I am following the example code for Transfer Learning on Pytorch documentation. My dataset though is not images and instead is numpy array with X size is 15 (read from 15 pixels) and y is uniques classes with 5 values (1,2,3,4,5). I explain my approach step by step:

```
import numpy as np
import time
import copy
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, TensorDataset, DataLoader, random_split
import torch.nn.functional as F
```

Here is how my X[0] and y[0] look like:

(array([739, 742, 734, 732, 746, 734, 736, 737, 728, 742, 741, 736, 736, 741, 316]), array([2]))

I create my dataset as:

```
class MyDataset(Dataset):
def __init__(self, data, target, transform=None):
self.data = torch.from_numpy(data).float()
self.target = torch.from_numpy(target).long()
self.transform = transform
def __getitem__(self, index):
x = self.data[index]
y = self.target[index]
if self.transform:
x = self.transform(x)
return x, y
def __len__(self):
return len(self.data)
```

I split the X, y for training and validation as:

```
full_ds = MyDataset(X, y)
trn_size = int(0.8*len(full_ds))
val_size = len(full_ds) - trn_size
trn_ds, val_ds = random_split(full_ds, [trn_size, val_size])
datasets = {'train': trn_ds, 'val': val_ds}
dataloaders = {x: DataLoader(datasets[x], batch_size=4, shuffle=True) for x in ['train', 'val']}
dataset_sizes = {x: len(datasets[x]) for x in ['train', 'val']}
```

My model, optimizer and loss are:

```
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(15, 8)
self.fc2 = nn.Linear(8, 5)
def forward(self, x):
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.log_softmax(x, dim=1)
net = Net()
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
criterion = nn.NLLLoss()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
```

and as i mentioned earlier my training function follows Pytorch standard example:

```
def train_model(model, criterion, optimizer, num_epochs=10):
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model
```

When running training function, I am getting the following runtime error:

```
RuntimeError: multi-target not supported at /Users/administrator/nightlies/pytorch-1.0.0/wheel_build_dirs/conda_3.7/conda/conda-bld/pytorch_1544144746443/work/aten/src/THNN/generic/ClassNLLCriterion.c:21
```

I am stuck here and I would appreciate your help!