{
  "id": 350664,
  "title": "need help - submission error",
  "url": "/competitions/hubmap-organ-segmentation/discussion/350664",
  "author_name": "",
  "post_date": "2022-09-06T16:03:37.093071300Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi guys, I've tried submitted this notebooks multiple times, but it always shows submission error. It ran well locally and generated meaningful results, but once submitted, it showed 'Notebook Threw Exception'.  Can anyone figure out the reason? Thanks…<br>\n<a href=\"https://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook\" target=\"_blank\">https://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook</a></p>\n<hr>\n<p>update<br>\nI've found the tips from Quan in this post very helpful <a href=\"url\" target=\"_blank\">https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/336582</a><br>\n<code>Make sure to read the data description carefully. For example: \"The HuBMAP images range in size from 4500x4500 down to 160x160 pixels\". My self-implemented sliding window inference did not account for this and it failed miserably.</code><br>\nThe problem is solved after I put the tiles to be 128x128</p>",
  "messages": [
    {
      "id": "1928784",
      "postDate": "09/06/2022 16:03:37",
      "content": "<p>Hi guys, I've tried submitted this notebooks multiple times, but it always shows submission error. It ran well locally and generated meaningful results, but once submitted, it showed 'Notebook Threw Exception'.  Can anyone figure out the reason? Thanks…<br>\n<a href=\"https://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook\" target=\"_blank\">https://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook</a></p>\n<hr>\n<p>update<br>\nI've found the tips from Quan in this post very helpful <a href=\"url\" target=\"_blank\">https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/336582</a><br>\n<code>Make sure to read the data description carefully. For example: \"The HuBMAP images range in size from 4500x4500 down to 160x160 pixels\". My self-implemented sliding window inference did not account for this and it failed miserably.</code><br>\nThe problem is solved after I put the tiles to be 128x128</p>",
      "rawMarkdown": "Hi guys, I've tried submitted this notebooks multiple times, but it always shows submission error. It ran well locally and generated meaningful results, but once submitted, it showed 'Notebook Threw Exception'.  Can anyone figure out the reason? Thanks...\nhttps://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook\n\n----\nupdate\nI've found the tips from Quan in this post very helpful [https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/336582](url)\n`Make sure to read the data description carefully. For example: \"The HuBMAP images range in size from 4500x4500 down to 160x160 pixels\". My self-implemented sliding window inference did not account for this and it failed miserably.`\nThe problem is solved after I put the tiles to be 128x128",
      "votes": null
    },
    {
      "id": "1928804",
      "postDate": "09/06/2022 16:17:01",
      "content": "<p>I think you need to pay attention to the following aspects: </p>\n<ol>\n<li>There is more than one image in the data set of the competition, so you can save or run, because your submit can only predict one picture. </li>\n<li>The image size of the internal test should be taken into account. The minimum size of their image is less than 512 pixels. </li>\n<li>In a word, it is recommended that you must add more pictures to test.csv in your own program and submit the simulation, so that there will be no mistakes.</li>\n</ol>",
      "rawMarkdown": "I think you need to pay attention to the following aspects: \n1. There is more than one image in the data set of the competition, so you can save or run, because your submit can only predict one picture. \n2. The image size of the internal test should be taken into account. The minimum size of their image is less than 512 pixels. \n3. In a word, it is recommended that you must add more pictures to test.csv in your own program and submit the simulation, so that there will be no mistakes.",
      "votes": null
    },
    {
      "id": "1928872",
      "postDate": "09/06/2022 17:01:49",
      "content": "<p>Great suggestions!  I’ll try that</p>",
      "rawMarkdown": "Great suggestions!  I’ll try that",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1928804,
      "author_name": "zhangasa",
      "author_url": "",
      "post_date": "09/06/2022 16:17:01",
      "content": "<p>I think you need to pay attention to the following aspects: </p>\n<ol>\n<li>There is more than one image in the data set of the competition, so you can save or run, because your submit can only predict one picture. </li>\n<li>The image size of the internal test should be taken into account. The minimum size of their image is less than 512 pixels. </li>\n<li>In a word, it is recommended that you must add more pictures to test.csv in your own program and submit the simulation, so that there will be no mistakes.</li>\n</ol>",
      "votes": null,
      "replies": [
        {
          "id": 1928872,
          "author_name": "lililycai",
          "author_url": "",
          "post_date": "09/06/2022 17:01:49",
          "content": "<p>Great suggestions!  I’ll try that</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1928784": "Hi guys, I've tried submitted this notebooks multiple times, but it always shows submission error. It ran well locally and generated meaningful results, but once submitted, it showed 'Notebook Threw Exception'.  Can anyone figure out the reason? Thanks...\nhttps://www.kaggle.com/code/lililycai/deepflash-efficient-sampling-infer2/notebook\n\n----\nupdate\nI've found the tips from Quan in this post very helpful [https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/336582](url)\n`Make sure to read the data description carefully. For example: \"The HuBMAP images range in size from 4500x4500 down to 160x160 pixels\". My self-implemented sliding window inference did not account for this and it failed miserably.`\nThe problem is solved after I put the tiles to be 128x128",
    "1928804": "I think you need to pay attention to the following aspects: \n1. There is more than one image in the data set of the competition, so you can save or run, because your submit can only predict one picture. \n2. The image size of the internal test should be taken into account. The minimum size of their image is less than 512 pixels. \n3. In a word, it is recommended that you must add more pictures to test.csv in your own program and submit the simulation, so that there will be no mistakes.",
    "1928872": "Great suggestions!  I’ll try that"
  },
  "source": "meta"
}