Images with different input shape about duralava HOT 1 CLOSED

The neural network's size is fixed. If you feed larger input images, also the output of the neural network is going to be larger. Then the shapes don't match anymore.

There are two options:

• Manually changing the neural network by, for example, adding an additional layer, since the input images are now larger.
• Resizing the input to 64x64

In general, any input size that isn't a square is going to be difficult because then the convolutional layers aren't symmetric anymore and it can be quite tedious to design them so that the shapes match everywhere.

from duralava.