{
  "id": 349200,
  "title": "Save memory and GPU quota in test time",
  "url": "/competitions/mayo-clinic-strip-ai/discussion/349200",
  "author_name": "Kirderf",
  "post_date": "2022-08-31T16:14:42.461000",
  "votes": 9,
  "comment_count": 1,
  "views": 0,
  "content": "<p>In the below notebook I show a way doing ensemble between solutions memory efficient and also use the new Kaggle env. feature when submitting, all in all this saves both memory when running multiple solutions and also your valuable weekly GPU quota.</p>\n<p><a href=\"https://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient\" target=\"_blank\">https://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient</a></p>\n<p>How it works: We save the codes for every solution in an own python file which we then run separately in isolated memory. We also take advantages of the new Kaggle env. feature that checks if we are in the hidden test running phase or only in the submitting phase, and use this by saving a submission sample in submitting phase and when in the phase of running the hidden private test phase, using the real code. This use only seconds of the GPU quota.</p>",
  "messages": [
    {
      "id": 1921169,
      "postDate": "2022-08-31T16:14:42.460Z",
      "content": "<p>In the below notebook I show a way doing ensemble between solutions memory efficient and also use the new Kaggle env. feature when submitting, all in all this saves both memory when running multiple solutions and also your valuable weekly GPU quota.</p>\n<p><a href=\"https://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient\" target=\"_blank\">https://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient</a></p>\n<p>How it works: We save the codes for every solution in an own python file which we then run separately in isolated memory. We also take advantages of the new Kaggle env. feature that checks if we are in the hidden test running phase or only in the submitting phase, and use this by saving a submission sample in submitting phase and when in the phase of running the hidden private test phase, using the real code. This use only seconds of the GPU quota.</p>",
      "rawMarkdown": "In the below notebook I show a way doing ensemble between solutions memory efficient and also use the new Kaggle env. feature when submitting, all in all this saves both memory when running multiple solutions and also your valuable weekly GPU quota.\n\nhttps://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient\n\nHow it works: We save the codes for every solution in an own python file which we then run separately in isolated memory. We also take advantages of the new Kaggle env. feature that checks if we are in the hidden test running phase or only in the submitting phase, and use this by saving a submission sample in submitting phase and when in the phase of running the hidden private test phase, using the real code. This use only seconds of the GPU quota.",
      "votes": 9
    },
    {
      "id": 1922521,
      "postDate": "2022-09-01T14:47:32.220Z",
      "content": "<p>Really cool and elegant approach </p>",
      "rawMarkdown": "Really cool and elegant approach ",
      "votes": 2
    }
  ],
  "comments": [
    {
      "id": 1922521,
      "author_name": "The Devastator",
      "author_url": "",
      "post_date": "2022-09-01T14:47:32.220000",
      "content": "<p>Really cool and elegant approach </p>",
      "votes": 2,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1921169": "In the below notebook I show a way doing ensemble between solutions memory efficient and also use the new Kaggle env. feature when submitting, all in all this saves both memory when running multiple solutions and also your valuable weekly GPU quota.\n\nhttps://www.kaggle.com/code/kirderf/mayo-inference-memory-and-gpu-quota-efficient\n\nHow it works: We save the codes for every solution in an own python file which we then run separately in isolated memory. We also take advantages of the new Kaggle env. feature that checks if we are in the hidden test running phase or only in the submitting phase, and use this by saving a submission sample in submitting phase and when in the phase of running the hidden private test phase, using the real code. This use only seconds of the GPU quota.",
    "1922521": "Really cool and elegant approach "
  }
}