Convolution layer output size calculation

gistfile1.txt

#Source Aurelion Geron https://colab.research.google.com/github/ageron/handson-ml3/blob/main/14_deep_computer_vision_with_cnns.ipynb#scrollTo=jisXP9jfpKz2
import numpy as np

def conv_output_size(input_size, kernel_size, strides=1, padding="valid"):
    if padding=="valid":
        z = input_size - kernel_size + strides
        output_size = z // strides
        num_ignored = z % strides
        return output_size, num_ignored
    else:
        output_size = (input_size - 1) // strides + 1
        num_padded = (output_size - 1) * strides + kernel_size - input_size
        return output_size, num_padded

conv_output_size(np.array([70, 120]), kernel_size=7, strides=2, padding="same")


https://www.baeldung.com/cs/convolutional-layer-size
Now let’s move on to the main goal of this tutorial which is to present the formula for computing the output size of a convolutional layer. We have the following input:

An image of dimensions W_{in} \times H_{in}.
A filter of dimensions K \times K.
Stride S and padding P.
The output activation map will have the following dimensions:

{W_{out} = {W_{in} - K + 2P}/{S} + 1}
{H_{out} = {H_{in} - K + 2P} / {S} + 1}
If the output dimensions are not integers, it means that we haven’t set the stride S correctly.