Documentation ¶
Overview ¶
Package vae implements Auto-Encoding Variational Bayes Algorithm
Index ¶
Constants ¶
View Source
const DecoderCollection = "decoder"
DecoderCollection is the name of collection containing decoder model
View Source
const DefaultBatchSize = 32
default batch size for auto-encoders training
View Source
const EncoderCollection = "encoder"
EncoderCollection is the name of collection containing encoder model
View Source
const LatentCol = "Latent"
Latent is the default name of feature for the decoder
View Source
const RecoderCollection = "recoder"
RecoderCollection is the name of collection containing recoder model
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Model ¶
type Model struct { // size of hidden layer, half of input by default Hidden int // size of additional hidden layer, can be zero Hidden2 int // size of latent (encoder Output/decoder input) layer Latent int // latent layer tensor as output of encoder and input for decoder // vae.LatentCol by default Feature string // generative output for decoder // model.PredictedCol by default Predicted string // Mxnet Context // mx.CPU by default Context mx.Context // batch size // vae.DefaultBatchSize by default BatchSize int // random generator seed // random by default Seed int // optimizer config // nn.Adam{Lr:0.001} by default Optimizer nn.OptimizerConf // input width // normally it's calculated from features Width int }
Model of the Variational Auto-Encoder
Click to show internal directories.
Click to hide internal directories.