@Namespace(value="nvinfer1") public static enum nvinfer.RNNInputMode extends Enum<nvinfer.RNNInputMode>
g
in the first layer of the RNN,
the input vector X[t]
(length E
) is left-multiplied by the gate's corresponding weight matrix W[g]
(dimensions HxE
) as usual, before being used to compute the gate output as described by \ref RNNOperation.
If the RNN is configured with RNNInputMode::kSKIP, then this initial matrix multiplication is "skipped"
and W[g]
is conceptually an identity matrix. In this case, the input vector X[t]
must have length H
(the size of the hidden state).IRNNv2Layer
Enum Constant and Description |
---|
kLINEAR
Perform the normal matrix multiplication in the first recurrent layer.
|
kSKIP
No operation is performed on the first recurrent layer.
|
Modifier and Type | Field and Description |
---|---|
int |
value |
Modifier and Type | Method and Description |
---|---|
nvinfer.RNNInputMode |
intern() |
String |
toString() |
static nvinfer.RNNInputMode |
valueOf(String name)
Returns the enum constant of this type with the specified name.
|
static nvinfer.RNNInputMode[] |
values()
Returns an array containing the constants of this enum type, in
the order they are declared.
|
public static final nvinfer.RNNInputMode kLINEAR
public static final nvinfer.RNNInputMode kSKIP
public static nvinfer.RNNInputMode[] values()
for (nvinfer.RNNInputMode c : nvinfer.RNNInputMode.values()) System.out.println(c);
public static nvinfer.RNNInputMode valueOf(String name)
name
- the name of the enum constant to be returned.IllegalArgumentException
- if this enum type has no constant with the specified nameNullPointerException
- if the argument is nullpublic nvinfer.RNNInputMode intern()
public String toString()
toString
in class Enum<nvinfer.RNNInputMode>
Copyright © 2024. All rights reserved.