{
  "id": 163123,
  "title": "Able to train using Kaggle Kernels?",
  "url": "/competitions/birdsong-recognition/discussion/163123",
  "author_name": "",
  "post_date": "2020-07-01T05:20:47.504263400Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi, </p>\n\n<p>I have access to GPUs but wondering for my potential teammates. Can we train models using Kaggle kernels for this one? Meaning is the kernel GPU/TPUs enough to train models to compete for this one?</p>\n\n<p>Thanks.</p>",
  "messages": [
    {
      "id": "910318",
      "postDate": "07/01/2020 05:20:47",
      "content": "<p>Hi, </p>\n\n<p>I have access to GPUs but wondering for my potential teammates. Can we train models using Kaggle kernels for this one? Meaning is the kernel GPU/TPUs enough to train models to compete for this one?</p>\n\n<p>Thanks.</p>",
      "rawMarkdown": "Hi, \n\nI have access to GPUs but wondering for my potential teammates. Can we train models using Kaggle kernels for this one? Meaning is the kernel GPU/TPUs enough to train models to compete for this one?\n\nThanks.",
      "votes": null
    },
    {
      "id": "911709",
      "postDate": "07/02/2020 00:54:08",
      "content": "<p>Yes, I think so. You can use Kaggle notebooks with GPU. Save your model after every nth epoch then load it back to train it again. The only limitation is the 30 hours they put on gpu usage.</p>",
      "rawMarkdown": "Yes, I think so. You can use Kaggle notebooks with GPU. Save your model after every nth epoch then load it back to train it again. The only limitation is the 30 hours they put on gpu usage.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 911709,
      "author_name": "alanchn31",
      "author_url": "",
      "post_date": "07/02/2020 00:54:08",
      "content": "<p>Yes, I think so. You can use Kaggle notebooks with GPU. Save your model after every nth epoch then load it back to train it again. The only limitation is the 30 hours they put on gpu usage.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "910318": "Hi, \n\nI have access to GPUs but wondering for my potential teammates. Can we train models using Kaggle kernels for this one? Meaning is the kernel GPU/TPUs enough to train models to compete for this one?\n\nThanks.",
    "911709": "Yes, I think so. You can use Kaggle notebooks with GPU. Save your model after every nth epoch then load it back to train it again. The only limitation is the 30 hours they put on gpu usage."
  },
  "source": "meta"
}