{
  "id": 60740,
  "title": "Paperspace Suggestion",
  "url": "/competitions/google-ai-open-images-object-detection-track/discussion/60740",
  "author_name": "",
  "post_date": "2018-07-09T09:29:29.257456700Z",
  "votes": 4,
  "comment_count": 9,
  "views": 0,
  "content": "<p>I want to participate in this competition, given the size of the dataset and the complexity of the problem, I've decided to use Paperspace's P4000 instance. I've never used Paperspace before but I'm all ready to bet on it for this competition.</p>\n\n<p>I just want to know if anyone could suggest me which instances would be enough/sufficient for me.</p>\n\n<p>Thanks</p>",
  "messages": [
    {
      "id": "354304",
      "postDate": "07/09/2018 09:29:29",
      "content": "<p>I want to participate in this competition, given the size of the dataset and the complexity of the problem, I've decided to use Paperspace's P4000 instance. I've never used Paperspace before but I'm all ready to bet on it for this competition.</p>\n\n<p>I just want to know if anyone could suggest me which instances would be enough/sufficient for me.</p>\n\n<p>Thanks</p>",
      "rawMarkdown": "I want to participate in this competition, given the size of the dataset and the complexity of the problem, I've decided to use Paperspace's P4000 instance. I've never used Paperspace before but I'm all ready to bet on it for this competition.\n\nI just want to know if anyone could suggest me which instances would be enough/sufficient for me.\n\nThanks",
      "votes": null
    },
    {
      "id": "354316",
      "postDate": "07/09/2018 10:01:56",
      "content": "<p>P4000 is more than enough. If you're using paperspace though, FastAI has a public template over there which is already all setup for use, and you'll be good to go in about 10-15 mins dodging nearly 1-2hrs of man hours setting up CUDA libraries to use GPU.</p>",
      "rawMarkdown": "P4000 is more than enough. If you're using paperspace though, FastAI has a public template over there which is already all setup for use, and you'll be good to go in about 10-15 mins dodging nearly 1-2hrs of man hours setting up CUDA libraries to use GPU.",
      "votes": null
    },
    {
      "id": "354329",
      "postDate": "07/09/2018 10:19:13",
      "content": "<p>Yeah, I'll use fast.ai template. Thanks :)</p>",
      "rawMarkdown": "Yeah, I'll use fast.ai template. Thanks :)",
      "votes": null
    },
    {
      "id": "354679",
      "postDate": "07/10/2018 03:48:53",
      "content": "<p>Dan here from Paperspace -- let me know if you need to be approved for any GPUs (part of our fraud prevention step).  Feel free to send me an email to dan@ Good luck with the competition btw!</p>",
      "rawMarkdown": "Dan here from Paperspace -- let me know if you need to be approved for any GPUs (part of our fraud prevention step).  Feel free to send me an email to dan@ Good luck with the competition btw!",
      "votes": null
    },
    {
      "id": "354937",
      "postDate": "07/10/2018 14:19:16",
      "content": "<p>Also if you are looking for an easy to use setup I'd suggest to go with <a href=\"https://neptune.ml/\">neptune.ml</a></p>\n\n<p>The data for this competition has already been uploaded so you can start with working in a matter of minutes.</p>\n\n<p>(Disclaimer I am working at neptune.ml)</p>",
      "rawMarkdown": "Also if you are looking for an easy to use setup I'd suggest to go with [neptune.ml](https://neptune.ml/)\n\nThe data for this competition has already been uploaded so you can start with working in a matter of minutes.\n\n(Disclaimer I am working at neptune.ml)",
      "votes": null
    },
    {
      "id": "355029",
      "postDate": "07/10/2018 18:14:59",
      "content": "<p>Good Luck To You</p>",
      "rawMarkdown": "Good Luck To You",
      "votes": null
    },
    {
      "id": "355573",
      "postDate": "07/12/2018 02:30:43",
      "content": "<p>Well Rishabh . PaperSpace was an excellent platform for deep learning and Complex data science problem.  I am sure you can achieve better results in P400 instance as well</p>",
      "rawMarkdown": "Well Rishabh . PaperSpace was an excellent platform for deep learning and Complex data science problem.  I am sure you can achieve better results in P400 instance as well",
      "votes": null
    },
    {
      "id": "355703",
      "postDate": "07/12/2018 08:21:43",
      "content": "<p>Thanks Ryan.</p>",
      "rawMarkdown": "Thanks Ryan.",
      "votes": null
    },
    {
      "id": "667418",
      "postDate": "11/07/2019 08:03:10",
      "content": "<p>How to download kaggle datasets from paperspace free GPU's can anyone help me </p>",
      "rawMarkdown": "How to download kaggle datasets from paperspace free GPU's can anyone help me",
      "votes": null
    },
    {
      "id": "667434",
      "postDate": "11/07/2019 08:19:02",
      "content": "<p><a href=\"/psksaiteja\">@psksaiteja</a> use kaggle cli</p>",
      "rawMarkdown": "psksaiteja use kaggle cli",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 354316,
      "author_name": "sominwadhwa",
      "author_url": "",
      "post_date": "07/09/2018 10:01:56",
      "content": "<p>P4000 is more than enough. If you're using paperspace though, FastAI has a public template over there which is already all setup for use, and you'll be good to go in about 10-15 mins dodging nearly 1-2hrs of man hours setting up CUDA libraries to use GPU.</p>",
      "votes": null,
      "replies": [
        {
          "id": 354329,
          "author_name": "rishabhiitbhu",
          "author_url": "",
          "post_date": "07/09/2018 10:19:13",
          "content": "<p>Yeah, I'll use fast.ai template. Thanks :)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 354679,
          "author_name": "dkobran",
          "author_url": "",
          "post_date": "07/10/2018 03:48:53",
          "content": "<p>Dan here from Paperspace -- let me know if you need to be approved for any GPUs (part of our fraud prevention step).  Feel free to send me an email to dan@ Good luck with the competition btw!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 354937,
      "author_name": "jakubczakon",
      "author_url": "",
      "post_date": "07/10/2018 14:19:16",
      "content": "<p>Also if you are looking for an easy to use setup I'd suggest to go with <a href=\"https://neptune.ml/\">neptune.ml</a></p>\n\n<p>The data for this competition has already been uploaded so you can start with working in a matter of minutes.</p>\n\n<p>(Disclaimer I am working at neptune.ml)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 355029,
      "author_name": "decentmakeover",
      "author_url": "",
      "post_date": "07/10/2018 18:14:59",
      "content": "<p>Good Luck To You</p>",
      "votes": null,
      "replies": [
        {
          "id": 355703,
          "author_name": "rishabhiitbhu",
          "author_url": "",
          "post_date": "07/12/2018 08:21:43",
          "content": "<p>Thanks Ryan.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 355573,
      "author_name": "dinuuu",
      "author_url": "",
      "post_date": "07/12/2018 02:30:43",
      "content": "<p>Well Rishabh . PaperSpace was an excellent platform for deep learning and Complex data science problem.  I am sure you can achieve better results in P400 instance as well</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 667418,
      "author_name": "psksaiteja",
      "author_url": "",
      "post_date": "11/07/2019 08:03:10",
      "content": "<p>How to download kaggle datasets from paperspace free GPU's can anyone help me </p>",
      "votes": null,
      "replies": [
        {
          "id": 667434,
          "author_name": "rishabhiitbhu",
          "author_url": "",
          "post_date": "11/07/2019 08:19:02",
          "content": "<p><a href=\"/psksaiteja\">@psksaiteja</a> use kaggle cli</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "354304": "I want to participate in this competition, given the size of the dataset and the complexity of the problem, I've decided to use Paperspace's P4000 instance. I've never used Paperspace before but I'm all ready to bet on it for this competition.\n\nI just want to know if anyone could suggest me which instances would be enough/sufficient for me.\n\nThanks",
    "354316": "P4000 is more than enough. If you're using paperspace though, FastAI has a public template over there which is already all setup for use, and you'll be good to go in about 10-15 mins dodging nearly 1-2hrs of man hours setting up CUDA libraries to use GPU.",
    "354329": "Yeah, I'll use fast.ai template. Thanks :)",
    "354679": "Dan here from Paperspace -- let me know if you need to be approved for any GPUs (part of our fraud prevention step).  Feel free to send me an email to dan@ Good luck with the competition btw!",
    "354937": "Also if you are looking for an easy to use setup I'd suggest to go with [neptune.ml](https://neptune.ml/)\n\nThe data for this competition has already been uploaded so you can start with working in a matter of minutes.\n\n(Disclaimer I am working at neptune.ml)",
    "355029": "Good Luck To You",
    "355573": "Well Rishabh . PaperSpace was an excellent platform for deep learning and Complex data science problem.  I am sure you can achieve better results in P400 instance as well",
    "355703": "Thanks Ryan.",
    "667418": "How to download kaggle datasets from paperspace free GPU's can anyone help me",
    "667434": "psksaiteja use kaggle cli"
  },
  "source": "meta"
}