{
  "id": 357203,
  "title": "Can i make an model without segmentation or bounding box data?",
  "url": "/competitions/rsna-2022-cervical-spine-fracture-detection/discussion/357203",
  "author_name": "osman bayram",
  "post_date": "2022-10-03T14:28:52.373000",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I am having hard time picturing a model that can utilize these segmentations or bounding boxes. How does one use these to train a model, if they are just gonna get images during inference?</p>",
  "messages": [
    {
      "id": 1969533,
      "postDate": "2022-10-03T14:35:26.683Z",
      "content": "<p><a href=\"https://www.kaggle.com/osmanf\" target=\"_blank\">@osmanf</a> this can help you,<br>\n<a href=\"https://www.kaggle.com/code/ritupande/object-localization-without-bounding-box\" target=\"_blank\">https://www.kaggle.com/code/ritupande/object-localization-without-bounding-box</a></p>",
      "rawMarkdown": "@osmanf this can help you,\nhttps://www.kaggle.com/code/ritupande/object-localization-without-bounding-box",
      "votes": 1,
      "replies": [
        {
          "id": 1969538,
          "postDate": "2022-10-03T14:38:47.503Z",
          "content": "<p>thank youu :)</p>",
          "rawMarkdown": "thank youu :)"
        }
      ]
    },
    {
      "id": 1969515,
      "postDate": "2022-10-03T14:28:52.373Z",
      "content": "<p>I am having hard time picturing a model that can utilize these segmentations or bounding boxes. How does one use these to train a model, if they are just gonna get images during inference?</p>",
      "rawMarkdown": "I am having hard time picturing a model that can utilize these segmentations or bounding boxes. How does one use these to train a model, if they are just gonna get images during inference?",
      "votes": 1
    }
  ],
  "comments": [
    {
      "id": 1969533,
      "author_name": "Ab_Rafey",
      "author_url": "",
      "post_date": "2022-10-03T14:35:26.683000",
      "content": "<p><a href=\"https://www.kaggle.com/osmanf\" target=\"_blank\">@osmanf</a> this can help you,<br>\n<a href=\"https://www.kaggle.com/code/ritupande/object-localization-without-bounding-box\" target=\"_blank\">https://www.kaggle.com/code/ritupande/object-localization-without-bounding-box</a></p>",
      "votes": 1,
      "replies": [
        {
          "id": 1969538,
          "author_name": "osman bayram",
          "author_url": "",
          "post_date": "2022-10-03T14:38:47.503000",
          "content": "<p>thank youu :)</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1969533": "@osmanf this can help you,\nhttps://www.kaggle.com/code/ritupande/object-localization-without-bounding-box",
    "1969515": "I am having hard time picturing a model that can utilize these segmentations or bounding boxes. How does one use these to train a model, if they are just gonna get images during inference?"
  }
}