Is it possible to auto-size the subsequent input of a layer following torch.nn.Flatten within torch.-CodePudding

If I have the following model class for example:

class MyTestModel(nn.Module):

    def __init__(self):
        super(MyTestModel, self).__init__()

        self.seq1 = nn.Sequential(
            nn.Conv2d(3, 6, 3),
            nn.MaxPool2d(2, 2),
            nn.Conv2d(6, 16, 3),
            nn.MaxPool2d(2, 2),
            nn.Flatten(),
            nn.Linear(myflattendinput(), 120), # how to automate this?
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, 2),
        )
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):

        x = self.seq1(x)
        x = self.softmax(x)
        return x

I know, normally you would let the data loader give a fixed size input to the model, thus having a fixed size for the input of the layer after nn.Flatten(), however I was wondering if you could somehow compute this automatically?

CodePudding user response：

PyTorch (>=1.8) has LazyLinear which infers the input dimension.