{
  "id": 98599,
  "title": "Submission error",
  "url": "/competitions/aptos2019-blindness-detection/discussion/98599",
  "author_name": "",
  "post_date": "2019-07-04T21:16:09.868497600Z",
  "votes": 8,
  "comment_count": 10,
  "views": 0,
  "content": "<p>A kernel completed with no errors, generated what looks like a valid submission (proper range of values, no missing ones etc) - and yet after clicking \"submit to competition\" I am getting a submission error with the message \"No additional details provided for this error\". </p>\n\n<p>Anybody else facing this in the last few hours?</p>",
  "messages": [
    {
      "id": "568403",
      "postDate": "07/04/2019 21:16:09",
      "content": "<p>A kernel completed with no errors, generated what looks like a valid submission (proper range of values, no missing ones etc) - and yet after clicking \"submit to competition\" I am getting a submission error with the message \"No additional details provided for this error\". </p>\n\n<p>Anybody else facing this in the last few hours?</p>",
      "rawMarkdown": "A kernel completed with no errors, generated what looks like a valid submission (proper range of values, no missing ones etc) - and yet after clicking \"submit to competition\" I am getting a submission error with the message \"No additional details provided for this error\". \n\nAnybody else facing this in the last few hours?",
      "votes": null
    },
    {
      "id": "568414",
      "postDate": "07/04/2019 22:11:44",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2034058%2F288c0565b375e5b5a6cc6f85cab0d28e%2Ferror.png?generation=1562278287480397&amp;alt=media\" alt=\"\">\nyes i faced the same issue!!!</p>",
      "rawMarkdown": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2034058%2F288c0565b375e5b5a6cc6f85cab0d28e%2Ferror.png?generation=1562278287480397&amp;alt=media)\nyes i faced the same issue!!!",
      "votes": null
    },
    {
      "id": "568415",
      "postDate": "07/04/2019 22:14:48",
      "content": "<p>Thanks - I saw a few other posts with variations on the same theme popping up in the last few hours, so the issue is probably bigger than me :-)</p>",
      "rawMarkdown": "Thanks - I saw a few other posts with variations on the same theme popping up in the last few hours, so the issue is probably bigger than me :-)",
      "votes": null
    },
    {
      "id": "568663",
      "postDate": "07/05/2019 09:21:11",
      "content": "<p>Same here 😂 . I'm trying submitting with a new kernel...</p>",
      "rawMarkdown": "Same here 😂 . I'm trying submitting with a new kernel...",
      "votes": null
    },
    {
      "id": "568795",
      "postDate": "07/05/2019 12:56:37",
      "content": "<p>Are all of your predictions integers?</p>",
      "rawMarkdown": "Are all of your predictions integers?",
      "votes": null
    },
    {
      "id": "568796",
      "postDate": "07/05/2019 13:00:06",
      "content": "<p>Mine yes</p>",
      "rawMarkdown": "Mine yes",
      "votes": null
    },
    {
      "id": "568810",
      "postDate": "07/05/2019 13:22:18",
      "content": "<p>I also have the same problem. Others suggested that this could be a problem with memory, so I changed image resolution and batch size, however it did not help. I've done the simple test to check if it is a problem related to the submission generation part or to anything else (like memory)- I left all the code unchanged except the diagnosis assignment line - I used numpy.random.randint to generate output and this worked. So, it doesn't seem to be memory related problem, but submission output as is stated in status. I also tried to change the type of the diagnosis output data (int, float) and it also failed. I have no idea what I am doing wrong, but I hope we would able to find a solution. </p>",
      "rawMarkdown": "I also have the same problem. Others suggested that this could be a problem with memory, so I changed image resolution and batch size, however it did not help. I've done the simple test to check if it is a problem related to the submission generation part or to anything else (like memory)- I left all the code unchanged except the diagnosis assignment line - I used numpy.random.randint to generate output and this worked. So, it doesn't seem to be memory related problem, but submission output as is stated in status. I also tried to change the type of the diagnosis output data (int, float) and it also failed. I have no idea what I am doing wrong, but I hope we would able to find a solution.",
      "votes": null
    },
    {
      "id": "569091",
      "postDate": "07/06/2019 03:31:06",
      "content": "<p>I also have the same problem. But I did two things, one of which was successful. \nFirst thing: my program is divided into two parts, one to generate the .h5 file, the other to load the .h5 file, it failed.\nSecond thing:Integrating the program into one large program, which involved training and testing with the model , was time-consuming at the time of submission, but it was successful.\nSo I think it has to do with loading .h5 files, but I don't know what the problem is.</p>",
      "rawMarkdown": "I also have the same problem. But I did two things, one of which was successful. \nFirst thing: my program is divided into two parts, one to generate the .h5 file, the other to load the .h5 file, it failed.\nSecond thing:Integrating the program into one large program, which involved training and testing with the model , was time-consuming at the time of submission, but it was successful.\nSo I think it has to do with loading .h5 files, but I don't know what the problem is.",
      "votes": null
    },
    {
      "id": "569152",
      "postDate": "07/06/2019 06:51:44",
      "content": "<p>Update： create two new kernels, one to generate .h5 and the other to load the .h5 file, successful !!!</p>",
      "rawMarkdown": "Update： create two new kernels, one to generate .h5 and the other to load the .h5 file, successful !!!",
      "votes": null
    },
    {
      "id": "569504",
      "postDate": "07/06/2019 19:17:05",
      "content": "<p>Hi! <a href=\"/konradb\">@konradb</a>, my recommendation will be to start small first, small batch size, Image size, # epochs or anything else, review also all your code so there are no hardcoded Ids.</p>",
      "rawMarkdown": "Hi! @konradb, my recommendation will be to start small first, small batch size, Image size, # epochs or anything else, review also all your code so there are no hardcoded Ids.",
      "votes": null
    },
    {
      "id": "607461",
      "postDate": "08/25/2019 09:54:51",
      "content": "<p>how you solved this error ? caan't make a single prediction.</p>",
      "rawMarkdown": "how you solved this error ? caan't make a single prediction.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 568414,
      "author_name": "mobassir",
      "author_url": "",
      "post_date": "07/04/2019 22:11:44",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2034058%2F288c0565b375e5b5a6cc6f85cab0d28e%2Ferror.png?generation=1562278287480397&amp;alt=media\" alt=\"\">\nyes i faced the same issue!!!</p>",
      "votes": null,
      "replies": [
        {
          "id": 568415,
          "author_name": "konradb",
          "author_url": "",
          "post_date": "07/04/2019 22:14:48",
          "content": "<p>Thanks - I saw a few other posts with variations on the same theme popping up in the last few hours, so the issue is probably bigger than me :-)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 568810,
          "author_name": "rafzy15",
          "author_url": "",
          "post_date": "07/05/2019 13:22:18",
          "content": "<p>I also have the same problem. Others suggested that this could be a problem with memory, so I changed image resolution and batch size, however it did not help. I've done the simple test to check if it is a problem related to the submission generation part or to anything else (like memory)- I left all the code unchanged except the diagnosis assignment line - I used numpy.random.randint to generate output and this worked. So, it doesn't seem to be memory related problem, but submission output as is stated in status. I also tried to change the type of the diagnosis output data (int, float) and it also failed. I have no idea what I am doing wrong, but I hope we would able to find a solution. </p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 607461,
          "author_name": "neeraj17",
          "author_url": "",
          "post_date": "08/25/2019 09:54:51",
          "content": "<p>how you solved this error ? caan't make a single prediction.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 568663,
      "author_name": "raimonds1993",
      "author_url": "",
      "post_date": "07/05/2019 09:21:11",
      "content": "<p>Same here 😂 . I'm trying submitting with a new kernel...</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 568795,
      "author_name": "monkeyorman",
      "author_url": "",
      "post_date": "07/05/2019 12:56:37",
      "content": "<p>Are all of your predictions integers?</p>",
      "votes": null,
      "replies": [
        {
          "id": 568796,
          "author_name": "raimonds1993",
          "author_url": "",
          "post_date": "07/05/2019 13:00:06",
          "content": "<p>Mine yes</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 569091,
      "author_name": "dm591692335",
      "author_url": "",
      "post_date": "07/06/2019 03:31:06",
      "content": "<p>I also have the same problem. But I did two things, one of which was successful. \nFirst thing: my program is divided into two parts, one to generate the .h5 file, the other to load the .h5 file, it failed.\nSecond thing:Integrating the program into one large program, which involved training and testing with the model , was time-consuming at the time of submission, but it was successful.\nSo I think it has to do with loading .h5 files, but I don't know what the problem is.</p>",
      "votes": null,
      "replies": [
        {
          "id": 569152,
          "author_name": "dm591692335",
          "author_url": "",
          "post_date": "07/06/2019 06:51:44",
          "content": "<p>Update： create two new kernels, one to generate .h5 and the other to load the .h5 file, successful !!!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 569504,
      "author_name": "cv13j0",
      "author_url": "",
      "post_date": "07/06/2019 19:17:05",
      "content": "<p>Hi! <a href=\"/konradb\">@konradb</a>, my recommendation will be to start small first, small batch size, Image size, # epochs or anything else, review also all your code so there are no hardcoded Ids.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "568403": "A kernel completed with no errors, generated what looks like a valid submission (proper range of values, no missing ones etc) - and yet after clicking \"submit to competition\" I am getting a submission error with the message \"No additional details provided for this error\". \n\nAnybody else facing this in the last few hours?",
    "568414": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2034058%2F288c0565b375e5b5a6cc6f85cab0d28e%2Ferror.png?generation=1562278287480397&amp;alt=media)\nyes i faced the same issue!!!",
    "568415": "Thanks - I saw a few other posts with variations on the same theme popping up in the last few hours, so the issue is probably bigger than me :-)",
    "568663": "Same here 😂 . I'm trying submitting with a new kernel...",
    "568795": "Are all of your predictions integers?",
    "568796": "Mine yes",
    "568810": "I also have the same problem. Others suggested that this could be a problem with memory, so I changed image resolution and batch size, however it did not help. I've done the simple test to check if it is a problem related to the submission generation part or to anything else (like memory)- I left all the code unchanged except the diagnosis assignment line - I used numpy.random.randint to generate output and this worked. So, it doesn't seem to be memory related problem, but submission output as is stated in status. I also tried to change the type of the diagnosis output data (int, float) and it also failed. I have no idea what I am doing wrong, but I hope we would able to find a solution.",
    "569091": "I also have the same problem. But I did two things, one of which was successful. \nFirst thing: my program is divided into two parts, one to generate the .h5 file, the other to load the .h5 file, it failed.\nSecond thing:Integrating the program into one large program, which involved training and testing with the model , was time-consuming at the time of submission, but it was successful.\nSo I think it has to do with loading .h5 files, but I don't know what the problem is.",
    "569152": "Update： create two new kernels, one to generate .h5 and the other to load the .h5 file, successful !!!",
    "569504": "Hi! @konradb, my recommendation will be to start small first, small batch size, Image size, # epochs or anything else, review also all your code so there are no hardcoded Ids.",
    "607461": "how you solved this error ? caan't make a single prediction."
  },
  "source": "meta"
}