{
  "id": 64899,
  "title": "About data pre-processing",
  "url": "/competitions/airbus-ship-detection/discussion/64899",
  "author_name": "",
  "post_date": "2018-09-04T02:43:06.376914900Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>In the segmentation file,  a label of a picture is divided into a several parts , is it necessary to fuse them before train? </p>",
  "messages": [
    {
      "id": "381065",
      "postDate": "09/04/2018 02:43:06",
      "content": "<p>In the segmentation file,  a label of a picture is divided into a several parts , is it necessary to fuse them before train? </p>",
      "rawMarkdown": "In the segmentation file,  a label of a picture is divided into a several parts , is it necessary to fuse them before train?",
      "votes": null
    },
    {
      "id": "381395",
      "postDate": "09/04/2018 15:26:24",
      "content": "<p>It depends on the method and loss function you are using. For a regular U-net with regular loss function: yes.</p>",
      "rawMarkdown": "It depends on the method and loss function you are using. For a regular U-net with regular loss function: yes.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 381395,
      "author_name": "iafoss",
      "author_url": "",
      "post_date": "09/04/2018 15:26:24",
      "content": "<p>It depends on the method and loss function you are using. For a regular U-net with regular loss function: yes.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "381065": "In the segmentation file,  a label of a picture is divided into a several parts , is it necessary to fuse them before train?",
    "381395": "It depends on the method and loss function you are using. For a regular U-net with regular loss function: yes."
  },
  "source": "meta"
}