【MNIST】PyTorchのsize mismatchエラー

こちらのサイトを元に以下の構成のネットワークをPyTorchで実装しようと思ったのですが、
size mismatch, m1: [128 x 256], m2: [128 x 256]axというエラーが出てきてしまいました。

当方まだ初学者で、ディープラーニングのお作法やPyTorchの記述方法があまりわかっていないので解決方法を教えていただきたいです。

実装したいネットワーク構成

conv - relu - conv- relu - pool -
conv - relu - conv- relu - pool -
conv - relu - conv- relu - pool -
affine - relu - dropout - affine - dropout - softmax

ソースコード(ネットワーク部分)

class CNNModel (nn.Module):
    def __init__(self):
        super(CNNModel, self).__init__()

        self.conv1=nn.Conv2d(1,16,3,1)
        self.conv2=nn.Conv2d(16,16,3,1)
        
        self.conv3=nn.Conv2d(16,32,3,1)
        self.conv4=nn.Conv2d(32,32,3,1)
        
        self.conv5=nn.Conv2d(32,64,3,1)
        self.conv6=nn.Conv2d(64,64,3,1)
        
        self.pool=nn.MaxPool2d(2,2)
        
        self.dropout1=nn.Dropout2d(0.25)
        self.dropout2=nn.Dropout2d(0.5)
        
        self.fc1=nn.Linear(128,256) # ,256
        self.fc2=nn.Linear(256,10)

    def forward(self, x):
        x=self.conv1(x)
        x=F.relu(x)
        x=self.conv2(x)
        x=F.relu(x)
        x=self.pool(x)
        
        x=self.conv3(x)
        x=F.relu(x)
        x=self.conv4(x)
        x=F.relu(x)

        x=self.conv5(x)
        x=F.relu(x)
        x=self.conv6(x)
        x=F.relu(x)
        
        
        x=self.pool(x)
        x=self.dropout1(x)
        
        x=x.view(-1,self.num_flat_features(x)) # 128*256
        
        print(x.size()[0])
        
        x=self.fc1(x)
        x=F.relu(x)
        x=self.dropout2(x)
        x=self.fc2(x)
        x=F.log_softmax(x,dim=1)
        
        return x

エラー詳細

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-5-7a8a290ae702> in <module>
    144         optimizer.zero_grad()
    145 
--> 146         output = cnn.forward(x) # WRITE ME (予測の計算)
    147         loss = loss_fn(output,t) # WRITE ME (損失関数の計算)
    148         loss.backward() # WRITE ME (勾配の計算)

<ipython-input-5-7a8a290ae702> in forward(self, x)
     97         print(x.size()[0])
     98 
---> 99         x=self.fc1(x)
    100         x=F.relu(x)
    101         x=self.dropout2(x)

/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)

/usr/local/lib/python3.7/dist-packages/torch/nn/modules/linear.py in forward(self, input)
     85 
     86     def forward(self, input):
---> 87         return F.linear(input, self.weight, self.bias)
     88 
     89     def extra_repr(self):

/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in linear(input, weight, bias)
   1608     if input.dim() == 2 and bias is not None:
   1609         # fused op is marginally faster
-> 1610         ret = torch.addmm(bias, input, weight.t())
   1611     else:
   1612         output = input.matmul(weight.t())

RuntimeError: size mismatch, m1: [128 x 256], m2: [128 x 256] at /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:283