Sorry if this sounds basic. But for input_shape, understand that the channel =3 for colored images.

But for black-white and grey-scale images, channel =1?

Thank you

model.add(Conv2D(filters=32, kernel_size=(4,4),input_shape=(28, 28, 1), activation='relu',))
input_shape = image_height, image_width, channels


1 Answer 1


This is indeed correct, when talking about single images a colored RGB image has three channels (R, G, and B) and a black and white has one channel indicating the pixel luminance.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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