{
  "id": 373420,
  "title": "HOW TO USE TPU v3-8",
  "url": "/competitions/rsna-breast-cancer-detection/discussion/373420",
  "author_name": "happymentee",
  "post_date": "2022-12-21T12:03:55.071000",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I'm currently trying to use TPU v3-8 to train my model. I see that this TPU has 128GB RAM but when I use my notebook on this TPU, have has only 16GB.<br>\nI got stuck on using TPU quite a lot of time :&lt;. Could anyone explain that to me? <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd47670d7d82efc77f29d15f096e49c9a%2FScreenshot%202022-12-21%20190038.jpg?generation=1671624228384433&amp;alt=media\" alt=\"\"><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd8773ee06373fe8c997af5907c4fce09%2FScreenshot%202022-12-21%20190149.jpg?generation=1671624264242016&amp;alt=media\" alt=\"\"></p>",
  "messages": [
    {
      "id": 2071939,
      "postDate": "2022-12-21T14:33:22.583Z",
      "content": "<p>This notebook can be helpful :<br>\n<a href=\"https://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla\" target=\"_blank\">https://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla</a></p>",
      "rawMarkdown": "This notebook can be helpful :\nhttps://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla",
      "votes": 1
    },
    {
      "id": 2071792,
      "postDate": "2022-12-21T12:03:55.070Z",
      "content": "<p>I'm currently trying to use TPU v3-8 to train my model. I see that this TPU has 128GB RAM but when I use my notebook on this TPU, have has only 16GB.<br>\nI got stuck on using TPU quite a lot of time :&lt;. Could anyone explain that to me? <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd47670d7d82efc77f29d15f096e49c9a%2FScreenshot%202022-12-21%20190038.jpg?generation=1671624228384433&amp;alt=media\" alt=\"\"><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd8773ee06373fe8c997af5907c4fce09%2FScreenshot%202022-12-21%20190149.jpg?generation=1671624264242016&amp;alt=media\" alt=\"\"></p>",
      "rawMarkdown": "I'm currently trying to use TPU v3-8 to train my model. I see that this TPU has 128GB RAM but when I use my notebook on this TPU, have has only 16GB.\nI got stuck on using TPU quite a lot of time :<. Could anyone explain that to me? ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd47670d7d82efc77f29d15f096e49c9a%2FScreenshot%202022-12-21%20190038.jpg?generation=1671624228384433&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd8773ee06373fe8c997af5907c4fce09%2FScreenshot%202022-12-21%20190149.jpg?generation=1671624264242016&alt=media)",
      "votes": 1
    }
  ],
  "comments": [
    {
      "id": 2071939,
      "author_name": "moth",
      "author_url": "",
      "post_date": "2022-12-21T14:33:22.583000",
      "content": "<p>This notebook can be helpful :<br>\n<a href=\"https://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla\" target=\"_blank\">https://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla</a></p>",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2071939": "This notebook can be helpful :\nhttps://www.kaggle.com/code/tanulsingh077/pytorch-xla-understanding-tpu-s-and-xla",
    "2071792": "I'm currently trying to use TPU v3-8 to train my model. I see that this TPU has 128GB RAM but when I use my notebook on this TPU, have has only 16GB.\nI got stuck on using TPU quite a lot of time :<. Could anyone explain that to me? ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd47670d7d82efc77f29d15f096e49c9a%2FScreenshot%202022-12-21%20190038.jpg?generation=1671624228384433&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F6230460%2Fd8773ee06373fe8c997af5907c4fce09%2FScreenshot%202022-12-21%20190149.jpg?generation=1671624264242016&alt=media)"
  }
}