I'd like to understand convolutional neural network.
Consider this quote from Stanford CS notes on Convolutional Neural Networks for Visual Recognition (CNNs/ConvNets):

Example Architecture: Overview. We will go into more details below, but a simple ConvNet for CIFAR-10 classification could have the architecture [INPUT - CONV - RELU - POOL - FC]. In more detail:

  • INPUT [32×32×3] will hold the raw pixel values of the image, in this case an image of width 32, height 32, and with three color channels R,G,B.
  • CONV layer will compute the output of neurons that are connected to local regions in the input, each computing a dot product between their weights and a small region they are connected to in the input volume. This may result in volume such as [32×32×12] if we decided to use 12 filters.
  • RELU layer will apply an elementwise activation function, such as the $\max(0,x)$ thresholding at zero. This leaves the size of the volume unchanged ([32×32×12]).
  • POOL layer will perform a downsampling operation along the spatial dimensions (width, height), resulting in volume such as [16×16×12].
  • FC (i.e. fully-connected) layer will compute the class scores, resulting in volume of size [1×1×10], where each of the 10 numbers correspond to a class score, such as among the 10 categories of CIFAR-10. As with ordinary Neural Networks and as the name implies, each neuron in this layer will be connected to all the numbers in the previous volume.

I don't understand why the result of applying convolution to the 32by32by3 input image is not of size 32 by 32 by 3 by 12? From what I understand, we there are 12 filters and we apply each filter to each of the 3 channels of the image to get 3 new images for each filter.

Suppose the result of the first convolution is really 32 by 32 by 12, I don't understand how you get them.

Also, what happen when we do a second convolution? Say we do a second full convolution with 5 filters, then the result of the second convolution is 32 by 32 by 3 by 12 by 5?

  • $\begingroup$ Please dutifully attribute quoted contents. Please do not present text as a pixel raster. $\endgroup$
    – greybeard
    Feb 4, 2020 at 9:03

1 Answer 1


We apply one filter to 32x32x3 image and output 32x32x1 image.And we stack all these twelve 32X32X1 images,which gives 32x32x12 volume.

check this image.In here we apply 5x5x3 kernal to 32x32x3 image with zero padding and stride 1.which gives you 28x28x1 output.if we use 12 filters like this,we get 28x28x12 volume. enter image description here


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.