0

What does the number 16 (no. of outputs) represent in this Convo layer?

 layers.Conv2D(16, 3, padding='same', activation='relu'),
Sushil Khadka
  • 11
  • 2
  • Hi @ShushilKgadka, welcome to the site. Here you have some context on the concept of "channels" in a convolutional layer. – noe Jun 17 '23 at 22:27

1 Answers1

1

It means that you have 16 filters of 3x3 kernels. If you check the number of trainable parameters, you have : 16 filters x 9 parameters per kernel x 3 channels (for RGB images) + 16 biaises (one per filter) = 448 trainable parameters

Pierre-Loic
  • 111
  • 3
  • So the software knows that both dimensions are $3$ pixels if you only specify one number? I feel like I’ve always specified both dimensions. – Dave Aug 18 '22 at 21:35
  • If you mean the size of the kernel yes , it does understand its a 3 X 3 kernel in case of 1 channel image and 3 x 3 x n in a n channel image. – Saandeep Sreerambatla Aug 19 '22 at 01:18