General clarification on Convolution layer, but citing the example from LeNet 5

- Input is
`32*32*1`

- First conv layer has 6
`3*3`

filters, with s=1 and p=0. So output of this is `28*28*6`

- First Avg Pooling layer has s=2 and f=2. so output is
`14*14*6`

volume
- In the second layer in the video professor says that the filters are
`5*5`

. But my question is, since the input to the second layer is a `14*14*6`

volume, wouldnt the filter in this layer also be `5*5*6`

Yes, my guess is the only reason Prof Ng does not explicitly mention that is that itâ€™s not a choice, right? You have a choice of f at each layer and you have a choice of how many filters you have, but you donâ€™t have a choice about the input channels: the filters have to match the input channels.

Also note that I edited your post to use the â€ś{}â€ť formatting tool on all the filter shapes, so that we can actually read them. The point is that â€ś*â€ť means â€śitalicsâ€ť in markdown, so you have to make sure that any mathematical expressions get formatted â€śas isâ€ť, not as markdown.

Thank you for the clarification, i just wanted to make sure that I was right about the dimension,

And thank you for explaining about my missing *, I saw that after I posted

Another way is to put a backslash before the asterisk. e.g. `3 \* 5 = 15`

gives 3 * 5 = 15.

2 Likes