{
  "id": 70577,
  "title": "My model doesn't complete all epochs",
  "url": "/competitions/quickdraw-doodle-recognition/discussion/70577",
  "author_name": "Dileep Patchigolla",
  "post_date": "2018-11-05T11:35:30.195000",
  "votes": -1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi</p>\n\n<p>I am running an LSTM model on the full data using fit_generator. I try to run the model for 16 epochs with early stopping. But the model is stopping in the middle of 7th epoch, even though the early stopping conditions are not met. My code is present here:</p>\n\n<p><a href=\"https://www.kaggle.com/dileep31/lstm-full-data-generator\">https://www.kaggle.com/dileep31/lstm-full-data-generator</a></p>\n\n<p>Can someone help me understand why this could be happening? Is this because of some Kaggle resource cap?</p>",
  "messages": [
    {
      "id": 415604,
      "postDate": "2018-11-05T11:35:30.197Z",
      "content": "<p>Hi</p>\n\n<p>I am running an LSTM model on the full data using fit_generator. I try to run the model for 16 epochs with early stopping. But the model is stopping in the middle of 7th epoch, even though the early stopping conditions are not met. My code is present here:</p>\n\n<p><a href=\"https://www.kaggle.com/dileep31/lstm-full-data-generator\">https://www.kaggle.com/dileep31/lstm-full-data-generator</a></p>\n\n<p>Can someone help me understand why this could be happening? Is this because of some Kaggle resource cap?</p>",
      "rawMarkdown": "Hi\n\nI am running an LSTM model on the full data using fit_generator. I try to run the model for 16 epochs with early stopping. But the model is stopping in the middle of 7th epoch, even though the early stopping conditions are not met. My code is present here:\n\nhttps://www.kaggle.com/dileep31/lstm-full-data-generator\n\nCan someone help me understand why this could be happening? Is this because of some Kaggle resource cap?\n",
      "votes": -1
    },
    {
      "id": 419490,
      "postDate": "2018-11-12T04:08:28.140Z",
      "content": "<p>Do some math on your model - batch size times steps times epochs until fail - I have had a number of generators in several challenges where this calculation indicates that the generator went through the data set one time and than dies.  Sadly I don't know enough to have fixed the generators.  </p>",
      "rawMarkdown": "Do some math on your model - batch size times steps times epochs until fail - I have had a number of generators in several challenges where this calculation indicates that the generator went through the data set one time and than dies.  Sadly I don't know enough to have fixed the generators.  "
    }
  ],
  "comments": [
    {
      "id": 419490,
      "author_name": "PC Jimmmy",
      "author_url": "",
      "post_date": "2018-11-12T04:08:28.140000",
      "content": "<p>Do some math on your model - batch size times steps times epochs until fail - I have had a number of generators in several challenges where this calculation indicates that the generator went through the data set one time and than dies.  Sadly I don't know enough to have fixed the generators.  </p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "415604": "Hi\n\nI am running an LSTM model on the full data using fit_generator. I try to run the model for 16 epochs with early stopping. But the model is stopping in the middle of 7th epoch, even though the early stopping conditions are not met. My code is present here:\n\nhttps://www.kaggle.com/dileep31/lstm-full-data-generator\n\nCan someone help me understand why this could be happening? Is this because of some Kaggle resource cap?\n",
    "419490": "Do some math on your model - batch size times steps times epochs until fail - I have had a number of generators in several challenges where this calculation indicates that the generator went through the data set one time and than dies.  Sadly I don't know enough to have fixed the generators.  "
  }
}