{
  "id": 457255,
  "title": "Is it overfitting my model !?",
  "url": "/competitions/UBC-OCEAN/discussion/457255",
  "author_name": "Aditya Parikh",
  "post_date": "2023-11-23T18:34:45.202000",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hello Kagglers!</p>\n<p>Having a CNN feature extractor and using a XGB on top of it overfitting my model? <br>\nShould I just have a small cnn head over it !?</p>",
  "messages": [
    {
      "id": 2542858,
      "postDate": "2023-11-29T15:06:35.710Z",
      "content": "<p>While training split your data into train and validation sets or even use Cross Validation if your training time is not extremely high.  Then just assess how the validation performance improves and once the validation performance decreases you have entered the point of overfitting.</p>",
      "rawMarkdown": "While training split your data into train and validation sets or even use Cross Validation if your training time is not extremely high.  Then just assess how the validation performance improves and once the validation performance decreases you have entered the point of overfitting.",
      "votes": 1
    },
    {
      "id": 2535941,
      "postDate": "2023-11-23T19:09:18.667Z",
      "content": "<p>It depends, we do not know what is in the test data. In order to check if it is overfitting or not you can split data into train/validation subsets and then test how well it performs on validation</p>",
      "rawMarkdown": "It depends, we do not know what is in the test data. In order to check if it is overfitting or not you can split data into train/validation subsets and then test how well it performs on validation",
      "votes": 1
    },
    {
      "id": 2535912,
      "postDate": "2023-11-23T18:34:45.203Z",
      "content": "<p>Hello Kagglers!</p>\n<p>Having a CNN feature extractor and using a XGB on top of it overfitting my model? <br>\nShould I just have a small cnn head over it !?</p>",
      "rawMarkdown": "Hello Kagglers!\n\nHaving a CNN feature extractor and using a XGB on top of it overfitting my model? \nShould I just have a small cnn head over it !?",
      "votes": 2
    }
  ],
  "comments": [
    {
      "id": 2542858,
      "author_name": "Connor",
      "author_url": "",
      "post_date": "2023-11-29T15:06:35.710000",
      "content": "<p>While training split your data into train and validation sets or even use Cross Validation if your training time is not extremely high.  Then just assess how the validation performance improves and once the validation performance decreases you have entered the point of overfitting.</p>",
      "votes": 1,
      "replies": []
    },
    {
      "id": 2535941,
      "author_name": "Ramil Khafizov",
      "author_url": "",
      "post_date": "2023-11-23T19:09:18.667000",
      "content": "<p>It depends, we do not know what is in the test data. In order to check if it is overfitting or not you can split data into train/validation subsets and then test how well it performs on validation</p>",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2542858": "While training split your data into train and validation sets or even use Cross Validation if your training time is not extremely high.  Then just assess how the validation performance improves and once the validation performance decreases you have entered the point of overfitting.",
    "2535941": "It depends, we do not know what is in the test data. In order to check if it is overfitting or not you can split data into train/validation subsets and then test how well it performs on validation",
    "2535912": "Hello Kagglers!\n\nHaving a CNN feature extractor and using a XGB on top of it overfitting my model? \nShould I just have a small cnn head over it !?"
  }
}