{
  "id": 269272,
  "title": "How can I load data into my model?",
  "url": "/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/269272",
  "author_name": "",
  "post_date": "2021-08-31T01:54:57.416121500Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Hello guys, I was wondering how can I load the data into my model? The number of images (if converted to video) varies from one class to another and therefore the size of the array differs. If I were to use only few images (like 8) then I won't be incorporating the full data. Please help me, I have been struggling with it for a while now. Thank you!</p>",
  "messages": [
    {
      "id": "1497150",
      "postDate": "08/31/2021 01:54:57",
      "content": "<p>Hello guys, I was wondering how can I load the data into my model? The number of images (if converted to video) varies from one class to another and therefore the size of the array differs. If I were to use only few images (like 8) then I won't be incorporating the full data. Please help me, I have been struggling with it for a while now. Thank you!</p>",
      "rawMarkdown": "Hello guys, I was wondering how can I load the data into my model? The number of images (if converted to video) varies from one class to another and therefore the size of the array differs. If I were to use only few images (like 8) then I won't be incorporating the full data. Please help me, I have been struggling with it for a while now. Thank you!",
      "votes": null
    },
    {
      "id": "1497305",
      "postDate": "08/31/2021 06:01:57",
      "content": "<p>Most people are resizing their data all into the same shape. For example if you have only 8 images then you could pad with empty images. Or if you have too many images, then you take the images in the middle. Or you can interpolate. Check out the function <code>load_dicom_images_3d</code> from this kernel: <a href=\"https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments\" target=\"_blank\">https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments</a> it's a good baseline to get started.</p>",
      "rawMarkdown": "Most people are resizing their data all into the same shape. For example if you have only 8 images then you could pad with empty images. Or if you have too many images, then you take the images in the middle. Or you can interpolate. Check out the function `load_dicom_images_3d` from this kernel: https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments it's a good baseline to get started.",
      "votes": null
    },
    {
      "id": "1497325",
      "postDate": "08/31/2021 06:20:08",
      "content": "<p>Thank you for your input Mr. Corey Levinson :D</p>",
      "rawMarkdown": "Thank you for your input Mr. Corey Levinson :D",
      "votes": null
    },
    {
      "id": "1500339",
      "postDate": "09/02/2021 09:47:37",
      "content": "<p>Also this includes <a href=\"https://www.kaggle.com/experienceinai/aivo-vii-nopea\" target=\"_blank\">https://www.kaggle.com/experienceinai/aivo-vii-nopea</a> easy functions for loading data (only small set for small testing but the whole dataset if you need and have more time to wait to get final results). </p>",
      "rawMarkdown": "Also this includes https://www.kaggle.com/experienceinai/aivo-vii-nopea easy functions for loading data (only small set for small testing but the whole dataset if you need and have more time to wait to get final results).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1497305,
      "author_name": "returnofsputnik",
      "author_url": "",
      "post_date": "08/31/2021 06:01:57",
      "content": "<p>Most people are resizing their data all into the same shape. For example if you have only 8 images then you could pad with empty images. Or if you have too many images, then you take the images in the middle. Or you can interpolate. Check out the function <code>load_dicom_images_3d</code> from this kernel: <a href=\"https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments\" target=\"_blank\">https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments</a> it's a good baseline to get started.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1497325,
          "author_name": "eddwait",
          "author_url": "",
          "post_date": "08/31/2021 06:20:08",
          "content": "<p>Thank you for your input Mr. Corey Levinson :D</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1500339,
      "author_name": "experienceinai",
      "author_url": "",
      "post_date": "09/02/2021 09:47:37",
      "content": "<p>Also this includes <a href=\"https://www.kaggle.com/experienceinai/aivo-vii-nopea\" target=\"_blank\">https://www.kaggle.com/experienceinai/aivo-vii-nopea</a> easy functions for loading data (only small set for small testing but the whole dataset if you need and have more time to wait to get final results). </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1497150": "Hello guys, I was wondering how can I load the data into my model? The number of images (if converted to video) varies from one class to another and therefore the size of the array differs. If I were to use only few images (like 8) then I won't be incorporating the full data. Please help me, I have been struggling with it for a while now. Thank you!",
    "1497305": "Most people are resizing their data all into the same shape. For example if you have only 8 images then you could pad with empty images. Or if you have too many images, then you take the images in the middle. Or you can interpolate. Check out the function `load_dicom_images_3d` from this kernel: https://www.kaggle.com/rluethy/efficientnet3d-with-one-mri-type/comments it's a good baseline to get started.",
    "1497325": "Thank you for your input Mr. Corey Levinson :D",
    "1500339": "Also this includes https://www.kaggle.com/experienceinai/aivo-vii-nopea easy functions for loading data (only small set for small testing but the whole dataset if you need and have more time to wait to get final results)."
  },
  "source": "meta"
}