{
  "id": 229253,
  "title": "Few questions",
  "url": "/competitions/hpa-single-cell-image-classification/discussion/229253",
  "author_name": "Shihao Shao",
  "post_date": "2021-03-29T09:34:51.410000",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I have joined this competition for few days. Sorry if I missed some informations.</p>\n<ol>\n<li>Did the Ground Truth of Test dataset be annonated by HPACellSeg? If so, HPACellSeg will be a must.</li>\n<li>What are the distribution between Public and Private Dataset? Since I have seen many people have said HPACellSeg was kind of slow. So if Private Dataset is huge, it is necessary to find ways to optimize the time cost.</li>\n<li>Did anyone success submitting using HPACellSeg within 9 hours (without approach to reduce the time cost)?</li>\n</ol>\n<p>Thanks for your explanation!</p>",
  "messages": [
    {
      "id": 1259247,
      "postDate": "2021-04-01T08:57:52.683Z",
      "content": "<p>Hi, </p>\n<p>discussion about Ground Through:</p>\n<p><a href=\"https://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141\" target=\"_blank\">https://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141</a></p>\n<p>distribution between private und public test set should be aproximatly 1:2,5. If calculation on public test set is lasting 2 hours then, calculation to whole test set is going to last 7 hour. </p>\n<p>If you want to speed up HPA CellSegmentor you can have a look at this notebook</p>\n<p><a href=\"https://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation\" target=\"_blank\">https://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation</a></p>",
      "rawMarkdown": "Hi, \n\ndiscussion about Ground Through:\n\nhttps://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141\n\ndistribution between private und public test set should be aproximatly 1:2,5. If calculation on public test set is lasting 2 hours then, calculation to whole test set is going to last 7 hour. \n\nIf you want to speed up HPA CellSegmentor you can have a look at this notebook\n\nhttps://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation\n\n",
      "votes": 1,
      "replies": [
        {
          "id": 1259392,
          "postDate": "2021-04-01T11:11:25.970Z",
          "content": "<p>Thanks, Luca. It really helps!</p>",
          "rawMarkdown": "Thanks, Luca. It really helps!"
        }
      ]
    },
    {
      "id": 1255864,
      "postDate": "2021-03-29T09:34:51.410Z",
      "content": "<p>I have joined this competition for few days. Sorry if I missed some informations.</p>\n<ol>\n<li>Did the Ground Truth of Test dataset be annonated by HPACellSeg? If so, HPACellSeg will be a must.</li>\n<li>What are the distribution between Public and Private Dataset? Since I have seen many people have said HPACellSeg was kind of slow. So if Private Dataset is huge, it is necessary to find ways to optimize the time cost.</li>\n<li>Did anyone success submitting using HPACellSeg within 9 hours (without approach to reduce the time cost)?</li>\n</ol>\n<p>Thanks for your explanation!</p>",
      "rawMarkdown": "I have joined this competition for few days. Sorry if I missed some informations.\n\n1. Did the Ground Truth of Test dataset be annonated by HPACellSeg? If so, HPACellSeg will be a must.\n2. What are the distribution between Public and Private Dataset? Since I have seen many people have said HPACellSeg was kind of slow. So if Private Dataset is huge, it is necessary to find ways to optimize the time cost.\n3. Did anyone success submitting using HPACellSeg within 9 hours (without approach to reduce the time cost)?\n\nThanks for your explanation!",
      "votes": 2
    }
  ],
  "comments": [
    {
      "id": 1259247,
      "author_name": "LucaMTB",
      "author_url": "",
      "post_date": "2021-04-01T08:57:52.683000",
      "content": "<p>Hi, </p>\n<p>discussion about Ground Through:</p>\n<p><a href=\"https://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141\" target=\"_blank\">https://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141</a></p>\n<p>distribution between private und public test set should be aproximatly 1:2,5. If calculation on public test set is lasting 2 hours then, calculation to whole test set is going to last 7 hour. </p>\n<p>If you want to speed up HPA CellSegmentor you can have a look at this notebook</p>\n<p><a href=\"https://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation\" target=\"_blank\">https://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation</a></p>",
      "votes": 1,
      "replies": [
        {
          "id": 1259392,
          "author_name": "Shihao Shao",
          "author_url": "",
          "post_date": "2021-04-01T11:11:25.970000",
          "content": "<p>Thanks, Luca. It really helps!</p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1259247": "Hi, \n\ndiscussion about Ground Through:\n\nhttps://www.kaggle.com/c/hpa-single-cell-image-classification/discussion/215141\n\ndistribution between private und public test set should be aproximatly 1:2,5. If calculation on public test set is lasting 2 hours then, calculation to whole test set is going to last 7 hour. \n\nIf you want to speed up HPA CellSegmentor you can have a look at this notebook\n\nhttps://www.kaggle.com/linshokaku/faster-hpa-cell-segmentation\n\n",
    "1255864": "I have joined this competition for few days. Sorry if I missed some informations.\n\n1. Did the Ground Truth of Test dataset be annonated by HPACellSeg? If so, HPACellSeg will be a must.\n2. What are the distribution between Public and Private Dataset? Since I have seen many people have said HPACellSeg was kind of slow. So if Private Dataset is huge, it is necessary to find ways to optimize the time cost.\n3. Did anyone success submitting using HPACellSeg within 9 hours (without approach to reduce the time cost)?\n\nThanks for your explanation!"
  }
}