# TypeError: forward() takes 2 positional arguments but 3 were given

**URL:** <https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343>\
**Category:** vision\
**Created:** [July 18, 2018, 5:27pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343 "2018-07-18T17:27:21Z")\
**Posts on this page:** 20\
**Page:** 1

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 18, 2018, 5:27pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/1 "2018-07-18T17:27:21Z")

</div>

```auto
class G(nn.Module):

    def __init__ (self):
        super(G, self). __init__ ()
        self.main = nn.Sequential(
            nn.ConvTranspose2d(100, 512, 4, 1, 0, bias = False),
            nn.BatchNorm2d(512),
            nn.ReLU(True),
            nn.ConvTranspose2d(512, 256, 4, 2, 1, bias = False),
            nn.BatchNorm2d(256),
            nn.ReLU(True),
            nn.ConvTranspose2d(256, 128, 4, 2, 1, bias = False),
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.ConvTranspose2d(128, 64, 4, 2, 1, bias = False),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.ConvTranspose2d(64, 3, 4, 2, 1, bias = False),
            nn.Tanh()
        )

    def forward(self, input):
        output = self.main(input)
        return output

# Creating the generator
netG = G()
netG.apply(weights_init)

# Defining the discriminator

class D(nn.Module):

    def __init__ (self):
        super(D, self). __init__ ()
        self.main = nn.Sequential(
            nn.Conv2d(3, 64, 4, 2, 1, bias = False),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(64, 128, 4, 2, 1, bias = False),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(128, 256, 4, 2, 1, bias = False),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(256, 512, 4, 2, 1, bias = False),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(512, 1, 4, 1, 0, bias = False),
            nn.Sigmoid()
        )

    def forward(self, input):
        output = self.main(input)
        return output.view(-1)

# Creating the discriminator
netD = D()
netD.apply(weights_init)
criterion = nn.Sigmoid()
optimizerD = optim.Adam(netD.parameters(), lr = 0.0002, betas = (0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr = 0.0002, betas = (0.5, 0.999))

```

Iam doing GAN using two classes dogs and cats.Its showing  
TypeError: forward() takes 2 positional arguments but 3 were giventype or paste code here

```auto

```

---

<div class="post-metadata">

**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:** [July 18, 2018, 5:40pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/2 "2018-07-18T17:40:11Z")

</div>

Could you post the code showing where your model tries to call `forward`?

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 18, 2018, 6:08pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/3 "2018-07-18T18:08:28Z")

</div>

```auto
for epoch in range(25):

    for i, data in enumerate(dataloader, 0):
        
        # 1st Step: Updating the weights of the neural network of the discriminator

        netD.zero_grad()
        
        # Training the discriminator with a real image of the dataset
        real, _ = data
        input = Variable(real)
        target = Variable(torch.ones(input.size()[0]))
        output = netD(input)
        errD_real = criterion(output, target)
        
        # Training the discriminator with a fake image generated by the generator
        noise = Variable(torch.randn(input.size()[0], 100, 1, 1))
        fake = netG(noise)
        target = Variable(torch.zeros(input.size()[0]))
        output = netD(fake.detach())
        errD_fake = criterion(output, target)
        
        # Backpropagating the total error
        errD = errD_real + errD_fake
        errD.backward()
        optimizerD.step()

        # 2nd Step: Updating the weights of the neural network of the generator

        netG.zero_grad()
        target = Variable(torch.ones(input.size()[0]))
        output = netD(fake)
        errG = criterion(output, target)
        errG.backward()
        optimizerG.step()

```

---

<div class="post-metadata">

**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:** [July 18, 2018, 6:10pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/4 "2018-07-18T18:10:04Z")

</div>

Thanks for the code. We would need to get more information on `real`.  
Could you print it, its `type`, and its `len`?

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 1:29am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/5 "2018-07-19T01:29:22Z")

</div>

real is image files of .jpg format.I gave batch\_size=1.I have two targets dogs and cats,so i used sigmoid.Total of 936 images are there in the dataset.

---

<div class="post-metadata">

**Author:** ![chenglu](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/chenglu/32/3901_2.png) [@chenglu](https://discuss.pytorch.org/u/chenglu)\
**Post date:** [July 19, 2018, 3:45am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/6 "2018-07-19T03:45:41Z")

</div>

Could you print the full call stack of the error message?

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 4:00am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/7 "2018-07-19T04:00:11Z")

</div>

```auto
C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torchvision\transforms\transforms.py:188: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead.
  "please use transforms.Resize instead.")
Traceback (most recent call last):

  File "<ipython-input-1-ca7bb5f3dbe2>", line 115, in <module>
    errD_real = criterion(output, target)

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\nn\modules\module.py", line 357, in __call__
    result = self.forward(*input, **kwargs)

TypeError: forward() takes 2 positional arguments but 3 were given

```

---

<div class="post-metadata">

**Author:** ![chenglu](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/chenglu/32/3901_2.png) [@chenglu](https://discuss.pytorch.org/u/chenglu)\
**Post date:** [July 19, 2018, 4:03am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/8 "2018-07-19T04:03:41Z")

</div>

The `nn.Sigmoid` takes only 1 params, but you give 2. [https://pytorch.org/docs/stable/torch.html?highlight=sigmoid#torch.sigmoid](https://pytorch.org/docs/stable/torch.html?highlight=sigmoid#torch.sigmoid)

I guess you actually are looking for this [https://pytorch.org/docs/stable/nn.html?highlight=cross\_entropy#torch.nn.functional.binary\_cross\_entropy](https://pytorch.org/docs/stable/nn.html?highlight=cross_entropy#torch.nn.functional.binary_cross_entropy)

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 10:37am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/9 "2018-07-19T10:37:28Z")

</div>

I changed my loss function to

```auto
nn.BCELoss()

```

Now iam getting

```auto
  "please use transforms.Resize instead.")
C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\nn\functional.py:1189: UserWarning: Using a target size (torch.Size([1])) that is different to the input size (torch.Size([15])) is deprecated. Please ensure they have the same size.
  "Please ensure they have the same size.".format(target.size(), input.size()))
Traceback (most recent call last):

  File "<ipython-input-1-7e0b4c8bc7b1>", line 115, in <module>
    errD_real = criterion(output, target)

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\nn\modules\module.py", line 357, in __call__
    result = self.forward(*input, **kwargs)

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\nn\modules\loss.py", line 430, in forward
    size_average=self.size_average)

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\nn\functional.py", line 1192, in binary_cross_entropy
    "!= input nelement ({})".format(target.nelement(), input.nelement()))

ValueError: Target and input must have the same number of elements. target nelement (1) != input nelement (15)

```

Iam new to pytorch.I chose pytorch over tensorflow bcoz I love pytorch.Please help me solve this error.Iam doing GAN with pytorcch.

---

<div class="post-metadata">

**Author:** ![chenglu](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/chenglu/32/3901_2.png) [@chenglu](https://discuss.pytorch.org/u/chenglu)\
**Post date:** [July 19, 2018, 10:40am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/10 "2018-07-19T10:40:23Z")

</div>

The error message is very clear, size of targets should be the same of output. Just print the shape of them using `xxx.size()` to debug.

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 10:44am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/11 "2018-07-19T10:44:19Z")

</div>

```auto
target.size()
Out[2]: torch.Size([1])

```

This is the output I got.I gave batch\_size=1.This is the input shape that I got

```auto
input.size()
Out[3]: torch.Size([1, 3, 100, 128])

```

---

<div class="post-metadata">

**Author:** ![chenglu](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/chenglu/32/3901_2.png) [@chenglu](https://discuss.pytorch.org/u/chenglu)\
**Post date:** [July 19, 2018, 10:54am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/12 "2018-07-19T10:54:35Z")

</div>

What you should print is the 2 variable you fed for criterion, which is `output`, `target`.

I suggest you to take a look at the official GAN example [https://github.com/pytorch/examples/blob/master/dcgan/main.py](https://github.com/pytorch/examples/blob/master/dcgan/main.py) .

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 11:04am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/13 "2018-07-19T11:04:30Z")

</div>

```auto
criterion = nn.Sigmoid()
optimizerD = optim.Adam(netD.parameters(), lr = 0.0002, betas = (0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr = 0.0002, betas = (0.5, 0.999))

for epoch in range(25):

    for i, data in enumerate(dataloader, 0):
        
        # 1st Step: Updating the weights of the neural network of the discriminator

        netD.zero_grad()
        
        # Training the discriminator with a real image of the dataset
        real, _ = data
        input = Variable(real)
        target = Variable(torch.ones(input.size()[0]))
        output = netD(input)
        errD_real = criterion(output, target)

```

I have given in the training loop.I created two neural network.One for discriminator and another for generator.I have posted my training code also.

---

<div class="post-metadata">

**Author:** ![justusschock](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/justusschock/32/4637_2.png) [@justusschock](https://discuss.pytorch.org/u/justusschock)\
**Post date:** [July 19, 2018, 1:20pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/14 "2018-07-19T13:20:44Z")

</div>

Your problem is, that the sigmoid is no criterion but an activation meaning it only accepts one input tensor and not two (which would be one for the prediction and one for the target). I think you are looking for the BCELoss instead.

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 1:45pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/15 "2018-07-19T13:45:06Z")

</div>

Yes I changed to BCELoss() but still its showing the same error

---

<div class="post-metadata">

**Author:** ![justusschock](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/justusschock/32/4637_2.png) [@justusschock](https://discuss.pytorch.org/u/justusschock)\
**Post date:** [July 19, 2018, 2:04pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/16 "2018-07-19T14:04:37Z")

</div>

Can you please do

```auto
print(output.size())
print(target.size()) # should be the same as output size

```

Above you are only printing the _input_ size but we need the _output_ size to help you.

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 2:42pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/17 "2018-07-19T14:42:21Z")

</div>

```auto
print(output.size())
print(target.size())
print(input.size())

torch.Size([15])
torch.Size([1])
torch.Size([1, 3, 100, 133])

```

This is my output,target and input shapes.Output and target are different.How to solve this.Should I post my whole code?

```auto

from __future__ import print_function
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.optim as optim
import torch.utils.data
import torchvision.datasets as dset
import torchvision.transforms as transforms
import torchvision.utils as vutils
from torch.autograd import Variable

batchSize = 64 
imageSize = 100 

# Creating the transformations
transform = transforms.Compose([transforms.Scale(imageSize), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),]) # We create a list of transformations (scaling, tensor conversion, normalization) to apply to the input images.

# Loading the dataset
dataset = dset.ImageFolder(root = 'Dataset/', transform = transform) # We download the training set in the ./data folder and we apply the previous transformations on each image.
dataloader = torch.utils.data.DataLoader(dataset, batch_size = 1, shuffle = True, num_workers = 2) # We use dataLoader to get the images of the training set batch by batch.

# Defining the weights_init function that takes as input a neural network m and that will initialize all its weights.
def weights_init(m):
    classname = m. __class__. __name__
    if classname.find('Conv') != -1:
        m.weight.data.normal_(0.0, 0.02)
    elif classname.find('BatchNorm') != -1:
        m.weight.data.normal_(1.0, 0.02)
        m.bias.data.fill_(0)

# Defining the generator

class G(nn.Module):

    def __init__ (self):
        super(G, self). __init__ ()
        self.main = nn.Sequential(
            nn.ConvTranspose2d(100, 512, 4, 1, 0, bias = False),
            nn.BatchNorm2d(512),
            nn.ReLU(True),
            nn.ConvTranspose2d(512, 256, 4, 2, 1, bias = False),
            nn.BatchNorm2d(256),
            nn.ReLU(True),
            nn.ConvTranspose2d(256, 128, 4, 2, 1, bias = False),
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.ConvTranspose2d(128, 64, 4, 2, 1, bias = False),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.ConvTranspose2d(64, 3, 4, 2, 1, bias = False),
            nn.Tanh()
        )

    def forward(self, input):
        output = self.main(input)
        return output

# Creating the generator
netG = G()
netG.apply(weights_init)

# Defining the discriminator

class D(nn.Module):

    def __init__ (self):
        super(D, self). __init__ ()
        self.main = nn.Sequential(
            nn.Conv2d(3, 64, 4, 2, 1, bias = False),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(64, 128, 4, 2, 1, bias = False),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(128, 256, 4, 2, 1, bias = False),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(256, 512, 4, 2, 1, bias = False),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2, inplace = True),
            nn.Conv2d(512, 1, 4, 1, 0, bias = False),
            nn.Sigmoid()
        )

    def forward(self, input):
        output = self.main(input)
        return output.view(-1)

# Creating the discriminator
netD = D()
netD.apply(weights_init)

# Training the DCGANs

criterion = nn.BCELoss()
optimizerD = optim.Adam(netD.parameters(), lr = 0.0002, betas = (0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr = 0.0002, betas = (0.5, 0.999))

for epoch in range(25):

    for i, data in enumerate(dataloader, 0):
        
        # 1st Step: Updating the weights of the neural network of the discriminator

        netD.zero_grad()
        
        # Training the discriminator with a real image of the dataset
        real, _ = data
        input = Variable(real)
        target = Variable(torch.ones(input.size()[0]))
        output = netD(input)
        errD_real = criterion(output, target)
        
        # Training the discriminator with a fake image generated by the generator
        noise = Variable(torch.randn(input.size()[0], 100, 1, 1))
        fake = netG(noise)
        target = Variable(torch.zeros(input.size()[0]))
        output = netD(fake.detach())
        errD_fake = criterion(output, target)
        target.size()
        input.size()
        # Backpropagating the total error
        errD = errD_real + errD_fake
        errD.backward()
        optimizerD.step()

        # 2nd Step: Updating the weights of the neural network of the generator

        netG.zero_grad()
        target = Variable(torch.ones(input.size()[0]))
        output = netD(fake)
        errG = criterion(output, target)
        errG.backward()
        optimizerG.step()
        
        # 3rd Step: Printing the losses and saving the real images and the generated images of the minibatch every 100 steps

        print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f' % (epoch, 25, i, len(dataloader), errD.data[0], errG.data[0]))
        if i % 100 == 0:
            vutils.save_image(real, '%s/real_samples.png' % "./results", normalize = True)
            fake = netG(noise)
            vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png' % ("./results", epoch), normalize = True)

```

I have posted my entire code.Please say me the solution.I have two classes(Dogs and cats).

---

<div class="post-metadata">

**Author:** ![justusschock](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/justusschock/32/4637_2.png) [@justusschock](https://discuss.pytorch.org/u/justusschock)\
**Post date:** [July 19, 2018, 2:50pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/18 "2018-07-19T14:50:27Z")

</div>

Could you please set the batchsize to a higher value than 1 and print the shapes again?

Edit: also you need to remove the `.view(-1)` part in your discriminators forward function.

---

<div class="post-metadata">

**Author:** ![anesh117](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/a/278dde/32.png) [@anesh117](https://discuss.pytorch.org/u/anesh117)\
**Post date:** [July 19, 2018, 3:37pm UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/19 "2018-07-19T15:37:21Z")

</div>

```auto
Traceback (most recent call last):

  File "<ipython-input-5-ede2393ccf01>", line 104, in <module>
    for i, data in enumerate(dataloader, 0):

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 281, in __next__
    return self._process_next_batch(batch)

  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)

RuntimeError: Traceback (most recent call last):
  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 55, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 135, in default_collate
    return [default_collate(samples) for samples in transposed]
  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 135, in <listcomp>
    return [default_collate(samples) for samples in transposed]
  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\utils\data\dataloader.py", line 112, in default_collate
    return torch.stack(batch, 0, out=out)
  File "C:\Users\anesh\Anaconda3\envs\virtual_platform\lib\site-packages\torch\functional.py", line 66, in stack
    return torch.cat(inputs, dim, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 115 and 100 in dimension 2 at c:\anaconda2\conda-bld\pytorch_1519492996300\work\torch\lib\th\generic/THTensorMath.c:2897

```

I changed the batch\_size=10 and removed the view(-1).Iam getting this error.I read that images in a batch must be of equal shape as they are stored as tensor.Thats y I set the batch\_size=1.

---

<div class="post-metadata">

**Author:** ![Aakash\_Bhatia](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/aakash_bhatia/32/13574_2.png) [@Aakash\_Bhatia](https://discuss.pytorch.org/u/Aakash_Bhatia)\
**Post date:** [November 19, 2019, 5:10am UTC](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343/20 "2019-11-19T05:10:29Z")

</div>

Traceback (most recent call last):  
File “/home/akb/pybook/pytorchupandrunning/chapter2/chapter2.py”, line 101, in   
train(model, optimizer, torch.nn.CrossEntropyLoss(),train\_data\_loader, test\_data\_loader)  
File “/home/akb/pybook/pytorchupandrunning/chapter2/chapter2.py”, line 75, in train  
output = model(inputs)  
File “/home/akb/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 547, in **call**  
result = self.forward(\*input)  
TypeError: forward() takes 1 positional argument but 2 were given

Please help me to solve this error.

[Next page](https://discuss.pytorch.org/t/typeerror-forward-takes-2-positional-arguments-but-3-were-given/21343.md?page=2)