Error when trying to parse the encoder output to the decoder

[mvp-aadesh]

Hello,

I am trying to remove the segmentation head and add some more layers before adding segmentation head to my model.
But whenever I pass my encoder output to the decoder I keep getting this Error
My encoder output is a list.
Please let me know what am I missing here.
Error msg:

TypeError                                 Traceback (most recent call last)
[<ipython-input-90-ce779b144a7b>](https://localhost:8080/#) in <cell line: 5>()
      3 sample_input = torch.randn(2, 3, 640, 640).to(device, dtype = torch.float32) / 128.0 - 1.0
      4 y = model.encoder(sample_input)
----> 5 model.decoder(y)

15 frames
[/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py](https://localhost:8080/#) in _conv_forward(self, input, weight, bias)
    547                 self.groups,
    548             )
--> 549         return F.conv2d(
    550             input, weight, bias, self.stride, self.padding, self.dilation, self.groups
    551         )

TypeError: conv2d() received an invalid combination of arguments - got (list, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:
 * (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, tuple of ints padding = 0, tuple of ints dilation = 1, int groups = 1)
      didn't match because some of the arguments have invalid types: (!list of [Tensor, Tensor, Tensor, Tensor, Tensor, Tensor]!, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (int, int)!, !int!)
 * (Tensor input, Tensor weight, Tensor bias = None, tuple of ints stride = 1, str padding = "valid", tuple of ints dilation = 1, int groups = 1)
      didn't match because some of the arguments have invalid types: (!list of [Tensor, Tensor, Tensor, Tensor, Tensor, Tensor]!, !Parameter!, !NoneType!, !tuple of (int, int)!, !tuple of (int, int)!, !tuple of (int, int)!, !int!)

This is my code:

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = smp.DeepLabV3Plus(encoder_name='timm-mobilenetv3_large_075', encoder_weights='imagenet').to(device)
sample_input = torch.randn(2, 3, 640, 640).to(device, dtype = torch.float32) / 128.0 - 1.0
y = model.encoder(sample_input)
model.decoder(y) 

[qubvel]

Hey @mvp-aadesh , you should unpack the list to make it work (add a star to y)

...
model.decoder(*y)