# Multi-Class Classifier **URL:** \ **Category:** Uncategorized\ **Created:** [November 18, 2018, 2:24pm UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901 "2018-11-18T14:24:20Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![ostaeria](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/o/919ad9/32.png) [@ostaeria](https://discuss.pytorch.org/u/ostaeria)\ **Post date:** [November 18, 2018, 2:24pm UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/1 "2018-11-18T14:24:20Z")
I’m facing immense confusion in the construction of my neural network. My input is of (140000 x 200) dimension. My output is of (140000) dimension. My input is basically a bunch of 200 dimensional floats. Its denoted by **x\_train\_regressors** My output consists of the following classes represented by numbers: 1, 2, 3, 4, 5, its denoted by **y\_train\_exact\_target**. I am trying to build and train a network to properly classify my output, but I am not sure how to classify to handle/format the output values. My code is below: ```auto class NeuralNet(nn.Module): def __init__ (self, input_size, hidden_size, num_classes): super(NeuralNet, self). __init__ () self.layer1 = nn.Linear(input_size, hidden_size) self.relu = nn.ReLU() self.layer2 = nn.Linear(hidden_size, num_classes) def forward(self, x): out = self.layer1(x) out = self.relu(out) out = self.layer2(out) return out ``` ```auto exact_net = NeuralNet(200 , 1000, 5) loss_function = nn.BCELoss() exact_net_opt = torch.optim.SGD(exact_net.parameters(), lr = 0.02) train_set = Variable(torch.from_numpy(np.array(x_train_regressors))).float() test_set = Variable(torch.LongTensor(y_train_exact_target)).long() epochs = 50 for epochs in range(epochs): exact_net_opt.zero_grad() out = exact_net(instance) loss = loss_function(out, label) loss.backward() exact_net_opt.step() --------------------------------------------------------------------------- ValueError Traceback (most recent call last) in 4 exact_net_opt.zero_grad() 5 out = exact_net(instance) ----> 6 loss = loss_function(out, label) 7 loss.backward() 8 exact_net_opt.step() ~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__ (self, *input, **kwargs) 475 result = self._slow_forward(*input, **kwargs) 476 else: --> 477 result = self.forward(*input, **kwargs) 478 for hook in self._forward_hooks.values(): 479 hook_result = hook(self, input, result) ~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target) 484 485 def forward(self, input, target): --> 486 return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction) 487 488 ~\AppData\Local\Continuum\anaconda3\lib\site-packages\torch\nn\functional.py in binary_cross_entropy(input, target, weight, size_average, reduce, reduction) 1595 if input.nelement() != target.nelement(): 1596 raise ValueError("Target and input must have the same number of elements. target nelement ({}) " -> 1597 "!= input nelement ({})".format(target.nelement(), input.nelement())) 1598 1599 if weight is not None: ValueError: Target and input must have the same number of elements. target nelement (1) != input nelement (5) ``` ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [November 18, 2018, 8:30pm UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/2 "2018-11-18T20:30:30Z")
If you want to classify each sample to one of your 5 classes, try to use `nn.CrossEntropyLoss`. Also, shift the target values to `[0, nb_classes-1]`, so `[0, 4]` in your case, as otherwise you’ll get an out of bounds error. ---
**Author:** ![ostaeria](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/o/919ad9/32.png) [@ostaeria](https://discuss.pytorch.org/u/ostaeria)\ **Post date:** [November 18, 2018, 9:55pm UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/3 "2018-11-18T21:55:25Z")
In this case, wouldn’t one hot encoding be necessary? ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [November 18, 2018, 10:06pm UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/4 "2018-11-18T22:06:59Z")
No, for multi-class classification (one target class for each sample), the targets should hold the class indices. Other frameworks often use one-hot encoded target vectors, which is not necessary in PyTorch. Have a look at the [docs](https://pytorch.org/docs/stable/nn.html#torch.nn.CrossEntropyLoss) for more information. ---
**Author:** ![Rojin](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/rojin/32/11062_2.png) [@Rojin](https://discuss.pytorch.org/u/Rojin)\ **Post date:** [June 11, 2019, 4:23am UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/5 "2019-06-11T04:23:09Z")
Hey! shouldn’t we add a softmax activation at the end when we want to do a multi-class classification? ---
**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\ **Post date:** [June 11, 2019, 9:08am UTC](https://discuss.pytorch.org/t/multi-class-classifier/29901/6 "2019-06-11T09:08:58Z")
If you are using `nn.CrossentropyLoss`, you should pass the logits without any non-linearity to the criterion, as internally `F.log_softmax` and `nn.NLLLoss` will be used. Alternatively, you could apply `F.log_softmax` manually and pass it directly to `nn.NLLLoss`. So usually you don’t use a softmax activation, unless e.g. you are implementing some custom criterion of course.