5,321
edits
Convolutional neural network: Difference between revisions
no edit summary
No edit summary |
|||
| Line 9: | Line 9: | ||
** Often includes some type of padding such as zero padding. | ** Often includes some type of padding such as zero padding. | ||
* Upscale layer (for decoders only). | * Upscale layer (for decoders only). | ||
* Normalization or pooling layer (e.g. | * Normalization or pooling layer (e.g. [[Batch normalization]] or Max Pool). | ||
* Activation (typically ReLU or some variant). | * Activation (typically ReLU or some variant). | ||
More traditionally as in the UNet paper, convolutional blocks come in blocks of two conv layers | |||
* Conv2D layer. | |||
* Activation. | |||
* Conv2d Layer. | |||
* Activation. | |||
* Max pool or Avg pool | |||
Upsampling blocks also have a transposed convolution or a bilinear upsample in the beginning. | |||
The last layer is typically just a Conv2D with a possible Sigmoid. | The last layer is typically just a Conv2D with a possible Sigmoid. | ||