pytorch 数据增强

https://github.com/miha-skalic/convolutedPredictions_Cdiscount/blob/b0d0fc8ae99e2c3fb8d06eaac19d0e3bcd951bce/heng/code/solution-submit-1/dataset/transform.py

  

   

    

     

    
    

     

      from common import *
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ## for debug
     
    
   

    

     

    
    

     

      def dummy_transform(img,text='dummy_transform'):
     
    
   

    

     

    
    

     
 print ('\t\t%s',text)
     
    
   

    

     

    
    

     
 return img
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ## custom data transform -----------------------------------
     
    
   

    

     

    
    

     

      ## https://github.com/pytorch/vision/blob/master/test/preprocess-bench.py
     
    
   

    

     

    
    

     

      ## http://pytorch-zh.readthedocs.io/en/latest/torchvision/models.html
     
    
   

    

     

    
    

     

      ## All pre-trained models expect input images normalized in the same way,
     
    
   

    

     

    
    

     

      ## i.e. mini-batches of 3-channel RGB images of shape (3 x H x W),
     
    
   

    

     

    
    

     

      ## where H and W are expected to be atleast 224. The images have to be
     
    
   

    

     

    
    

     

      ## loaded in to a range of [0, 1] a
     
    
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/101315249