{
  "id": 158981,
  "title": "Keras VS PyTorch",
  "url": "/competitions/prostate-cancer-grade-assessment/discussion/158981",
  "author_name": "Salman",
  "post_date": "2020-06-16T02:43:29.383000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Ok. So I have achieved MSE LOSS of 0.90178 CV using simple intermediate tiles in 30 epochs.\nBut my code is implemented in tensorflow.\nI am not familiar with pytorch. Are there any differences in AdaptiveAveragePooling from pytorch and AveragePooling from tensorflow?\nKind of confused with this.\nMoreover, I am following approach to concatenate patches to make a bigger image.\nPassing individual patch from pretrained network and concatenating their feature map for dense layers will work better or this bigger image is enough with augmentation on each patch and over all?\nLet me know. Thanks. :)</p>",
  "messages": [
    {
      "id": 887939,
      "postDate": "2020-06-16T02:43:29.383Z",
      "content": "<p>Ok. So I have achieved MSE LOSS of 0.90178 CV using simple intermediate tiles in 30 epochs.\nBut my code is implemented in tensorflow.\nI am not familiar with pytorch. Are there any differences in AdaptiveAveragePooling from pytorch and AveragePooling from tensorflow?\nKind of confused with this.\nMoreover, I am following approach to concatenate patches to make a bigger image.\nPassing individual patch from pretrained network and concatenating their feature map for dense layers will work better or this bigger image is enough with augmentation on each patch and over all?\nLet me know. Thanks. :)</p>",
      "rawMarkdown": "Ok. So I have achieved MSE LOSS of 0.90178 CV using simple intermediate tiles in 30 epochs.\nBut my code is implemented in tensorflow.\nI am not familiar with pytorch. Are there any differences in AdaptiveAveragePooling from pytorch and AveragePooling from tensorflow?\nKind of confused with this.\nMoreover, I am following approach to concatenate patches to make a bigger image.\nPassing individual patch from pretrained network and concatenating their feature map for dense layers will work better or this bigger image is enough with augmentation on each patch and over all?\nLet me know. Thanks. :)",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "887939": "Ok. So I have achieved MSE LOSS of 0.90178 CV using simple intermediate tiles in 30 epochs.\nBut my code is implemented in tensorflow.\nI am not familiar with pytorch. Are there any differences in AdaptiveAveragePooling from pytorch and AveragePooling from tensorflow?\nKind of confused with this.\nMoreover, I am following approach to concatenate patches to make a bigger image.\nPassing individual patch from pretrained network and concatenating their feature map for dense layers will work better or this bigger image is enough with augmentation on each patch and over all?\nLet me know. Thanks. :)"
  }
}