{
  "id": 51146,
  "title": "Plot training history",
  "url": "/competitions/data-science-bowl-2018/discussion/51146",
  "author_name": "",
  "post_date": "2018-03-05T21:22:44.158057100Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi!</p>\n\n<p>I would like to run model trainings with different settings (e.g. data augmentation, coco vs. imagenet weights, etc) and look at the training history (e.g. val_rpn_class_loss,val_rpn_bbox_loss, etc)</p>\n\n<p>Has anyone figured out how to get the full training history?</p>",
  "messages": [
    {
      "id": "291252",
      "postDate": "03/05/2018 21:22:44",
      "content": "<p>Hi!</p>\n\n<p>I would like to run model trainings with different settings (e.g. data augmentation, coco vs. imagenet weights, etc) and look at the training history (e.g. val_rpn_class_loss,val_rpn_bbox_loss, etc)</p>\n\n<p>Has anyone figured out how to get the full training history?</p>",
      "rawMarkdown": "Hi!\n\nI would like to run model trainings with different settings (e.g. data augmentation, coco vs. imagenet weights, etc) and look at the training history (e.g. val_rpn_class_loss,val_rpn_bbox_loss, etc)\n\nHas anyone figured out how to get the full training history?",
      "votes": null
    },
    {
      "id": "291299",
      "postDate": "03/05/2018 23:49:08",
      "content": "<p>Hi Fab! \nI have the following graphs by using this comand tensorboard --logdir \"path_to_logs_file\" --port \"port_now\". \nHope this helps. </p>\n\n<p>Also Do you know of a listing of the importance of the variables ? \nExample: is val_loss more important than val_rpn_bbox_loss and so on. </p>",
      "rawMarkdown": "Hi Fab! \nI have the following graphs by using this comand tensorboard --logdir \"path_to_logs_file\" --port \"port_now\". \nHope this helps. \n\nAlso Do you know of a listing of the importance of the variables ? \nExample: is val_loss more important than val_rpn_bbox_loss and so on.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 291299,
      "author_name": "mpsampat",
      "author_url": "",
      "post_date": "03/05/2018 23:49:08",
      "content": "<p>Hi Fab! \nI have the following graphs by using this comand tensorboard --logdir \"path_to_logs_file\" --port \"port_now\". \nHope this helps. </p>\n\n<p>Also Do you know of a listing of the importance of the variables ? \nExample: is val_loss more important than val_rpn_bbox_loss and so on. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "291252": "Hi!\n\nI would like to run model trainings with different settings (e.g. data augmentation, coco vs. imagenet weights, etc) and look at the training history (e.g. val_rpn_class_loss,val_rpn_bbox_loss, etc)\n\nHas anyone figured out how to get the full training history?",
    "291299": "Hi Fab! \nI have the following graphs by using this comand tensorboard --logdir \"path_to_logs_file\" --port \"port_now\". \nHope this helps. \n\nAlso Do you know of a listing of the importance of the variables ? \nExample: is val_loss more important than val_rpn_bbox_loss and so on."
  },
  "source": "meta"
}