Re-using a classification CNN model for autoencoding - pytorch

Question

I am very new to pytorch so I need a bit of handholding. I am trying to re-use an old CNN classification model -- reusing the already trained convolutional layers as the encoder in an autoencoder and then training the decoder layers. The below code is what I have.

class Autoencoder(nn.Module):
  def __init__(self, model, specs):

    super(Autoencoder, self).__init__()

    self.encoder = nn.Sequential(
        *list(model.conv_layer.children())
        )

    self.decoder = nn.Sequential(
        nn.ConvTranspose2d(in_channels=C7, out_channels=C6, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),
        nn.ConvTranspose2d(in_channels=C6, out_channels=C5, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),
        nn.ConvTranspose2d(in_channels=C5, out_channels=C4, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),
        nn.ConvTranspose2d(in_channels=C4, out_channels=C3, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),
        nn.ConvTranspose2d(in_channels=C3, out_channels=C2, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),
        nn.ConvTranspose2d(in_channels=C2, out_channels=C1, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True), 
        nn.ConvTranspose2d(in_channels=C1, out_channels=C0, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True), 
        nn.ConvTranspose2d(in_channels=C0, out_channels=3, kernel_size=pooling, padding=0),
        nn.ReLU(inplace=True),       
        )
    for param in self.encoder.parameters():
      param.requires_grad = False

    for p in self.decoder.parameters():
      if p.dim() > 1:
        nn.init.kaiming_normal_(p)
        pass

    def forward(self, x):
      x = self.encoder(x)
      x = self.decoder(x)
      return x

However, I am getting a "NotImplementedError". What am I doing wrong? When I initiate an instance of that class, I would be passing the pretrained CNN classification model and self.encoder should take care of taking the layers I am interested from the model (those in conv_layer). When I:

model = pretrainedCNNmodel
autoencoder = Autoencoder(model, specs)
print(autoencoder)

the print looks okay, it has all layers and everything I am hoping for, but when I try to train on it I get the "NotImplementedError:".

Edit

Here is the entire error:

---------------------------------------------------------------------------
NotImplementedError                       Traceback (most recent call last)
<ipython-input-20-9adc467b2472> in <module>()
      2 optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate, weight_decay=L2_lambda)
      3 
----> 4 train(x, train_loader, test_loader, optimizer, criterion)

2 frames
<ipython-input-5-b25edb14cf5f> in train(model, train_loader, test_loader, optimizer, criterion)
     15       data, target = data.cuda(), target.cuda()
     16       optimizer.zero_grad()
---> 17       output = model(data)
     18       loss = criterion(output, target)
     19       loss.backward()

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in forward(self, *input)
     94             registered hooks while the latter silently ignores them.
     95         """
---> 96         raise NotImplementedError
     97 
     98     def register_buffer(self, name, tensor):

NotImplementedError: 

Answer 1

Since you have a bounty on this question, it cannot be closed. However, the exact same question was already asked and answered in this thread.

Basically, you have an indentation problem in your code: Your forward method is indented such that it is inside your __init__ method, instead of being part of the Autoencoder class.

Please see my other answer for more details.