{
  "id": 264588,
  "title": "Some Useful external Datasets Used helped boost score",
  "url": "/competitions/siim-covid19-detection/discussion/264588",
  "author_name": "Jaideep",
  "post_date": "2021-08-12T14:54:06.786000",
  "votes": 7,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Belo are some of the datasets i prepared  to train models with more data. <br>\nI regret i dint use much of RSNA data that would helped move .001 up in LB to come in gold range. </p>\n<p>If any one wants to make use of this as part post competition practice make use of this to see if they are useful for you.</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/bimcv-dataset\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/bimcv-dataset</a>        </p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/dataset\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/dataset</a>   -Vinbig Supposedly Atypical case<br>\n<a href=\"https://www.kaggle.com/jaideepvalani/vinbig-indeterminate\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/vinbig-indeterminate</a>  -Vinbig Supposedly indeterminate  </p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/ricord-downscale\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/ricord-downscale</a>  -downscaled by 2<br>\n<a href=\"https://www.kaggle.com/jaideepvalani/ricord-pl-035-045\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/ricord-pl-035-045</a>   -PLs</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-normal-images\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-normal-images</a>  -Normal Images using more of these should have helped more  I used only 500 of these,still get boost of 0.001</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/vin-big-opacity\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/vin-big-opacity</a>   -Opacity Class of Vin Big</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-p-train\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-p-train</a> -RSNA P images</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-meta-data\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-meta-data</a>  -csv containing the list of Hi and Med Prob Pneumonia images as per list uploaded by host</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/test-ds-pl\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/test-ds-pl</a>  -Test data PL and downscaled images</p>",
  "messages": [
    {
      "id": 1468739,
      "postDate": "2021-08-12T14:54:06.787Z",
      "content": "<p>Belo are some of the datasets i prepared  to train models with more data. <br>\nI regret i dint use much of RSNA data that would helped move .001 up in LB to come in gold range. </p>\n<p>If any one wants to make use of this as part post competition practice make use of this to see if they are useful for you.</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/bimcv-dataset\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/bimcv-dataset</a>        </p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/dataset\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/dataset</a>   -Vinbig Supposedly Atypical case<br>\n<a href=\"https://www.kaggle.com/jaideepvalani/vinbig-indeterminate\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/vinbig-indeterminate</a>  -Vinbig Supposedly indeterminate  </p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/ricord-downscale\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/ricord-downscale</a>  -downscaled by 2<br>\n<a href=\"https://www.kaggle.com/jaideepvalani/ricord-pl-035-045\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/ricord-pl-035-045</a>   -PLs</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-normal-images\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-normal-images</a>  -Normal Images using more of these should have helped more  I used only 500 of these,still get boost of 0.001</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/vin-big-opacity\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/vin-big-opacity</a>   -Opacity Class of Vin Big</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-p-train\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-p-train</a> -RSNA P images</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/rsna-meta-data\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/rsna-meta-data</a>  -csv containing the list of Hi and Med Prob Pneumonia images as per list uploaded by host</p>\n<p><a href=\"https://www.kaggle.com/jaideepvalani/test-ds-pl\" target=\"_blank\">https://www.kaggle.com/jaideepvalani/test-ds-pl</a>  -Test data PL and downscaled images</p>",
      "rawMarkdown": "Belo are some of the datasets i prepared  to train models with more data. \nI regret i dint use much of RSNA data that would helped move .001 up in LB to come in gold range. \n\nIf any one wants to make use of this as part post competition practice make use of this to see if they are useful for you.\n\n\nhttps://www.kaggle.com/jaideepvalani/bimcv-dataset        \n\nhttps://www.kaggle.com/jaideepvalani/dataset   -Vinbig Supposedly Atypical case\nhttps://www.kaggle.com/jaideepvalani/vinbig-indeterminate  -Vinbig Supposedly indeterminate  \n\nhttps://www.kaggle.com/jaideepvalani/ricord-downscale  -downscaled by 2\nhttps://www.kaggle.com/jaideepvalani/ricord-pl-035-045   -PLs\n\nhttps://www.kaggle.com/jaideepvalani/rsna-normal-images  -Normal Images using more of these should have helped more  I used only 500 of these,still get boost of 0.001\n\nhttps://www.kaggle.com/jaideepvalani/vin-big-opacity   -Opacity Class of Vin Big\n\nhttps://www.kaggle.com/jaideepvalani/rsna-p-train -RSNA P images\n\nhttps://www.kaggle.com/jaideepvalani/rsna-meta-data  -csv containing the list of Hi and Med Prob Pneumonia images as per list uploaded by host\n\nhttps://www.kaggle.com/jaideepvalani/test-ds-pl  -Test data PL and downscaled images\n",
      "votes": 7
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1468739": "Belo are some of the datasets i prepared  to train models with more data. \nI regret i dint use much of RSNA data that would helped move .001 up in LB to come in gold range. \n\nIf any one wants to make use of this as part post competition practice make use of this to see if they are useful for you.\n\n\nhttps://www.kaggle.com/jaideepvalani/bimcv-dataset        \n\nhttps://www.kaggle.com/jaideepvalani/dataset   -Vinbig Supposedly Atypical case\nhttps://www.kaggle.com/jaideepvalani/vinbig-indeterminate  -Vinbig Supposedly indeterminate  \n\nhttps://www.kaggle.com/jaideepvalani/ricord-downscale  -downscaled by 2\nhttps://www.kaggle.com/jaideepvalani/ricord-pl-035-045   -PLs\n\nhttps://www.kaggle.com/jaideepvalani/rsna-normal-images  -Normal Images using more of these should have helped more  I used only 500 of these,still get boost of 0.001\n\nhttps://www.kaggle.com/jaideepvalani/vin-big-opacity   -Opacity Class of Vin Big\n\nhttps://www.kaggle.com/jaideepvalani/rsna-p-train -RSNA P images\n\nhttps://www.kaggle.com/jaideepvalani/rsna-meta-data  -csv containing the list of Hi and Med Prob Pneumonia images as per list uploaded by host\n\nhttps://www.kaggle.com/jaideepvalani/test-ds-pl  -Test data PL and downscaled images\n"
  }
}