{
  "id": 117567,
  "title": "MXNetError",
  "url": "/competitions/understanding_cloud_organization/discussion/117567",
  "author_name": "Mobassir",
  "post_date": "2019-11-16T11:02:06.464000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>hi kagglers,\ni was working on a kernel for this competition for learning purpose only.\nhere is the kernel : <a href=\"https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594\">https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594</a></p>\n\n<p>in 15th cell i am getting this error : \n<strong>MXNetError: [10:54:55] src/storage/./pooled_storage_manager.h:157: cudaMalloc failed: out of memory</strong>\ni understand the error  is with memory allocation and i am running out of memory during runtime but i am unable to  figure out how to solve this issue,because initially batch size was 10 for steel defect detection competition,i changed it down to 4 and also changed the height and weight,it was 256x1600 in steel defect detection but for this competition and for learning purpose only  i used 400x400 to avoid cudaMalloc error but it is not working and i am getting same error over and over again so i understand the error is occuring for something else that i am unable to figure out,will  you please help me a bit on this issue? thanks in advance!</p>",
  "messages": [
    {
      "id": 674371,
      "postDate": "2019-11-16T11:02:06.463Z",
      "content": "<p>hi kagglers,\ni was working on a kernel for this competition for learning purpose only.\nhere is the kernel : <a href=\"https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594\">https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594</a></p>\n\n<p>in 15th cell i am getting this error : \n<strong>MXNetError: [10:54:55] src/storage/./pooled_storage_manager.h:157: cudaMalloc failed: out of memory</strong>\ni understand the error  is with memory allocation and i am running out of memory during runtime but i am unable to  figure out how to solve this issue,because initially batch size was 10 for steel defect detection competition,i changed it down to 4 and also changed the height and weight,it was 256x1600 in steel defect detection but for this competition and for learning purpose only  i used 400x400 to avoid cudaMalloc error but it is not working and i am getting same error over and over again so i understand the error is occuring for something else that i am unable to figure out,will  you please help me a bit on this issue? thanks in advance!</p>",
      "rawMarkdown": "hi kagglers,\ni was working on a kernel for this competition for learning purpose only.\nhere is the kernel : https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594\n\nin 15th cell i am getting this error : \n**MXNetError: [10:54:55] src/storage/./pooled_storage_manager.h:157: cudaMalloc failed: out of memory**\ni understand the error  is with memory allocation and i am running out of memory during runtime but i am unable to  figure out how to solve this issue,because initially batch size was 10 for steel defect detection competition,i changed it down to 4 and also changed the height and weight,it was 256x1600 in steel defect detection but for this competition and for learning purpose only  i used 400x400 to avoid cudaMalloc error but it is not working and i am getting same error over and over again so i understand the error is occuring for something else that i am unable to figure out,will  you please help me a bit on this issue? thanks in advance!",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "674371": "hi kagglers,\ni was working on a kernel for this competition for learning purpose only.\nhere is the kernel : https://www.kaggle.com/mobassir/mxnet-gluon-for-cloud-classification?scriptVersionId=23552594\n\nin 15th cell i am getting this error : \n**MXNetError: [10:54:55] src/storage/./pooled_storage_manager.h:157: cudaMalloc failed: out of memory**\ni understand the error  is with memory allocation and i am running out of memory during runtime but i am unable to  figure out how to solve this issue,because initially batch size was 10 for steel defect detection competition,i changed it down to 4 and also changed the height and weight,it was 256x1600 in steel defect detection but for this competition and for learning purpose only  i used 400x400 to avoid cudaMalloc error but it is not working and i am getting same error over and over again so i understand the error is occuring for something else that i am unable to figure out,will  you please help me a bit on this issue? thanks in advance!"
  }
}