1
$\begingroup$

Say there is a convolutional layer that has 8 filters of size 3x3 and takes as input 28x28x1 images.

Then the output size will be 26x26x8.

So how are there 8 26x26 feature maps for that layer or just 1 26x26 feature map? If the answer is 1 feature map then how is it created since the output has 8 channels?

$\endgroup$
0
0
$\begingroup$

Each channel corresponds to a $26 \times 26$ feature map, hence the answer to your question is that if the output has dimensions $8 \times 26 \times 26$, the output has 8 feature maps.

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.