InputLayer {Microsoft.VisualBasic.MachineLearning.CNN.layers}

.NET clr documentation

InputLayer

Description

The input layer is a simple layer that will pass the data though and create a window into the full training data set. So for instance if we have an image of size 28x28x1 which means that we have 28 pixels in the x axle and 28 pixels in the y axle and one color (gray scale), then this layer might give you a window of another size example 24x24x1 that is randomly chosen in order to create some distortion into the dataset so the algorithm don't over-fit the training. @author Daniel Persson (mailto.woden@gmail.com)

Declare

            
# namespace Microsoft.VisualBasic.MachineLearning.CNN.layers
export class InputLayer extends DataLink {
   BackPropagationResult: iterates(BackPropResult);
   # the image data size dimension [width, height]
   dims: Dimension;
   # the image data channels, example as color rgb channels, brightness, etc
   out_depth: integer;
   Type: LayerTypes;
}

        

.NET clr type reference tree

1. this class extends from DataLink class: DataLink
2. use by property member BackPropagationResult: iterates(BackPropResult)
3. use by property member dims: Dimension
4. use by property member Type: LayerTypes

---