Convolutional Networks

Pooling

Compare max, average and min pooling on real values.

Max of the selected window

0, 0, 0, 1

Output = 1

Output size = floor((input + 2×padding − kernel) / stride) + 1floor((5 + 2×0 − 2) / 1) + 1 = 4

Speed ×Step 0 / 15

Opening this lab…

No account required. Local images and model files stay in your browser. Educational models demonstrate mechanisms; they are not production predictors.

Pooling

Continue exploring