5,321
edits
(→Kernel) |
|||
Line 89: | Line 89: | ||
Note that in practice, people use multi-channel inputs so the actual kernel will be 3D. | Note that in practice, people use multi-channel inputs so the actual kernel will be 3D. | ||
A ''Conv2D'' layer with \(C_1\) input channels and \(C_2\) output channels will have \(C_2\) \(3 \times 3 \times C_1\) kernels. | A ''Conv2D'' layer with \(C_1\) input channels and \(C_2\) output channels will have \(C_2\) number of \(3 \times 3 \times C_1\) kernels. | ||
However, we still call this ''Conv2D'' because the kernel moves in 2D only. | However, we still call this ''Conv2D'' because the kernel moves in 2D only. | ||
Similarly, a ''Conv3D'' layer will typically have a 4D kernel. | Similarly, a ''Conv3D'' layer will typically have a 4D kernel. |