MAEConfig
Options & Configuration · AiDotNet.SelfSupervisedLearning
MAE-specific configuration settings.
For Beginners
MAE (Masked Autoencoder) learns by masking random patches of an image and training the model to reconstruct them.
Constructors
| Constructor | Summary |
|---|---|
MAEConfig() |
Properties
| Property | Summary |
|---|---|
bool? NormalizeTarget { get; set; } |
Gets or sets whether to normalize reconstruction target. |
double? MaskRatio { get; set; } |
Gets or sets the fraction of patches to mask. |
int? DecoderDepth { get; set; } |
Gets or sets the number of decoder transformer blocks. |
int? DecoderEmbedDimension { get; set; } |
Gets or sets the decoder embedding dimension. |
int? DecoderNumHeads { get; set; } |
Gets or sets the number of decoder attention heads. |
int? PatchSize { get; set; } |
Gets or sets the patch size. |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetConfiguration() |
Gets the configuration as a dictionary. |