{
  "id": 403423,
  "title": "Can We use gpu to improve training time when we use xgboost",
  "url": "/competitions/tlvmc-parkinsons-freezing-gait-prediction/discussion/403423",
  "author_name": "",
  "post_date": "2023-04-23T03:00:43.333226600Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi, everyone,</p>\n<p>I try to use xgboost in kaggle enveriment, and I intend to use accelerator to speed up training time. But when I select accelerator, I get </p>\n<blockquote>\n  <p>Turning on GPU T4 x2/P100 will reduce the number of CPUs available and will only speed up image processing and neural networks.</p>\n</blockquote>\n<p>So I'm not sure if gpu can use for xgb. According to the description, maybe we can't?😅</p>",
  "messages": [
    {
      "id": "2231028",
      "postDate": "04/23/2023 03:00:43",
      "content": "<p>Hi, everyone,</p>\n<p>I try to use xgboost in kaggle enveriment, and I intend to use accelerator to speed up training time. But when I select accelerator, I get </p>\n<blockquote>\n  <p>Turning on GPU T4 x2/P100 will reduce the number of CPUs available and will only speed up image processing and neural networks.</p>\n</blockquote>\n<p>So I'm not sure if gpu can use for xgb. According to the description, maybe we can't?😅</p>",
      "rawMarkdown": "Hi, everyone,\n\nI try to use xgboost in kaggle enveriment, and I intend to use accelerator to speed up training time. But when I select accelerator, I get \n> Turning on GPU T4 x2/P100 will reduce the number of CPUs available and will only speed up image processing and neural networks.\n\nSo I'm not sure if gpu can use for xgb. According to the description, maybe we can't?😅",
      "votes": null
    },
    {
      "id": "2231619",
      "postDate": "04/23/2023 13:30:54",
      "content": "<p>We could use a GPU to good effect for ML models like XGboost. Just use P100 and turn on the GPU using <code>tree_method = 'gpu_hist'</code> <a href=\"https://www.kaggle.com/roger92\" target=\"_blank\">@roger92</a> </p>",
      "rawMarkdown": "We could use a GPU to good effect for ML models like XGboost. Just use P100 and turn on the GPU using `tree_method = 'gpu_hist'` @roger92",
      "votes": null
    },
    {
      "id": "2232086",
      "postDate": "04/24/2023 02:22:52",
      "content": "<p>thank you, I will try later😄</p>",
      "rawMarkdown": "thank you, I will try later😄",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2231619,
      "author_name": "ravi20076",
      "author_url": "",
      "post_date": "04/23/2023 13:30:54",
      "content": "<p>We could use a GPU to good effect for ML models like XGboost. Just use P100 and turn on the GPU using <code>tree_method = 'gpu_hist'</code> <a href=\"https://www.kaggle.com/roger92\" target=\"_blank\">@roger92</a> </p>",
      "votes": null,
      "replies": [
        {
          "id": 2232086,
          "author_name": "roger92",
          "author_url": "",
          "post_date": "04/24/2023 02:22:52",
          "content": "<p>thank you, I will try later😄</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2231028": "Hi, everyone,\n\nI try to use xgboost in kaggle enveriment, and I intend to use accelerator to speed up training time. But when I select accelerator, I get \n> Turning on GPU T4 x2/P100 will reduce the number of CPUs available and will only speed up image processing and neural networks.\n\nSo I'm not sure if gpu can use for xgb. According to the description, maybe we can't?😅",
    "2231619": "We could use a GPU to good effect for ML models like XGboost. Just use P100 and turn on the GPU using `tree_method = 'gpu_hist'` @roger92",
    "2232086": "thank you, I will try later😄"
  },
  "source": "meta"
}