5,321
edits
Convolutional neural network: Difference between revisions
→Kernel
(→Kernel) |
(→Kernel) |
||
| Line 91: | Line 91: | ||
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. | 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 | Similarly, a ''Conv3D'' layer will typically have multiple 4D kernels. | ||
===Stride=== | ===Stride=== | ||