{
  "id": 116509,
  "title": "MultiScale Training?",
  "url": "/competitions/understanding_cloud_organization/discussion/116509",
  "author_name": "Bibek",
  "post_date": "2019-11-09T17:15:39.600000",
  "votes": 8,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Did anybody try(with success) multi-scale training in one epoch as done by <a href=\"https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114297#latest-660842\">9th place solution</a> in Steel Competition?\nIn code, this would look something like this:</p>\n\n<p>```python\nfor epoch in range(total_epochs):\n   for i, loader in enumerate([tr_dl_256, tr_dl_320, tr_dl_640, val_loader]):\n             if i != 3:\n                   train_model(loader)\n             else:\n                   validate_model(loader)</p>\n\n<p>```</p>",
  "messages": [
    {
      "id": 669199,
      "postDate": "2019-11-09T17:15:39.600Z",
      "content": "<p>Did anybody try(with success) multi-scale training in one epoch as done by <a href=\"https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114297#latest-660842\">9th place solution</a> in Steel Competition?\nIn code, this would look something like this:</p>\n\n<p>```python\nfor epoch in range(total_epochs):\n   for i, loader in enumerate([tr_dl_256, tr_dl_320, tr_dl_640, val_loader]):\n             if i != 3:\n                   train_model(loader)\n             else:\n                   validate_model(loader)</p>\n\n<p>```</p>",
      "rawMarkdown": "Did anybody try(with success) multi-scale training in one epoch as done by [9th place solution](https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114297#latest-660842) in Steel Competition?\nIn code, this would look something like this:\n\n```python\nfor epoch in range(total_epochs):\n   for i, loader in enumerate([tr_dl_256, tr_dl_320, tr_dl_640, val_loader]):\n             if i != 3:\n                   train_model(loader)\n             else:\n                   validate_model(loader)\n\n```\n\n",
      "votes": 8
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "669199": "Did anybody try(with success) multi-scale training in one epoch as done by [9th place solution](https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114297#latest-660842) in Steel Competition?\nIn code, this would look something like this:\n\n```python\nfor epoch in range(total_epochs):\n   for i, loader in enumerate([tr_dl_256, tr_dl_320, tr_dl_640, val_loader]):\n             if i != 3:\n                   train_model(loader)\n             else:\n                   validate_model(loader)\n\n```\n\n"
  }
}