Convolutional neural network: Difference between revisions
| (4 intermediate revisions by the same user not shown) | |||
| Line 96: | Line 96: | ||
===Stride=== | ===Stride=== | ||
How much the kernel moves. Typically 1 or 2. | How much the kernel moves. Typically 1 or 2. | ||
Moving by 2 will yield half the resolution of the input. | |||
===Padding=== | ===Padding=== | ||
| Line 104: | Line 105: | ||
;Common Types of padding | ;Common Types of padding | ||
* Zero | * Zero or Constant padding | ||
* Mirror/Reflection | * Mirror/Reflection padding | ||
* Replication | * Replication padding | ||
With convolution layers in | With convolution layers in libraries you often see these two types of padding which can be added to the conv layer directly: | ||
* <code>VALID</code> - Do not do any padding | * <code>VALID</code> - Do not do any padding | ||
* <code>SAME</code> - Apply zero padding such that the output will have resolution \(\lfloor x/stride \rfloor\). | * <code>SAME</code> - Apply zero padding such that the output will have resolution \(\lfloor x/stride \rfloor\). | ||