{
  "id": 156405,
  "title": "Advice Needed !!",
  "url": "/competitions/siim-isic-melanoma-classification/discussion/156405",
  "author_name": "Anshul Sharma",
  "post_date": "2020-06-05T21:31:51.592000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>I have tried tried to extract features from the images and then used those along with tabular data to make predictions using LGBM. The maximum score I could achieve is 0.892. Here’s a link to my notebook: <a href=\"https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm\">https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm</a></p>\n\n<p>How should I proceed forward\n- use encodings from 512x512 images instead of 256x256 images\n- use stacking to improve the score further\n- or a completely new way that I haven’t thought of </p>\n\n<p>Thanks in advance :)</p>",
  "messages": [
    {
      "id": 875511,
      "postDate": "2020-06-05T21:31:51.593Z",
      "content": "<p>Hi,</p>\n\n<p>I have tried tried to extract features from the images and then used those along with tabular data to make predictions using LGBM. The maximum score I could achieve is 0.892. Here’s a link to my notebook: <a href=\"https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm\">https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm</a></p>\n\n<p>How should I proceed forward\n- use encodings from 512x512 images instead of 256x256 images\n- use stacking to improve the score further\n- or a completely new way that I haven’t thought of </p>\n\n<p>Thanks in advance :)</p>",
      "rawMarkdown": "Hi,\n\nI have tried tried to extract features from the images and then used those along with tabular data to make predictions using LGBM. The maximum score I could achieve is 0.892. Here’s a link to my notebook: https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm\n\nHow should I proceed forward\n- use encodings from 512x512 images instead of 256x256 images\n- use stacking to improve the score further\n- or a completely new way that I haven’t thought of \n\nThanks in advance :)",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "875511": "Hi,\n\nI have tried tried to extract features from the images and then used those along with tabular data to make predictions using LGBM. The maximum score I could achieve is 0.892. Here’s a link to my notebook: https://www.kaggle.com/anshuls235/melanoma-eda-prediction-using-lightgbm\n\nHow should I proceed forward\n- use encodings from 512x512 images instead of 256x256 images\n- use stacking to improve the score further\n- or a completely new way that I haven’t thought of \n\nThanks in advance :)"
  }
}