Feed a convolutional layer's output to a linear layer?

I am trying to build a convolutional neural network to classify different boat types. I have input images of dimensions [3, 512, 512]. I am unsure as to how to feed the output of convolutional layers into a linear layer in my network.

You should reshape the activation of your conv layer to match the number of input features of your linear layer.
Have a look at the MNIST example.

1 Like