{
  "id": 102843,
  "title": "Quick Observation/Tip",
  "url": "/competitions/aptos2019-blindness-detection/discussion/102843",
  "author_name": "",
  "post_date": "2019-08-05T13:26:16.318231700Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Perhaps someone noticed and discussed this before, but the train data is mostly un-zoomed, while test contains many already zoomed into certain areas, perhaps since they show signs of diabetes. The same applies to the old data from 2015, mostly zoomed in, much less circular and more square (zoomed). This might explain why training with a mix of old and new is problematic.</p>",
  "messages": [
    {
      "id": "592559",
      "postDate": "08/05/2019 13:26:16",
      "content": "<p>Perhaps someone noticed and discussed this before, but the train data is mostly un-zoomed, while test contains many already zoomed into certain areas, perhaps since they show signs of diabetes. The same applies to the old data from 2015, mostly zoomed in, much less circular and more square (zoomed). This might explain why training with a mix of old and new is problematic.</p>",
      "rawMarkdown": "Perhaps someone noticed and discussed this before, but the train data is mostly un-zoomed, while test contains many already zoomed into certain areas, perhaps since they show signs of diabetes. The same applies to the old data from 2015, mostly zoomed in, much less circular and more square (zoomed). This might explain why training with a mix of old and new is problematic.",
      "votes": null
    },
    {
      "id": "594464",
      "postDate": "08/08/2019 04:25:21",
      "content": "<p>I think that the training set should do some enlargement and reduction.</p>",
      "rawMarkdown": "I think that the training set should do some enlargement and reduction.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 594464,
      "author_name": "a18974761777",
      "author_url": "",
      "post_date": "08/08/2019 04:25:21",
      "content": "<p>I think that the training set should do some enlargement and reduction.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "592559": "Perhaps someone noticed and discussed this before, but the train data is mostly un-zoomed, while test contains many already zoomed into certain areas, perhaps since they show signs of diabetes. The same applies to the old data from 2015, mostly zoomed in, much less circular and more square (zoomed). This might explain why training with a mix of old and new is problematic.",
    "594464": "I think that the training set should do some enlargement and reduction."
  },
  "source": "meta"
}