pytorch DataLoader

COCODataset 中返回numpy数组或者字典中包含numpy，会自动转换为tenser

  

   

    

     

    
    

     

      from torch.utils.data import DataLoader
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       dataloader =DataLoader(COCODataset(data_path,
     
    
   

    

     

    
    

     

       (512, 512),
     
    
   

    

     

    
    

     

       is_training=False, is_scene=True),
     
    
   

    

     

    
    

     

       batch_size=batch_size,
     
    
   

    

     

    
    

     

       shuffle=False, num_workers=0, pin_memory=False,
     
    
   

    

     

    
    

     

       drop_last=True)  # DataLoader
     
    
   

    

     

    
    

     

       start = time.time()
     
    
   

    

     

    
    

     

       dat_files = [os.path.join(rootdir, file) for rootdir, _, files in os.walk(target_path) for file in files if
     
    
   

    

     

    
    

     

       (file.endswith('.dat'))]
     
    
   

    

     

    
    

     

       dat_files_len = len(dat_files)
     
    
   

    

     

    
    

     
 for step, samples in enumerate(dataloader):
     
    
   

    

     

    
    

     

       image_paths = samples["img_path"]
     
    
  
 

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/91348836