{
  "id": 406173,
  "title": "Question about hardware specifications",
  "url": "/competitions/vesuvius-challenge-ink-detection/discussion/406173",
  "author_name": "",
  "post_date": "2023-05-01T07:48:04.612127800Z",
  "votes": null,
  "comment_count": 4,
  "views": 0,
  "content": "<p>When I edit my inference code on kaggle notebook, only 13GB CPU RAM is available.<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9735064%2F7078281daa2e1638e1e906e2f20a62b8%2F1.png?generation=1682927184140390&amp;alt=media\" alt=\"13GB RAM\"><br>\nBut I have found <a href=\"https://www.kaggle.com/docs/notebooks#technical-specifications\" target=\"_blank\">notebooks technical specifications</a> showing 30GB CPU RAM available.<br>\nSo do our submissions run on the 30GB RAM CPU specification?</p>",
  "messages": [
    {
      "id": "2241104",
      "postDate": "05/01/2023 07:48:04",
      "content": "<p>When I edit my inference code on kaggle notebook, only 13GB CPU RAM is available.<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9735064%2F7078281daa2e1638e1e906e2f20a62b8%2F1.png?generation=1682927184140390&amp;alt=media\" alt=\"13GB RAM\"><br>\nBut I have found <a href=\"https://www.kaggle.com/docs/notebooks#technical-specifications\" target=\"_blank\">notebooks technical specifications</a> showing 30GB CPU RAM available.<br>\nSo do our submissions run on the 30GB RAM CPU specification?</p>",
      "rawMarkdown": "When I edit my inference code on kaggle notebook, only 13GB CPU RAM is available.\n![13GB RAM](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9735064%2F7078281daa2e1638e1e906e2f20a62b8%2F1.png?generation=1682927184140390&alt=media)\nBut I have found [notebooks technical specifications](https://www.kaggle.com/docs/notebooks#technical-specifications) showing 30GB CPU RAM available.\nSo do our submissions run on the 30GB RAM CPU specification?",
      "votes": null
    },
    {
      "id": "2241122",
      "postDate": "05/01/2023 08:07:43",
      "content": "<p>from the link you shared:</p>\n<pre><code>CPU Specifications\n CPU cores\n Gigabytes of RAM\n\nP100 GPU Specifications\n Nvidia Telsa P100 GPU\n CPU cores\n Gigabytes of RAM\n</code></pre>\n<p>30GB is available for the CPU instance, while for the GPU 13GB</p>",
      "rawMarkdown": "from the link you shared:\n\n```python\nCPU Specifications\n4 CPU cores\n30 Gigabytes of RAM\n\nP100 GPU Specifications\n1 Nvidia Telsa P100 GPU\n2 CPU cores\n13 Gigabytes of RAM\n```\n30GB is available for the CPU instance, while for the GPU 13GB",
      "votes": null
    },
    {
      "id": "2241134",
      "postDate": "05/01/2023 08:18:53",
      "content": "<p>thanks for such quick response!<br>\nyeah, even there is little difference on P100 GPU RAM between notebook edition interface and the notebook doc.<br>\nso, when we submit our notebook, it is actually running on a 30GB RAM CPU, but why there are differences between them?</p>",
      "rawMarkdown": "thanks for such quick response!\nyeah, even there is little difference on P100 GPU RAM between notebook edition interface and the notebook doc.\nso, when we submit our notebook, it is actually running on a 30GB RAM CPU, but why there are differences between them?",
      "votes": null
    },
    {
      "id": "2241480",
      "postDate": "05/01/2023 14:34:32",
      "content": "<p>If you specified in your notebook the CPU instance (without a GPU/TPU) it will run everything without the GPU/TPU (submit + hidden test) on the instance with 30GB of RAM and 4 core CPU, if you prefer to run with a GPU/TPU and specify GPU/TPU instance it will have parameters of the GPU instance with 13GB of RAM and 2 core CPU.</p>",
      "rawMarkdown": "If you specified in your notebook the CPU instance (without a GPU/TPU) it will run everything without the GPU/TPU (submit + hidden test) on the instance with 30GB of RAM and 4 core CPU, if you prefer to run with a GPU/TPU and specify GPU/TPU instance it will have parameters of the GPU instance with 13GB of RAM and 2 core CPU.",
      "votes": null
    },
    {
      "id": "2242004",
      "postDate": "05/02/2023 01:56:45",
      "content": "<p>got it, thanks!</p>",
      "rawMarkdown": "got it, thanks!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2241122,
      "author_name": "igorkrashenyi",
      "author_url": "",
      "post_date": "05/01/2023 08:07:43",
      "content": "<p>from the link you shared:</p>\n<pre><code>CPU Specifications\n CPU cores\n Gigabytes of RAM\n\nP100 GPU Specifications\n Nvidia Telsa P100 GPU\n CPU cores\n Gigabytes of RAM\n</code></pre>\n<p>30GB is available for the CPU instance, while for the GPU 13GB</p>",
      "votes": null,
      "replies": [
        {
          "id": 2241134,
          "author_name": "traptinblur",
          "author_url": "",
          "post_date": "05/01/2023 08:18:53",
          "content": "<p>thanks for such quick response!<br>\nyeah, even there is little difference on P100 GPU RAM between notebook edition interface and the notebook doc.<br>\nso, when we submit our notebook, it is actually running on a 30GB RAM CPU, but why there are differences between them?</p>",
          "votes": null,
          "replies": [
            {
              "id": 2241480,
              "author_name": "igorkrashenyi",
              "author_url": "",
              "post_date": "05/01/2023 14:34:32",
              "content": "<p>If you specified in your notebook the CPU instance (without a GPU/TPU) it will run everything without the GPU/TPU (submit + hidden test) on the instance with 30GB of RAM and 4 core CPU, if you prefer to run with a GPU/TPU and specify GPU/TPU instance it will have parameters of the GPU instance with 13GB of RAM and 2 core CPU.</p>",
              "votes": null,
              "replies": [
                {
                  "id": 2242004,
                  "author_name": "traptinblur",
                  "author_url": "",
                  "post_date": "05/02/2023 01:56:45",
                  "content": "<p>got it, thanks!</p>",
                  "votes": null,
                  "replies": []
                }
              ]
            }
          ]
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2241104": "When I edit my inference code on kaggle notebook, only 13GB CPU RAM is available.\n![13GB RAM](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F9735064%2F7078281daa2e1638e1e906e2f20a62b8%2F1.png?generation=1682927184140390&alt=media)\nBut I have found [notebooks technical specifications](https://www.kaggle.com/docs/notebooks#technical-specifications) showing 30GB CPU RAM available.\nSo do our submissions run on the 30GB RAM CPU specification?",
    "2241122": "from the link you shared:\n\n```python\nCPU Specifications\n4 CPU cores\n30 Gigabytes of RAM\n\nP100 GPU Specifications\n1 Nvidia Telsa P100 GPU\n2 CPU cores\n13 Gigabytes of RAM\n```\n30GB is available for the CPU instance, while for the GPU 13GB",
    "2241134": "thanks for such quick response!\nyeah, even there is little difference on P100 GPU RAM between notebook edition interface and the notebook doc.\nso, when we submit our notebook, it is actually running on a 30GB RAM CPU, but why there are differences between them?",
    "2241480": "If you specified in your notebook the CPU instance (without a GPU/TPU) it will run everything without the GPU/TPU (submit + hidden test) on the instance with 30GB of RAM and 4 core CPU, if you prefer to run with a GPU/TPU and specify GPU/TPU instance it will have parameters of the GPU instance with 13GB of RAM and 2 core CPU.",
    "2242004": "got it, thanks!"
  },
  "source": "meta"
}