt, as I am not the organizer of this contest. That said, in the past contests you could all sorts of manual processing of the training set, as long as your method processed the test set automatically.",
      "votes": null
    },
    {
      "id": "172502",
      "postDate": "04/03/2017 22:18:35",
      "content": "<p>Manual annotations/cropping of the training data are fine. Good luck!</p>",
      "rawMarkdown": "Manual annotations/cropping of the training data are fine. Good luck!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 172500,
      "author_name": "mmucha",
      "author_url": "",
      "post_date": "04/03/2017 21:55:03",
      "content": "<p>Take my words with a grain of salt, as I am not the organizer of this contest. That said, in the past contests you could all sorts of manual processing of the training set, as long as your method processed the test set automatically.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 172502,
      "author_name": "datacanary",
      "author_url": "",
      "post_date": "04/03/2017 22:18:35",
      "content": "<p>Manual annotations/cropping of the training data are fine. Good luck!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "172322": "This is the first image based competition I am working on. I have a few questions about the rules, I am not sure what is and what is not permitted. \n \n1. Can I manually change the train images in any way? For example 338.jpg dotted has some red lines at the bottom of the image, that throws away my dot parser, can I black out that part manually? \n \n2. I want to create a training set of 32x32 images of the sea lions. Can I manually delete some of these images? or do I have to be able to generate the training set by running a script? \n \n3. In general, what can we do and what we cannot manually do to the training set?",
    "172500": "Take my words with a grain of salt, as I am not the organizer of this contest. That said, in the past contests you could all sorts of manual processing of the training set, as long as your method processed the test set automatically.",
    "172502": "Manual annotations/cropping of the training data are fine. Good luck!"
  },
  "source": "meta"
}