{
  "id": 188172,
  "title": "Torch can not find GPU after GPU is switched on",
  "url": "/competitions/lyft-motion-prediction-autonomous-vehicles/discussion/188172",
  "author_name": "",
  "post_date": "2020-10-02T04:18:51.979580700Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1187149%2F08b1a13049104dc1bc4978b5f09583a2%2FScreenshot%202020-10-02%20at%2012.17.06%20PM.png?generation=1601612244399386&amp;alt=media\" alt=\"1\"></p>\n<p>Hi, I've tried to use gpu, but clearly the <code>torch.cuda.device_count()</code> is showing there is no GPU detected, however when I try tensorflow, it did find GPU device. And also in the training process, I can see from the vertical bar no GPU resource is being used, anyone has idea why?</p>",
  "messages": [
    {
      "id": "1034665",
      "postDate": "10/02/2020 04:18:51",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1187149%2F08b1a13049104dc1bc4978b5f09583a2%2FScreenshot%202020-10-02%20at%2012.17.06%20PM.png?generation=1601612244399386&amp;alt=media\" alt=\"1\"></p>\n<p>Hi, I've tried to use gpu, but clearly the <code>torch.cuda.device_count()</code> is showing there is no GPU detected, however when I try tensorflow, it did find GPU device. And also in the training process, I can see from the vertical bar no GPU resource is being used, anyone has idea why?</p>",
      "rawMarkdown": "![1](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1187149%2F08b1a13049104dc1bc4978b5f09583a2%2FScreenshot%202020-10-02%20at%2012.17.06%20PM.png?generation=1601612244399386&alt=media)\n\nHi, I've tried to use gpu, but clearly the `torch.cuda.device_count()` is showing there is no GPU detected, however when I try tensorflow, it did find GPU device. And also in the training process, I can see from the vertical bar no GPU resource is being used, anyone has idea why?",
      "votes": null
    },
    {
      "id": "1034995",
      "postDate": "10/02/2020 11:17:00",
      "content": "<p>this is probably a dublicate from <a href=\"https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177125\" target=\"_blank\">here</a></p>\n<p>The easiest solution in my opinion is this</p>\n<ol>\n<li>dont use the provided l5kit utils (those are causing the error as they are loaded into the working directory)</li>\n<li>instead, install l5kit via pip</li>\n</ol>\n<pre><code>!pip uninstall -y typing\n!pip install l5kit\n</code></pre>",
      "rawMarkdown": "this is probably a dublicate from [here](https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177125)\n\nThe easiest solution in my opinion is this\n1. dont use the provided l5kit utils (those are causing the error as they are loaded into the working directory)\n2. instead, install l5kit via pip\n```\n!pip uninstall -y typing\n!pip install l5kit\n```",
      "votes": null
    },
    {
      "id": "1037427",
      "postDate": "10/05/2020 02:40:58",
      "content": "<p>thanks a lot, it worked</p>",
      "rawMarkdown": "thanks a lot, it worked",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1034995,
      "author_name": "ilu000",
      "author_url": "",
      "post_date": "10/02/2020 11:17:00",
      "content": "<p>this is probably a dublicate from <a href=\"https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177125\" target=\"_blank\">here</a></p>\n<p>The easiest solution in my opinion is this</p>\n<ol>\n<li>dont use the provided l5kit utils (those are causing the error as they are loaded into the working directory)</li>\n<li>instead, install l5kit via pip</li>\n</ol>\n<pre><code>!pip uninstall -y typing\n!pip install l5kit\n</code></pre>",
      "votes": null,
      "replies": [
        {
          "id": 1037427,
          "author_name": "zhangyue199",
          "author_url": "",
          "post_date": "10/05/2020 02:40:58",
          "content": "<p>thanks a lot, it worked</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1034665": "![1](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1187149%2F08b1a13049104dc1bc4978b5f09583a2%2FScreenshot%202020-10-02%20at%2012.17.06%20PM.png?generation=1601612244399386&alt=media)\n\nHi, I've tried to use gpu, but clearly the `torch.cuda.device_count()` is showing there is no GPU detected, however when I try tensorflow, it did find GPU device. And also in the training process, I can see from the vertical bar no GPU resource is being used, anyone has idea why?",
    "1034995": "this is probably a dublicate from [here](https://www.kaggle.com/c/lyft-motion-prediction-autonomous-vehicles/discussion/177125)\n\nThe easiest solution in my opinion is this\n1. dont use the provided l5kit utils (those are causing the error as they are loaded into the working directory)\n2. instead, install l5kit via pip\n```\n!pip uninstall -y typing\n!pip install l5kit\n```",
    "1037427": "thanks a lot, it worked"
  },
  "source": "meta"
}