Maxpool node gets added to output of the modle

Required prerequisites

• Make sure you've read the documentation. Your issue may be addressed there.
• Search the issue tracker and discussions to verify that this hasn't already been reported. +1 or comment there if it has.

What commit version of aidge do you use

• aidge_core: dev
• aidge_learning: dev

Problem description

When creating a model with a Maxpool layer, this layer is included in the model outputs.

import aidge_core

model = aidge_core.sequential(
    [
        aidge_core.Conv2D(in_channels=3, out_channels=16, kernel_dims=[3, 3]),
        aidge_core.ReLU(),
        aidge_core.MaxPooling2D(kernel_dims=[2, 2], stride_dims=[2, 2]),
        aidge_core.FC(in_channels=1024, out_channels=10, name="FC_0"), #in_channels is random here
    ]
)

print(list(model.get_output_nodes()))

Returns

[Node(name='', optype='FC', parents: [1, 1, 1], children: [[]]), Node(name='', optype='MaxPooling2D', parents: [1], children: [[1], []])]

Only the FC node should be in there. When using model.get_output_nodes() to get the prediction depending on the list order we might get the Maxpool node instead of the correct output.