vdumoulin / conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Possible typo in Figure 4.6 caption: 2 × 2 input -> 3 × 3 input

hmf opened this issue · comments

commented

Part of the figure 4.6 caption states:

It is equivalent to convolving a 3 × 3 kernel over a 2 × 2 input

I think that should be:

It is equivalent to convolving a 3 × 3 kernel over a 3 × 3 input"

Edit: figure 4.7 may also have he same typo

commented

Just realized this has been pointed out in #18. I was looking at an old version of the document. However, the new version has figure 4.6 corrected, but figure 4.7 was not.