sample = torch.Tensor((sample_1, sample_2))

[MADS391667]

UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_new.cpp:204.) sample = torch.Tensor((sample_1, sample_2))

[HL-ESLAB]

I have the same problem as you, and you solved the problem?

[MADS391667]

    I didn't solve it. The first problem I encountered was this. I modified it to sample=torch. FloatTensor (np. stack ([sample_1, sample_2]); Second, I encountered a problem where the dataset was not properly guided, resulting in data not being read. I thought I needed to use the sample_ Create another sample in data_ data; But it's still not right; The above is my compilation record.
    
     
    
        
                    ***@***.***
        
    
 


---- Replied Message ----



  
    
     From 
    
    
        ***@***.***>
        
    
  
  
    
     Date 
    
    
    3/22/2023 15:23
    
  
  
    
     To 
    
    
     
      
        ***@***.***>
        
      
    
  
  
    
     Cc 
    
    
      
        ***@***.***>
        ,
      
      
        ***@***.***>
        
      
    
  
  
    
     Subject 
    
    
          Re: [erizmr/UnLiteFlowNet-PIV] sample = torch.Tensor((sample_1, sample_2)) (Issue #5)
    
  

I have the same problem as you, and you solved the problem?

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: @.***>