RuntimeError: expected scalar type Long but found Float (Pytorch)

Question

I've tried many times to fix, also I've used the example codes from functional.py then I got my same "loss" value. How can I fix this?

My libraries

    import matplotlib.pyplot as plt
    import torch
    import torch.nn as nn
    import numpy as np
    import matplotlib
    import pandas as pd
    from torch.autograd import Variable
    from torch.utils.data import DataLoader,TensorDataset
    from sklearn.model_selection import train_test_split
    import warnings
    import os
    import torchvision
    import torchvision.datasets as dsets
    import torchvision.transforms as transforms

Data set of Mnis

    
    train=pd.read_csv("train.csv",dtype=np.float32)
    
    
    targets_numpy = train.label.values
    features_numpy = train.loc[:,train.columns != "label"].values/255 # normalization
    
    
    features_train, features_test, targets_train, targets_test = train_test_split(features_numpy,
                                                                                 targets_numpy,test_size = 0.2,
                                                                                 random_state = 42) 
   
    featuresTrain=torch.from_numpy(features_train)
    targetsTrain=torch.from_numpy(targets_train)
    
    
    featuresTest=torch.from_numpy(features_test)
    targetsTest=torch.from_numpy(targets_test)     
    
    
    batch_size=100
    n_iterations=10000
    num_epochs=n_iterations/(len(features_train)/batch_size)
    num_epochs=int(num_epochs)
    
    
    train=torch.utils.data.TensorDataset(featuresTrain,targetsTrain) 
    test=torch.utils.data.TensorDataset(featuresTest,targetsTest)
    
    print(type(train))
    
    
    
    train_loader=DataLoader(train,batch_size=batch_size,shuffle=False)
    test_loader=DataLoader(test,batch_size=batch_size,shuffle=False)
    print(type(train_loader))
    
    plt.imshow(features_numpy[226].reshape(28,28))
    plt.axis("off")
    plt.title(str(targets_numpy[226]))
    plt.show()

Here is my model

  

    class ANNModel(nn.Module):  
      
      def __init__(self,input_dim,hidden_dim,output_dim):
        super(ANNModel,self).__init__()
    
        
        self.fc1=nn.Linear(input_dim,hidden_dim)
        
        self.relu1=nn.ReLU()
    
        
        self.fc2=nn.Linear(hidden_dim,hidden_dim)
        
        self.tanh2=nn.Tanh()
    
       
    
        
        self.fc4=nn.Linear(hidden_dim,output_dim)
    
      def forward (self,x): #forward ile elde edilen layer lar bağlanır
        
        out=self.fc1(x)
        
        out=self.relu1(out)
    
        
        out=self.fc2(out)
        
        out=self.tanh2(out)
    
       
        
    
        
        out=self.fc4(out)
        return out  
      
    input_dim=28*28
    hidden_dim=150  
    output_dim=10 
    
    
    
    model=ANNModel(input_dim,hidden_dim,output_dim)
    
    
    error=nn.CrossEntropyLoss()
    
    
    learning_rate=0.02
    optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)

where the problem is

 

   
    count=0
    loss_list=[]
    iteration_list=[]
    accuracy_list = []
    for epoch in range(num_epochs):
      for i,(images,labels) in enumerate(train_loader):
        
        train=Variable(images.view(-1,28*28))
        labels=Variable(labels)
        #print(labels)
        #print(outputs)  
       
        optimizer.zero_grad()
    
        #forward propagation
        outputs=model(train)
    
       
       
        #outputs=torch.randn(784,10,requires_grad=True)
        ##labels=torch.randn(784,10).softmax(dim=1)
        loss=error(outputs,labels)
        
        
        
       
        loss.backward()
    
        
        optimizer.step()
        
        count+=1
         
        if count %50 ==0:
          
          
          correct=0
          total=0
          
         
          for images,labels in test_loader:
            test=Variable(images.view(-1,28*28))
    
            
            outputs=model(test)
    
            
            predicted=torch.max(outputs.data,1)[1] #mantık???
    
           
            total+= len(labels)
    
            
            correct+=(predicted==labels).sum()
    
          accuracy=100  *correct/float(total)
         
          loss_list.append(loss.data)
          iteration_list.append(count)
          accuracy_list.append(accuracy)
          if  count %500 ==0 :
           
           print('Iteration: {}  Loss: {}  Accuracy: {} %'.format(count, loss.data, accuracy))

Which gives

    ---------------------------------------------------------------------------
    RuntimeError                              Traceback (most recent call last)
    <ipython-input-9-9e53988ad250> in <module>()
         26     #outputs=torch.randn(784,10,requires_grad=True)
         27     ##labels=torch.randn(784,10).softmax(dim=1)
    ---> 28     loss=error(outputs,labels)
         29 
         30 
    
    2 frames
    /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
       2844     if size_average is not None or reduce is not None:
       2845         reduction = _Reduction.legacy_get_string(size_average, reduce)
    -> 2846     return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
       2847 
       2848 
    
    RuntimeError: expected scalar type Long but found Float

Answer 1

it seems that the dtype of the tensor "labels" is FloatTensor. However, nn.CrossEntropyLoss expects a target of type LongTensor. This means that you should check the type of "labels". if its the case then you should use the following code to convert the dtype of "labels" from FloatTensor to LongTensor:

loss=error(outputs,labels.long())

Answer 2

targetsTrain=torch.from_numpy(targets_train)
targetsTest=torch.from_numpy(targets_test)

in these lines you have to add these codes:

targetsTrain=torch.from_numpy(targets_train).type(torch.LongTensor)#data type is long
targetsTest=torch.from_numpy(targets_test).type(torch.LongTensor)#data type is long

then it works without problem