Add convolutional layer to match other image size

Hello everyone!
I have a network whose first layer is:

nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1), that expects a 3x96x96 image.

I want to add a previous layer in order to make the neural network accept images of 3x384x384 .

I tried to use the formula in the pytorch documentation, but I am not sure if I understood how to use them: Conv2d — PyTorch 1.7.1 documentation

Thank you in advance

You need:
https://pytorch.org/docs/stable/generated/torch.nn.ConvTranspose2d.html
or:
https://pytorch.org/docs/stable/generated/torch.nn.Upsample.html