# How do I find output size of a network?

The input to a convolutional layer of a neural network is an image of size $$128\times 128\times 3.$$

$$40$$ convolutional filters of size $$5\times 5$$ are applied to it. Would you get an output? If no then why not? If yes, what will be the output size?

Yes, and it would be $$124 \times 124 \times40$$.

To calculate the output dimensions:

$$(dim_x - filterdim_x + 1) \times (dim_y - filterdim_y + 1) \times filters$$

$$(128 - 5 + 1) \times (128 - 5 + 1) \times 40 = 124 \times 124 \times40$$

• It also depends on padding and stride parameters also @Simon. – Gaurav Koradiya Jul 14 '20 at 4:28
• That is correct. – Simon Larsson Sep 15 '20 at 21:08