{
  "id": 72342,
  "title": "Data Processing on external GPU",
  "url": "/competitions/ga-customer-revenue-prediction/discussion/72342",
  "author_name": "",
  "post_date": "2018-11-22T11:36:45.163049800Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>Can you clarify whether one can upload the competition data on AWS or any other cloud services like Google cloud on private mode to get the GPU processing ?,  as unable to process the data on the kaggle kernel after 1 hour spending Kernel died?</p>\n\n<p>Please help.</p>",
  "messages": [
    {
      "id": "425983",
      "postDate": "11/22/2018 11:36:45",
      "content": "<p>Hi,</p>\n\n<p>Can you clarify whether one can upload the competition data on AWS or any other cloud services like Google cloud on private mode to get the GPU processing ?,  as unable to process the data on the kaggle kernel after 1 hour spending Kernel died?</p>\n\n<p>Please help.</p>",
      "rawMarkdown": "Hi,\n\nCan you clarify whether one can upload the competition data on AWS or any other cloud services like Google cloud on private mode to get the GPU processing ?,  as unable to process the data on the kaggle kernel after 1 hour spending Kernel died?\n\nPlease help.",
      "votes": null
    },
    {
      "id": "425999",
      "postDate": "11/22/2018 12:19:30",
      "content": "<p>It depends on which python package you use, if you use xgboost or lightgbm, it need to be built by source manually. Tensorflow would be lot more easy on Google colab.   </p>",
      "rawMarkdown": "It depends on which python package you use, if you use xgboost or lightgbm, it need to be built by source manually. Tensorflow would be lot more easy on Google colab.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 425999,
      "author_name": "diaper151",
      "author_url": "",
      "post_date": "11/22/2018 12:19:30",
      "content": "<p>It depends on which python package you use, if you use xgboost or lightgbm, it need to be built by source manually. Tensorflow would be lot more easy on Google colab.   </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "425983": "Hi,\n\nCan you clarify whether one can upload the competition data on AWS or any other cloud services like Google cloud on private mode to get the GPU processing ?,  as unable to process the data on the kaggle kernel after 1 hour spending Kernel died?\n\nPlease help.",
    "425999": "It depends on which python package you use, if you use xgboost or lightgbm, it need to be built by source manually. Tensorflow would be lot more easy on Google colab."
  },
  "source": "meta"
}