{
  "id": 167535,
  "title": "\"What is prediction string actually\"",
  "url": "/competitions/global-wheat-detection/discussion/167535",
  "author_name": "",
  "post_date": "2020-07-17T01:36:16.484502800Z",
  "votes": null,
  "comment_count": 6,
  "views": 0,
  "content": "<p>what is the output meaning?</p>",
  "messages": [
    {
      "id": "932338",
      "postDate": "07/17/2020 01:36:16",
      "content": "<p>what is the output meaning?</p>",
      "rawMarkdown": "what is the output meaning?",
      "votes": null
    },
    {
      "id": "932341",
      "postDate": "07/17/2020 01:40:05",
      "content": "<p>actually what is trying to predict at the final stage of the image???</p>",
      "rawMarkdown": "actually what is trying to predict at the final stage of the image???",
      "votes": null
    },
    {
      "id": "932348",
      "postDate": "07/17/2020 01:45:38",
      "content": "<p>The goal of the competition is to detect wheat heads in images. The PredictionString in your submission csv is simply a formatted string of all the boxes you detect. The format is like [prediction confidence, box x min, box y min, box width, box height] separated by spaces. If there are multiple boxes detected in one image, you concatenate these all together into one PredictionString.</p>",
      "rawMarkdown": "The goal of the competition is to detect wheat heads in images. The PredictionString in your submission csv is simply a formatted string of all the boxes you detect. The format is like [prediction confidence, box x min, box y min, box width, box height] separated by spaces. If there are multiple boxes detected in one image, you concatenate these all together into one PredictionString.",
      "votes": null
    },
    {
      "id": "932353",
      "postDate": "07/17/2020 02:02:27",
      "content": "<p>Okay, for example, one wheat heads have detected the 5 this is our [prediction confidence] and box width and box height like for example 299 * 299, so what are the all rest of the things actually? in the output like \"box x min, box y min\".</p>\n\n<p>finally above example of my would be like [5, box x min, box y min, 299, 299]</p>\n\n<p>so what are the 2 rest of the things actually? in the output like \"box x min, box y min\"</p>",
      "rawMarkdown": "Okay, for example, one wheat heads have detected the 5 this is our [prediction confidence] and box width and box height like for example 299 * 299, so what are the all rest of the things actually? in the output like \"box x min, box y min\".\n\nfinally above example of my would be like [5, box x min, box y min, 299, 299]\n\nso what are the 2 rest of the things actually? in the output like \"box x min, box y min\"",
      "votes": null
    },
    {
      "id": "932356",
      "postDate": "07/17/2020 02:08:31",
      "content": "<p>It's the position of the box (specifically of the top-left corner).</p>",
      "rawMarkdown": "It's the position of the box (specifically of the top-left corner).",
      "votes": null
    },
    {
      "id": "932372",
      "postDate": "07/17/2020 02:53:35",
      "content": "<p>Can you post the example of it???</p>",
      "rawMarkdown": "Can you post the example of it???",
      "votes": null
    },
    {
      "id": "932392",
      "postDate": "07/17/2020 03:24:32",
      "content": "<p>1.0 40 40 160 160\nWould be the prediction string for a 160x160 box with it's top left corner positioned at (40, 40).</p>\n\n<p>Please refer to the existing public notebooks, they will help guide you</p>",
      "rawMarkdown": "1.0 40 40 160 160\nWould be the prediction string for a 160x160 box with it's top left corner positioned at (40, 40).\n\nPlease refer to the existing public notebooks, they will help guide you",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 932341,
      "author_name": "pathivenkatesh",
      "author_url": "",
      "post_date": "07/17/2020 01:40:05",
      "content": "<p>actually what is trying to predict at the final stage of the image???</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 932348,
      "author_name": "matthewmasters",
      "author_url": "",
      "post_date": "07/17/2020 01:45:38",
      "content": "<p>The goal of the competition is to detect wheat heads in images. The PredictionString in your submission csv is simply a formatted string of all the boxes you detect. The format is like [prediction confidence, box x min, box y min, box width, box height] separated by spaces. If there are multiple boxes detected in one image, you concatenate these all together into one PredictionString.</p>",
      "votes": null,
      "replies": [
        {
          "id": 932353,
          "author_name": "pathivenkatesh",
          "author_url": "",
          "post_date": "07/17/2020 02:02:27",
          "content": "<p>Okay, for example, one wheat heads have detected the 5 this is our [prediction confidence] and box width and box height like for example 299 * 299, so what are the all rest of the things actually? in the output like \"box x min, box y min\".</p>\n\n<p>finally above example of my would be like [5, box x min, box y min, 299, 299]</p>\n\n<p>so what are the 2 rest of the things actually? in the output like \"box x min, box y min\"</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 932356,
          "author_name": "matthewmasters",
          "author_url": "",
          "post_date": "07/17/2020 02:08:31",
          "content": "<p>It's the position of the box (specifically of the top-left corner).</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 932372,
          "author_name": "pathivenkatesh",
          "author_url": "",
          "post_date": "07/17/2020 02:53:35",
          "content": "<p>Can you post the example of it???</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 932392,
          "author_name": "matthewmasters",
          "author_url": "",
          "post_date": "07/17/2020 03:24:32",
          "content": "<p>1.0 40 40 160 160\nWould be the prediction string for a 160x160 box with it's top left corner positioned at (40, 40).</p>\n\n<p>Please refer to the existing public notebooks, they will help guide you</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "932338": "what is the output meaning?",
    "932341": "actually what is trying to predict at the final stage of the image???",
    "932348": "The goal of the competition is to detect wheat heads in images. The PredictionString in your submission csv is simply a formatted string of all the boxes you detect. The format is like [prediction confidence, box x min, box y min, box width, box height] separated by spaces. If there are multiple boxes detected in one image, you concatenate these all together into one PredictionString.",
    "932353": "Okay, for example, one wheat heads have detected the 5 this is our [prediction confidence] and box width and box height like for example 299 * 299, so what are the all rest of the things actually? in the output like \"box x min, box y min\".\n\nfinally above example of my would be like [5, box x min, box y min, 299, 299]\n\nso what are the 2 rest of the things actually? in the output like \"box x min, box y min\"",
    "932356": "It's the position of the box (specifically of the top-left corner).",
    "932372": "Can you post the example of it???",
    "932392": "1.0 40 40 160 160\nWould be the prediction string for a 160x160 box with it's top left corner positioned at (40, 40).\n\nPlease refer to the existing public notebooks, they will help guide you"
  },
  "source": "meta"
}