# Tensor Type Issue

**URL:** <https://discuss.pytorch.org/t/tensor-type-issue/38443>\
**Category:** Uncategorized\
**Created:** [February 27, 2019, 7:46pm UTC](https://discuss.pytorch.org/t/tensor-type-issue/38443 "2019-02-27T19:46:50Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![bapriddy](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/bapriddy/32/9577_2.png) [@bapriddy](https://discuss.pytorch.org/u/bapriddy)\
**Post date:** [February 27, 2019, 7:46pm UTC](https://discuss.pytorch.org/t/tensor-type-issue/38443/1 "2019-02-27T19:46:50Z")

</div>

When executing the following in a Jupyter notebook (below) it always give the error

* * *

RuntimeError Traceback (most recent call last)  
 in ()  
1 epochs=10  
2 for epoch in range(1, epochs + 1):  
----\> 3 train(model, device, train\_loader, optimizer, epoch)  
4 test(model, device, test\_loader)

in train(model, device, train\_loader, optimizer, epoch)  
59 optimizer.zero\_grad()  
60 output = model(data)  
—\> 61 loss = F.nll\_loss(output, target)  
62 loss.backward()  
63 optimizer.step()

~/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py in nll\_loss(input, target, weight, size\_average, ignore\_index, reduce, reduction)  
1788 .format(input.size(0), target.size(0)))  
1789 if dim == 2:  
-\> 1790 ret = torch.\_C.\_nn.nll\_loss(input, target, weight, \_Reduction.get\_enum(reduction), ignore\_index)  
1791 elif dim == 4:  
1792 ret = torch.\_C.\_nn.nll\_loss2d(input, target, weight, \_Reduction.get\_enum(reduction), ignore\_index)

RuntimeError: Expected object of scalar type Long but got scalar type Float for argument #2 ‘target’

## Jupyter Notebook

```auto
import os
import numpy as np

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.utils.data
from torch.utils.data import DataLoader, Dataset
import torch.utils.data as data_utils

dtype = torch.float
#device = torch.device("cpu")
device = torch.device("cuda" )

# Prepare data
wdata = np.load("data.npy")
data1=torch.from_numpy(wdata) 
X1 = data1[:,:4]
Y1 = data1[:,4:]
U1 = data1[:,:4]
V1 = data1[:,4:]

X=X1.type(torch.FloatTensor)
Y=Y1.type(torch.FloatTensor)
U=U1.type(torch.FloatTensor)
V=V1.type(torch.FloatTensor)

train = data_utils.TensorDataset(X, Y)
train_loader = data_utils.DataLoader(train, batch_size=128, shuffle=True)

test = data_utils.TensorDataset(U, V)
test_loader= data_utils.DataLoader(test, batch_size=4, shuffle=True)

class Net(nn.Module):
    def __init__ (self):
        super(Net, self). __init__ ()
        self.fc1 = nn.Linear(4,512)
        self.drp1 = nn.Dropout(0.2)
        self.fc2 = nn.Linear(512, 512)
        self.drp2 = nn.Dropout(0.2)
        self.fc3 = nn.Linear(512, 4)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    
model = Net().to(device)

optimizer = optim.Adam(model.parameters(), lr=1e-4)   
    

def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        
            
def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

epochs=10
for epoch in range(1, epochs + 1):
    train(model, device, train_loader, optimizer, epoch)
    test(model, device, test_loader)

```

## However, when executing

```auto
input=s.to(device)
out = model(input)
print(out)

```

## I get

tensor([[-0.0278, 0.0300, 0.0424, -0.1008]], device=‘cuda:0’, grad\_fn=\<AddmmBackward\>)

Data.npy is 8 columns x 2203 Rows where  
X = first 4 and Y= last four

---

<div class="post-metadata">

**Author:** ![LeviViana](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/leviviana/32/9548_2.png) [@LeviViana](https://discuss.pytorch.org/u/LeviViana)\
**Post date:** [February 27, 2019, 8:57pm UTC](https://discuss.pytorch.org/t/tensor-type-issue/38443/2 "2019-02-27T20:57:36Z")

</div>

The `NLLLoss` expects the target class index. Maybe [this](https://discuss.pytorch.org/t/understanding-nllloss-function/23702/2) could help. Otherwise, try reading the documentation at [https://pytorch.org/docs/stable/nn.html#](https://pytorch.org/docs/stable/nn.html#).

---

<div class="post-metadata">

**Author:** ![bapriddy](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/bapriddy/32/9577_2.png) [@bapriddy](https://discuss.pytorch.org/u/bapriddy)\
**Post date:** [February 27, 2019, 9:09pm UTC](https://discuss.pytorch.org/t/tensor-type-issue/38443/3 "2019-02-27T21:09:11Z")

</div>

Yes, that works. I replaced

`loss = F.nll_loss(output, target)`

with a simpler loss function

`loss_fn = torch.nn.MSELoss(reduction='sum')`

Thanks.