{
  "id": 276881,
  "title": "Submission Scoring Error",
  "url": "/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/276881",
  "author_name": "",
  "post_date": "2021-10-06T19:33:44.523830300Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>We are generating a csv file named submission.csv in the kaggle output directory, yet are getting a submission scoring error when trying to submit. The notebook however runs successfully when we try to submit. We double checked the submission file and it is indeed in the right format. The only thing we can think of is that we are loading our model weights from a private dataset that we created, could this be the cause of the submission scoring error?</p>",
  "messages": [
    {
      "id": "1536563",
      "postDate": "10/06/2021 19:33:44",
      "content": "<p>We are generating a csv file named submission.csv in the kaggle output directory, yet are getting a submission scoring error when trying to submit. The notebook however runs successfully when we try to submit. We double checked the submission file and it is indeed in the right format. The only thing we can think of is that we are loading our model weights from a private dataset that we created, could this be the cause of the submission scoring error?</p>",
      "rawMarkdown": "We are generating a csv file named submission.csv in the kaggle output directory, yet are getting a submission scoring error when trying to submit. The notebook however runs successfully when we try to submit. We double checked the submission file and it is indeed in the right format. The only thing we can think of is that we are loading our model weights from a private dataset that we created, could this be the cause of the submission scoring error?",
      "votes": null
    },
    {
      "id": "1536636",
      "postDate": "10/06/2021 21:51:02",
      "content": "<p>As mentioned in the Code Competitions - Errors &amp; Debugging Tips page:</p>\n<p>Submission Scoring Error: Your notebook generated a submission file with an incorrect format. Some examples causing this are:  wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.</p>\n<p>check the number of rows (should be 87 rows) also check the name of the two columns of your submission file</p>",
      "rawMarkdown": "As mentioned in the Code Competitions - Errors & Debugging Tips page:\n\nSubmission Scoring Error: Your notebook generated a submission file with an incorrect format. Some examples causing this are:  wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.\n\ncheck the number of rows (should be 87 rows) also check the name of the two columns of your submission file",
      "votes": null
    },
    {
      "id": "1536791",
      "postDate": "10/07/2021 03:10:43",
      "content": "<p>I had the same problem Shawn. I maybe wrong for your case. In my case I used my png test data and not the .dcm test data. Now, here's why you should use the .dcm instead of .png, its because the private dataset is in the .dcm format and not in the .png format. And since you don't have a function converting .png to .dcm you get the error. At least, this was so in my case. Good luck :D</p>",
      "rawMarkdown": "I had the same problem Shawn. I maybe wrong for your case. In my case I used my png test data and not the .dcm test data. Now, here's why you should use the .dcm instead of .png, its because the private dataset is in the .dcm format and not in the .png format. And since you don't have a function converting .png to .dcm you get the error. At least, this was so in my case. Good luck :D",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1536636,
      "author_name": "hamzaghanmi",
      "author_url": "",
      "post_date": "10/06/2021 21:51:02",
      "content": "<p>As mentioned in the Code Competitions - Errors &amp; Debugging Tips page:</p>\n<p>Submission Scoring Error: Your notebook generated a submission file with an incorrect format. Some examples causing this are:  wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.</p>\n<p>check the number of rows (should be 87 rows) also check the name of the two columns of your submission file</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1536791,
      "author_name": "eddwait",
      "author_url": "",
      "post_date": "10/07/2021 03:10:43",
      "content": "<p>I had the same problem Shawn. I maybe wrong for your case. In my case I used my png test data and not the .dcm test data. Now, here's why you should use the .dcm instead of .png, its because the private dataset is in the .dcm format and not in the .png format. And since you don't have a function converting .png to .dcm you get the error. At least, this was so in my case. Good luck :D</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1536563": "We are generating a csv file named submission.csv in the kaggle output directory, yet are getting a submission scoring error when trying to submit. The notebook however runs successfully when we try to submit. We double checked the submission file and it is indeed in the right format. The only thing we can think of is that we are loading our model weights from a private dataset that we created, could this be the cause of the submission scoring error?",
    "1536636": "As mentioned in the Code Competitions - Errors & Debugging Tips page:\n\nSubmission Scoring Error: Your notebook generated a submission file with an incorrect format. Some examples causing this are:  wrong number of rows or columns, empty values, an incorrect data type for a value, or invalid submission values from what is expected.\n\ncheck the number of rows (should be 87 rows) also check the name of the two columns of your submission file",
    "1536791": "I had the same problem Shawn. I maybe wrong for your case. In my case I used my png test data and not the .dcm test data. Now, here's why you should use the .dcm instead of .png, its because the private dataset is in the .dcm format and not in the .png format. And since you don't have a function converting .png to .dcm you get the error. At least, this was so in my case. Good luck :D"
  },
  "source": "meta"
}