Class SpatialDropout2D

Spatial 2D version of Dropout. This version performs the same function as Dropout, however it drops entire 2D feature maps instead of individual elements.If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease.In this case, SpatialDropout2D will help promote independence between feature maps and should be used instead.

Inheritance
System.Object
Keras
Base
BaseLayer
SpatialDropout2D
Implements
System.IDisposable
Inherited Members
System.Object.Equals(System.Object)
System.Object.Equals(System.Object, System.Object)
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
System.Object.ReferenceEquals(System.Object, System.Object)
System.Object.ToString()
Namespace: Keras.Layers
Assembly: Keras.dll
Syntax
public class SpatialDropout2D : BaseLayer, IDisposable

Constructors

| Improve this Doc View Source

SpatialDropout2D(Single, String, Shape)

Initializes a new instance of the SpatialDropout2D class.

Declaration
public SpatialDropout2D(float rate, string data_format = "", Shape input_shape = null)
Parameters
Type Name Description
System.Single rate

float between 0 and 1. Fraction of the input units to drop.
System.String data_format

'channels_first' or 'channels_last'. In 'channels_first' mode, the channels dimension (the depth) is at index 1, in 'channels_last' mode is it at index 3. It defaults to the image_data_format value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be "channels_last".
Shape input_shape

4D tensor with shape: (samples, channels, rows, cols) if data_format='channels_first' or 4D tensor with shape: (samples, rows, cols, channels) if data_format='channels_last'.

Implements

System.IDisposable