{
  "id": 121192,
  "title": "Does an access to external computation resources play decisive role? ",
  "url": "/competitions/deepfake-detection-challenge/discussion/121192",
  "author_name": "",
  "post_date": "2019-12-11T19:28:10.811932700Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi there,</p>\n\n<p>I've heard an oppinion that in competitions like that having an access to \"unlimited\" computation resources outside of kaggle kernels plays a decisive role. Say you can afford to train your model elsewhere and then import it. I am new to kaggle and will be grateful for the tipps or oppinions whether it is worthy to participate and possible to compete given the additional resources are not accessable.</p>\n\n<p>Thank you in advance!</p>\n\n<p>P.S. lets assume \"its a good learning opportunity\" is already mentioned in the answers:)    </p>",
  "messages": [
    {
      "id": "692840",
      "postDate": "12/11/2019 19:28:10",
      "content": "<p>Hi there,</p>\n\n<p>I've heard an oppinion that in competitions like that having an access to \"unlimited\" computation resources outside of kaggle kernels plays a decisive role. Say you can afford to train your model elsewhere and then import it. I am new to kaggle and will be grateful for the tipps or oppinions whether it is worthy to participate and possible to compete given the additional resources are not accessable.</p>\n\n<p>Thank you in advance!</p>\n\n<p>P.S. lets assume \"its a good learning opportunity\" is already mentioned in the answers:)    </p>",
      "rawMarkdown": "Hi there,\n\nI've heard an oppinion that in competitions like that having an access to \"unlimited\" computation resources outside of kaggle kernels plays a decisive role. Say you can afford to train your model elsewhere and then import it. I am new to kaggle and will be grateful for the tipps or oppinions whether it is worthy to participate and possible to compete given the additional resources are not accessable.\n\nThank you in advance!\n\nP.S. lets assume \"its a good learning opportunity\" is already mentioned in the answers:)",
      "votes": null
    },
    {
      "id": "692955",
      "postDate": "12/11/2019 22:16:33",
      "content": "<p>Having lots of compute always helps. However, clever ideas may help more. ;-)</p>",
      "rawMarkdown": "Having lots of compute always helps. However, clever ideas may help more. ;-)",
      "votes": null
    },
    {
      "id": "692958",
      "postDate": "12/11/2019 22:29:42",
      "content": "<p>Just use low resolution and prototype. Having access to resources is always helpful, however creative solutions are the aim of this competition. </p>\n\n<blockquote>\n  <p>The goal of the challenge is to spur researchers around the world to build innovative new technologies that can help detect deepfakes and manipulated media.</p>\n</blockquote>\n\n<p>Just use whatever hardware you can afford. Aim to build a scalable solution that you can easily upscale input dimensions, parameters, etc.</p>",
      "rawMarkdown": "Just use low resolution and prototype. Having access to resources is always helpful, however creative solutions are the aim of this competition. \n\n&gt; The goal of the challenge is to spur researchers around the world to build innovative new technologies that can help detect deepfakes and manipulated media.\n\nJust use whatever hardware you can afford. Aim to build a scalable solution that you can easily upscale input dimensions, parameters, etc.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 692955,
      "author_name": "humananalog",
      "author_url": "",
      "post_date": "12/11/2019 22:16:33",
      "content": "<p>Having lots of compute always helps. However, clever ideas may help more. ;-)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 692958,
      "author_name": "teeyee314",
      "author_url": "",
      "post_date": "12/11/2019 22:29:42",
      "content": "<p>Just use low resolution and prototype. Having access to resources is always helpful, however creative solutions are the aim of this competition. </p>\n\n<blockquote>\n  <p>The goal of the challenge is to spur researchers around the world to build innovative new technologies that can help detect deepfakes and manipulated media.</p>\n</blockquote>\n\n<p>Just use whatever hardware you can afford. Aim to build a scalable solution that you can easily upscale input dimensions, parameters, etc.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "692840": "Hi there,\n\nI've heard an oppinion that in competitions like that having an access to \"unlimited\" computation resources outside of kaggle kernels plays a decisive role. Say you can afford to train your model elsewhere and then import it. I am new to kaggle and will be grateful for the tipps or oppinions whether it is worthy to participate and possible to compete given the additional resources are not accessable.\n\nThank you in advance!\n\nP.S. lets assume \"its a good learning opportunity\" is already mentioned in the answers:)",
    "692955": "Having lots of compute always helps. However, clever ideas may help more. ;-)",
    "692958": "Just use low resolution and prototype. Having access to resources is always helpful, however creative solutions are the aim of this competition. \n\n&gt; The goal of the challenge is to spur researchers around the world to build innovative new technologies that can help detect deepfakes and manipulated media.\n\nJust use whatever hardware you can afford. Aim to build a scalable solution that you can easily upscale input dimensions, parameters, etc."
  },
  "source": "meta"
}