{
  "id": 100899,
  "title": "image preprocessing",
  "url": "/competitions/aptos2019-blindness-detection/discussion/100899",
  "author_name": "",
  "post_date": "2019-07-22T01:46:13.977012700Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Except shape transform (like crop，flip and affine), what other image preprocessing can be taken on imagedate\nI think take some preprocessing on retina images, can make models are easier to train</p>",
  "messages": [
    {
      "id": "581473",
      "postDate": "07/22/2019 01:46:13",
      "content": "<p>Except shape transform (like crop，flip and affine), what other image preprocessing can be taken on imagedate\nI think take some preprocessing on retina images, can make models are easier to train</p>",
      "rawMarkdown": "Except shape transform (like crop，flip and affine), what other image preprocessing can be taken on imagedate\nI think take some preprocessing on retina images, can make models are easier to train",
      "votes": null
    },
    {
      "id": "581557",
      "postDate": "07/22/2019 05:12:39",
      "content": "<p>Zoom, and ben's processing (subtracting local avg)</p>",
      "rawMarkdown": "Zoom, and ben's processing (subtracting local avg)",
      "votes": null
    },
    {
      "id": "582334",
      "postDate": "07/23/2019 04:28:49",
      "content": "<p>thanks for your reply ~ </p>",
      "rawMarkdown": "thanks for your reply ~",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 581557,
      "author_name": "sidhanthholalkere",
      "author_url": "",
      "post_date": "07/22/2019 05:12:39",
      "content": "<p>Zoom, and ben's processing (subtracting local avg)</p>",
      "votes": null,
      "replies": [
        {
          "id": 582334,
          "author_name": "suzhengpeng",
          "author_url": "",
          "post_date": "07/23/2019 04:28:49",
          "content": "<p>thanks for your reply ~ </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "581473": "Except shape transform (like crop，flip and affine), what other image preprocessing can be taken on imagedate\nI think take some preprocessing on retina images, can make models are easier to train",
    "581557": "Zoom, and ben's processing (subtracting local avg)",
    "582334": "thanks for your reply ~"
  },
  "source": "meta"
}